Wednesday, December 29, 2010

PSYC 2001: Research Designs

1. Qualitative Research
2. Quantitative Research
3. Experimental Designs
4. Quasi- and Non-Experimental
5. Factorial Designs
6. Correlational Designs

1. Qualitative Research

Other than quantitative research, there are four major approaches to qualitative research:

Naturalistic Observation: describes behaviour in real life.
- Strengths: gives insight into contexts, relationships, behaviours (more real life) and flexible.
- Weaknesses: time-consuming, hard to document, observe – don’t interpret, access may be hard to get, informed consent may be difficult to get, and may not be representative.
Questionnaires.
Conversation Analysis.
Single-Case Study: an in-depth analysis of a single person or small group. If there is no treatment, it’s called a case history.

We can use indirect measures (e.g., observing people) or content analysis (e.g., looking at patterns and themes in written text or media).

Program Evaluation: in order of increasing usefulness, we can use reactions and feelings, learning, changes in skills, and effectiveness to evaluate a program.
- Issue: Participants may not volunteer or may feel coerced to participate.

There are 6 ways to evaluate a program:

Questionnaires: used to quickly/easily access information from a large sample in a non-threatening way.
- Pros: anonymous, cheap, easy to compare and analyze, already exist.
- Cons: getting careful feedback is tough, wording can bias responses, representative sample may not be available, limited to questions on the sheet.
Interviews: used to fully understand someone’s answers or expand on questionnaire responses.
- Pros: full range and depth of information, develops relationship with client.
- Cons: time consuming, hard to analyze and compare, expensive, interviewer can bias response.
Documentation Review: used when we want an impression of how a program operates without interrupting the program (where we review applications, finances, memos, etc).
- Pros: historical information is available, doesn’t interrupt the client, few biases in information.
- Cons: information may be incomplete, no flexibility (you have what exists and nothing more), need to be clear about what you’re looking for (so much data).
Observation: used to gather information about how a program operates (particularly about specific processes).
- Pros: views operations of a program as they are actually occurring, can adapt to events as they occur.
- Cons: difficult to interpret observations, hard to categorize observations, can influence behaviour of participants.
Focus Groups: used to explore a topic in depth with a discussion (useful in evaluations and marketing).
- Pros: quickly and reliably get common impressions, fast and efficient way to get a wide range of information, can convey key information about programs.
- Cons: hard to analyze responses, need a good facilitator, hard to schedule people together.
Case Studies: used to fully understand a client’s experience in a program and conduct comprehensive examination through cross comparison of cases.
- Pros: fully depicts client’s experience, powerful way to portray program to outsiders.
- Cons: time consuming, provides depth but not breadth.

Developing Surveys and Questionnaires

Surveys evaluate attitudes, feelings, experience, and knowledge, whereas questionnaires evaluate aptitudes, abilities, and characteristics.

There are two characteristics of tests:

Reliability: inter-rater reliability and evaluation (split-half – is performance in one section relate to performance in another?; and test-retest – are scores consistent over time?)
Validity: concurrent (do results concur with other tests?) and criterion (does it predict behaviour? Is it meaningful? Is it useful?)

Though we can use existing measures, they can be expensive, intended for special populations, have and restricted access.

There are five types of questions:

Yes-No: easy to mark. Measure with frequency/percentage.
Forced-Alternative: easy to score but nothing ever fits anyone perfectly.
Multiple-Choice: easy to mark.
Likert Scales: people tend not to choose the extremes – if you use even numbers, people have to at least agree/disagree. Measure with a mean/modal response.
Open-Ended: allows a wide variety of responses. Measure by coding first.

Remove questions that have low variability, were omitted or commented on by participants, or do an item analysis (if too many people get it wrong, remove the question).

There are three ways to distribute surveys (in addition to online and interviews):

	Pros	Cons
Mail	No need to be present Potential for larger sample	No idea who completed it Questions may not be answered in order Low sample rate (biased return, 20-30%) Incomplete questions Unanswered questions Answers are not representative
Phone	No need to be present Random sample possible Questions in correct order Survey completed Clarification possible	Random number dialing may call same person twice Hang-ups, blocked calls, screening No visuals in survey Harder to establish a rapport Lower response rate (between mail and in-person)
In Person	High return rate (90%) Answer classification possible Ensures surveys are completed Questions answered in correct order	Time Money Training Interviewer Bias Harder to access (in-home)

2. Quantitative Research

There are five major approaches to quantitative research:

Descriptive Statistics: describes a group using numerical scores on variables.
- Use: often a starting point in research.
- Statistics: mean, median, and standard deviation.
Correlational: where we look for relationships between two or more variables. We measure each participant on each variable but there is no causal inferences.
- Use: for testing theories and help form predictions; often as a secondary analysis.
- Statistics: often requires a linear relationship which is evaluated on strength and direction.
Experimental: tests your hypotheses on the causal effects of the IV on the DV. The IV is actively manipulated and there are two levels. Your participants must be randomly assigned to conditions and you need to specify your procedures for testing your hypothesis. Also, you have to control for major threats to internal validity.
Quasi-Experimental: where we test our hypotheses about relationships between the IV and DV but we have limited ability to actively manipulate the IV or randomly assign participants to conditions. We must still include specific procedures for testing the hypotheses and still control for the major threats to internal validity. We cannot make true causal inferences.
Non-Experimental: see book!

3. Experimental Designs

There are four characteristics of an experimental design:

Two levels of the IV (by manipulating the IV).
Include a measurement variable (DV) to compare the participants in each condition.
Look for consistent differences between groups.
Include control for the major threats to internal validity.

You should also test your hypothesis about the causal effects of the IV, randomly assign participants to conditions, and limit the influence of extraneous variables (so they don’t become confounds).

Causation and Directionality: when we find a relationship between two variables, we have to ensure that we manipulate and control our variables to ensure that we can make a causal and directional conclusion.

Some variables may be hard to manipulate (ethically or logistically).

3.1. Control Groups

A good experiment will always have a control group, otherwise we can’t be sure if the treatment caused the change or whether it was due to some other variable. The control group must receive the exact same experience as the treatment group (with the exception of the actual treatment).

There are two types of control groups:

No-Treatment Group: where the group receives no treatment. This provides a baseline to compare the treatment group with.
Placebo Group: where the group receives a placebo treatment. It helps rule out the possibility that the difference between the treatment and no-treatment group are due to participant expectations and regression to the mean (i.e., people will ‘get better’ without treatment so we have to know if it’s a result of the treatment or time).
- There are three types of placebos:
  - Inert substance – a sugar pill.
  - Sham surgery.
  - False information – telling participants they’re getting the ‘better’ treatment.

Manipulation Check: tests whether the manipulation of the IV actually worked as intended.

3.2. Between-Subject Designs

Between-Subject Design: where we compare scores from separate group (different treatment conditions) to determine which treatment is more effective. Scores are independent.

Groups should be equivalent. The process in which they are created should be the same, they should be treated equally, and they should be composed of equivalent individuals.

Advantages: each score is independent of other scores.
- Not influenced by experience from other treatments (i.e., practice effects).
- Not influenced by fatigue or boredom.
- Not influenced by contrast effects.
Disadvantages:
- Requires a large number of participants (can be difficult with special populations).
- Individual Differences: characteristics that differ from one participant to another; these can become confounding variables and can produce high variability in the scores.
  - Assignment bias (e.g. older versus younger group)
  - Confounding environmental variables

Variance Between and Within Groups

We want variance within groups but we want to control unwanted sources of variance. There are two forms of variance:

Systematic Between-Group Variance: experimental variance due to the IV, or extraneous variance due to confounding variables.
Non-systematic Within-Group Variance: due to chance or individual differences.

To determine if there is a systematic difference between groups, we must compare between-group and within-group variance. If between-group variance is greater than within-group variance, there is a significant, systematic difference, meaning the null hypothesis should likely be rejected.

Using a t-test or ANOVA, we can calculate the difference between groups divided by the difference expected by chance. t = (difference between groups)/(difference expected by chance [error]) or F = (difference between groups)/(difference expected by chance [error])

To determine the variability due to chance, we calculate the signal to noise ratio. The signal to noise ratio must be large in order to conclude that the difference is due to something other than chance.

Noise: the standard deviation.
Signal:
10:3 would be large whereas 8:7 is small
Signal : Noise, where signal > noise.

There are three ways we can control the variance:

Maximize experimental variance: make sure that the differences between groups are real by using a manipulation check or maximizing the effect size.
Control extraneous variance: rule out confounds by making sure the groups are as similar as possible.
Minimize error variance: control your study with careful measurements.

Threats to Internal Validity

There are two major threats to internal validity with this design:

Differential Attrition: if too many participants drop out, your groups may be uneven, creating problems.
Communication between groups:
- Diffusion: where participants from the no-treatment group start using techniques from the treatment group.
- Compensatory Equalization: where the no-treatment group wants the treatment.
- Compensatory Rivalry: where the no-treatment group tries harder than the treatment group to prove themselves.
- Resentful Demoralization: where the no-treatment resents the treated groups and performs poorly.

Applications

Two-Group Mean Difference: where we compare only two groups of participants and the research manipulates only one independent variable with only two levels (single-factor two-group design).

Often used when we compare treatment and control group.
Advantage: simple and provides best opportunity to maximize variance between groups.
Disadvantage: provides little data for comparison (only 2 data sets).

Comparing Means for More than Two Groups: where we compare multiple groups and the research manipulates the independent variables on several levels (single-factor multiple group design).

Advantage: provides stronger evidence for real cause-and-effect relationship.
Disadvantage: minimizes the differences between groups so we have to ensure we manipulate the independent variables sufficiently.

Comparing Proportions for Two or More Groups: when you use nominal or ordinal scales, you can’t compute a mean but you can compare proportions using a chi-square test.

3.3. Within-Subject Designs

Within-Subject Design: where we use a single group of participants and test/observe each individual in all of the different treatments being compared. (Aka. repeated-measures design.) Scores are dependent.

Advantages: requires few participants and eliminates all issues relating to individual differences.
- Possible to measure differences between treatments without involving individual differences.
- Possible to measure differences between individuals – these individual differences can be measured and removed.
- Easier to detect a treatment effect with this design.
Disadvantages:
- Time variables (fatigue, weather) can influence participants and threaten internal validity.
- Participant attrition – counteract this by getting more participants at the outset than you think you’ll need.

There are two major threats to internal validity:

Confounding environmental variables (e.g., morning versus afternoon).
Confounding time variables (history, maturation, instrumentation, testing effects, and regression).

There are two type of order effects:

Carryover Effect: (treatment-specific experience) participant develops new skills/techniques that carries over to the new study
Progressive Error: (general experience)
- Practice Effects: progressive improvement in performance as a participant gains experience.
- Fatigue: progressive decline in performance as a participant gains experience.

Three ways to control time-related threats and order effects:

Controlling Time: shortening the time between experiments can reduce time-related threats to internal validity but increases order effects.
Switch to a Between-Subject Design: whenever you have reason to suspect that order effects will play a substantial role, switch to between-subject design
Counterbalancing – Matching Treatments with Respect to Time: where we change the order in which treatments are given – the goal is to use every possible order of treatments with an equal amount of participants in each sequence
- Note that this method doesn’t eliminate order effects but distributes the effects evenly across treatment groups
- Limitations:
  - Counterbalancing and Variance: counterbalancing increases the variance within the treatment groups.
  - Asymmetrical Order Effects: counterbalancing doesn’t take into account that some treatments may be more demanding (have an unbalanced amount of order effects).
  - Counterbalancing and the Number of Treatments: n! (n factorial) is the number of sequences needed to get a complete counterbalance study; partial counterbalancing can be used (Latin square or randomly assigning treatment group orders).

Applications

Two-Treatment Designs: where there are only two treatment conditions.

Advantages: easy to conduct and results are easy to understand, easy to counterbalance, easy to get a statistical difference.
Disadvantages: doesn’t demonstrate any functional relationship between the two data sets – we can’t know how gradual changes in the independent variable would affect the dependent variable.
Statistical Analysis: t (repeated-measures) or analysis of variance can be used (interval or ratio). For ordinal scales, the Wilcox on test can be used.

Multiple-Treatment Designs:

Advantage: demonstrates stronger cause-and-effect relationship.
Disadvantage: too many treatments may not result in statistically significant variation and increases the amount of time to complete the study which increases participant attrition.

3.4. Comparing Within- and Between-Subject Designs

There are three ways in which these design differ significantly:

When you suspect…	Good for…	Bad for…
Individual Differences	Within-subject	Between-subject
Time-Related Factors and Order Effects	Between-subject	Within-subject
Fewer Participants	Within-subject	Between-subject

3.5. Single-Subject Research Design

Single-subject research designs allow researchers to manipulate IVs and measure the DV with a single person (or small group) and infer a causal relationship. There is no control group.

Useful for studying unusual disorders and unique experiences, or when we’re concerned that group variation will hide individual effects. (Often used in clinical psychology.)
Flexible and you only need one (or a small group of) participant(s).

Classical Research Design: [baseline] – [treatment] – [post-treatment]

ABAB Reversal Design: [baseline] – [treatment] – [baseline] – [treatment]

In the treatment conditions, we’re looking for a full reversal of behaviour so we can conclusively so that the treatment is effecting the behaviour.
The baseline conditions act as the ‘control’.
This can’t be used for treatments that are expected to have long-lasting or permanent effects.

There are three Multiple-Baseline Designs:

Multiple-Baseline Across Subjects: where a baseline is established for multiple participants and the treatment is staggered across (only once) each participant.
Multiple-Baseline Across Behaviours: where baseline behaviours are established for a single participants and treatments are staggered to determine whether the treatment had an effect.
Multiple-Baseline Across Situations: where baseline behaviours are established in two different situations and the treatments are staggered.
All of the multiple-baseline designs follow this pattern:
Observation 1: [---baseline---] [---treatment---]
Observation 2: [---baseline---] [---treatment---]
Strengths: good for treatments with long-lasting effects.
Weaknesses: hard to discern between individual behaviours; treatments may produce a general effect.

There are three other types of single-subject designs:

Dismantling (Component-Analysis) Design: where each phase adds or subtracts one component of a complex treatment to determine how each component contributes to the overall treatment.
Changing Criterion Design: where each phase is defined by a specific criterion that determines a target level of behaviour (e.g., 20 cigarettes a day for the first week, 10 for the next). To ensure there is a correlation between the treatment and the behaviour, researchers often include backward phases (“now have 30 cigarettes!”) to make sure the behaviour is causally related to the treatment.
Alternating-Treatment Design: where two or more treatment conditions are randomly alternated from one observation to the next.

Single-subject designs have low external validity but high internal validity. We can generalize our results using systematic, clinical, and direct replication.

Systematic replication is where we test the effectiveness of a given treatment across a variety of behaviours (e.g., change the participant, setting, or behaviour).
Clinical replication is where we test the effectiveness of a combination of treatments for various behaviours, participants, and settings.
Direct replication is where we test the effectiveness of a given treatment for a single behaviour, multiple times. ABAB design uses this approach.

4. Quasi- and Non-Experimental

Quasi-experimental makes some attempt to reduce threats to internal validity whereas non-experimental makes none. In both cases, the conditions are not changed by manipulating an IV but are defined by pre-existing conditions (e.g., gender, age) or in terms of time (e.g., before and after). These designs look for differences between groups.

There are two categories of designs that can be classified as quasi- or non-experimental:

Between-subject designs, or non-equivalent group designs; and
Within-subject designs, or pre-post designs.

Non-equivalent group (between-subject) designs are so named because the researcher cannot control the assignment of individuals to a group.

All three design subtypes suffer from assignment bias.
The three design subtypes:

Differential Design (non-experimental): where participants are assigned to groups on a particular participant character (such as gender or race). The DV is compared between the groups to see if there is a consistent difference. Similar to correlational research.
Non-Equivalent Group Design (non-experimental): where the control and treatment groups are pre-existing and not randomly assigned.

Posttest-only Non-equivalent Control Group Design: where two non-equivalent groups are compared – they are measured at the same time but only one group receives the treatment.
X O (treatment group)
O (control group)

Pretest-Posttest Non-Equivalent Group Design (quasi): where two non-equivalent groups (treatment and control ) are compared – the treatment group is measured before AND after the treatment whereas the control group is measured twice (before and after) but with no treatment in between.
O X O (treatment group)
O O (control group)

This design reduces assignment bias, limits threats from time-related factors and provides evidence for a cause-and-effect relationship.

History effects that affect groups differently are called differential threats. Time-related threats may occur with all of the above as well.

Pre-post group designs (within-subject) measures the pretest and posttest scores of a group before and after treatment to determine if there’s an effect. There is no control group with this design.

There are three types of designs:

One-Group Pretest-Posttest Design (non-experimental): only one group is used
O X O
Time-Series Design (quasi-experimental): multiple observations are made before and after the treatment. This is often used with predictable events (e.g., a change in law).
O O O X O O O

These designs suffer from time-related threats to internal validity (history, instrumentation, testing effects, maturation, and statistical regression).

Developmental Research Designs: experiments that examine changes in behaviour that are related to age. There are three types:

Cross-Sectional: (between-subject) different cohorts are measured at one point in time and then compared.
- Cohorts: individuals born roughly at the time same and growing up in similar conditions.
- Cohort Effects: differences between age groups caused by unique experiences other than age. (Be careful! Developmental differences may just be cohort effects.)
Longitudinal: examines development by observing or measuring one group of cohorts over time.
Cross-Sectional Longitudinal Designs: compare results obtained from separate samples that were obtained at different times (i.e., many cohorts, many times).

	Cross-Sectional	Longitudinal
Strengths	Time efficient No long-term cooperation required Easier to generalize	No cohort or generation effects Assess individual behaviour effects
Weaknesses	Individual changes not assessed Cohort or generation effects	Time consuming Participant dropout may create bias Potential for practice effects Harder to generalize results

5. Factorial Designs

Experimental factorial designs are studies that contain more than one IV (or more than one factor) and allow us to examine the interactive effects of IVs. This is good for external validity.

We use ANOVA for factorial designs. It’s written to express the number of levels of each IV.

For example, if there are two IVs and the first IV has 2 levels and the second IV has 5 levels, it would be a 2 × 5 factorial design.

A Main Effects describes the individual effect of each IV on the DV.

On a graph, the x variable has an effect if the mean line drawn is not parallel.
On a graph, the y variable has an effect if the mean points are not in the same place.

An Interaction Effect describes the combined effect of two or more IVs on the DV.

On a graph, there is an interaction if the lines are not parallel.

Interaction and Main Effect for BAR

6. Correlational Designs

Correlational designs allow us to measure each participant on each variable and find a relationship between two variables (which is calculated using a correlational coefficient and a scatter plot). This design looks for a relationship between two or more variables.

There are three characteristics of a correlation:

The direction can be upward (+r), downward (−r), or non-existent (r = 0).
The nature of the relationship: linear (Pearson’s r) or curved (Spearman’s rho, ρ).
The consistency or strength. The closer r is to 1, the more consistent the relationship (i.e., the closer the data points appear on the scatter plot).

To interpret a correlation:

The strength of the relationship is indicated by the coefficient of determination (r²). This tells us the variability of one variable that is predicted by another.

For example, if the correlation coefficient r = .80, then r² = .64 which means that 64% of the differences are predictable.
Small (r = .10, medium (r = .30), large (r = .64)
Small (r² = .01, medium (r² = .09), large (r² = .25)

The significance of the relationship is indicated by the statistical significance of the correlation, which means that the result is unlikely to have occurred by random chance.

There are three applications of correlational designs:

Prediction: if x and y are correlated, we can use the x value to predict the y value! We can use a regression line to plot the prediction.
Test-Retest Reliability: where we can see if our first and second tests are positively correlated.
Concurrent Validity: where we can see if our test correlates positively with a well-tested test.

There are strengths and weaknesses of correlational designs:

Strengths:

Describes relationships between variables
Nonintrusive – allows natural behaviour to emerge
High external validity

Weaknesses:

Cannot assess causality
Third-variable problem
Directionality problem
Low internal validity

PSYC 2001: Operational Definitions, Scales of Measurement, and Evaluating Measures

1. Operational Definitions
2. Scales of Measurement
3. Evaluating Measures

Hypothesis: a sentence that clearly states the relationship we expect to see between our IV(s) and DV(s). Variables are stated in operational definition terms.

1. Operational Definitions

Operational Definition (OD): describes your variables in terms of the way you will measure them.

Importance: ODs are necessary in order to replicate studies.
Look at past research to see how variables are operationally defined.

Example of an OD: A nacho can be defined as: the result of covering a corn-chip with cut vegetables (olives, red peppers, mushrooms, and onions) and shredded cheese, and baking it in the oven at 350°C for approximately 15 minutes.

Constructs: hypothetical mechanisms or attributes to explain behaviour (e.g., motivation, self-esteem).

Variables: a characteristic or condition that changes or has different values for different individuals; any measure or characteristic that we use in research

Examples of Typical Psychological Variables:
Cognitive: IQ, memory, reading language
Perceptual: vision, audition, tactile
Social: personality, self-esteem, attachment

There are three types of variables:

Independent Variables (IV): what we manipulate.
Dependent Variables (DV): what we analyze or measure.
Extraneous Variables (EV): any other variable (confound or not) that is not an IV or a DV.

There are two ways to categorize variables:

Categorical (qualitative): descriptive qualities that describe something (e.g., male/female, University attended)
Continuous (quantitative): quantifiable qualities that describe something (e.g., age, height)

Note: we can often convert between the two. For example, I may be 22 (continuous) but I am also an adult (categorical). How you define your variables will depend on your study.

We can have any number and combination of IVs and DVs.

We can also measure variables directly (e.g., IQ can be measured using an IQ test) but others have to be measured using more creative techniques; unfortunately, when we can’t measure something directly, we can’t conclusively get an accurate measurement. We can use constructs to help us measure behaviour.

2. Scales of Measurement

There are four ways to measure variables (NOIR):

Nominal: categorizing variables in no particular order.
- E.g., by gender (male/female/other), or religion (Jewish, Muslim, Hindu)
- Statistics: chi-square; proportions, percentages, and mode.
Ordinal: categorizing variables unequally along a continuum. (We can talk about magnitude.)
- E.g., by satisfaction (1 through 7).
- Statistics: Mann-Witney U; proportions, percentages, mode, and median.
Interval: categorizing variables equally along a continuum. There is no true zero.
- E.g., (temperature) it can be 10°C today and 20°C tomorrow but that doesn’t mean that tomorrow will be twice as hot as today.
- E.g., (IQ) if you have an IQ of zero, you don’t have an absence of intelligence.
- Statistics: t-test or ANOVA; median, mean and standard deviation.
Ratio: categorizing variables equally along a continuum with a true zero.
- E.g., length, height, and reaction times can all have zero values. A 10 second reaction time is twice as fast as a 5 second reaction time.
- Statistics: t-test or ANOVA; median, mean and standard deviation.

In Psychology, we normally use interval scales in tests and measurement.

3. Evaluating Measures

There are three ways to evaluate your measures: the reliability, effective range, and validity.

3.1. Reliability

Reliability: the consistency of a measurement. There are three ways to measure how reliable your study is:

Inter-rater: the degree of agreement between two independent raters.
Test-retest: the degree of consistency (in scores) over time.
Internal Consistency: the degree to which all items of a test measure the same thing. This is often measured using the split-half reliability test, where the scores taken from a random sample of questions match the scores taken from another sample of questions.

There are three factors that influence the reliability of your study:

Clarity: Clarity of your operation definition;
Follow-Through: The extent to which your operational definition is followed; and
Observations: The number of observations the overall score is based on (more is better).

3.2. Effective Range

Effective Range: the range of scores we need to get a good idea of the performance on our dependent variable(s). We have to consider:

Characteristics of the Sample: formulate your study to match the characteristics of your sample. E.g., don’t ask blind people to watch a movie.

Scale Attenuation Effects: where the range is restricted – people above or below the effective range aren’t accurately measured; this distorts the scores, reducing reliability and validity. This can occur in two ways:

Ceiling Effects: there’s an insufficient range at the top of the scale – most high scores are bunched together, preventing us from increasing scores.
Floor Effects: there’s an insufficient range at the bottom of the scale – most low scores are bunched together, preventing us from decreasing scores.

3.3. Validity

There are four major types of validity (ESCI) and five others:

External: the degree to which your study applies to the real world (i.e., generalizability).
- Influenced by: quality of sample selection (e.g., random selection, representativeness).
Statistical: the degree to which your decision about the null hypothesis is reasonable.
- Influenced by: reliability of your measures, ability to meet assumptions of statistical tests used.
Construct: the degree to which underlying theories fit with your results (and vice versa).
- Influenced by: quality of rationalistic reasoning, consideration of possible theories.
Internal: the degree to which your study accurately demonstrates that measured changes were a result of manipulating the IV.
- Influenced by: the degree to which you controlled extraneous confound variables.
- We want to ensure:
  - One Explanation: there should be only one explanation for the results.
  - Groups Differ: the treatment and non-treatment groups differ.
  - Other: we have to consider that other variables may have an effect (e.g., environment, groups, and time variables).
Face Validity: a measure superficially appears to measure what it claims to measure.
Concurrent Validity: scores obtained from a new measure relate to scores obtained from an old, established measure. (Note: this always compares new and old.)
Predictive Validity: scores obtained from a measure accurately predict behaviour according to a theory.
Convergent Validity: strong relationship between scores obtained from two different methods of measuring the same construct.
Divergent Validity: demonstrated by using two different methods to measure two different constructs. Then convergent validity must be shown for each of the two constructs. Finally, there should be little or no relationship between scores obtained for the two different constructs when they are measured by the same method. This shows that we’re measuring one construct, not two. (Note: this always compares new methods.)

3.4. Confounding Variables

We must control our confounding variables only when:

A variable changes systematically with the IV; or
A variable influences the DV.

There are three types of confounding variables (or many threats to internal validity):

Participant: each person has different demographics.
- Subject Effects: people tend to be suspicious when they are in an experiment.
  - Demand Characteristics: where people interpret what the purpose of the experiment is and change their behaviour unconsciously.
  - Hawthorne Effect: people try harder because they’re in an experiment.
  - Social Desirability Bias: tendency to respond in a way that will be viewed favourably by others.
  - Control by using deception, placebos, and single/double-blind designs.
- Selection Effects: use random assignment or match groups to ensure participants are the same before the treatment.
- Attrition Effects: where participants drop-out or die before completing the experiment.
Environmental: experiments may be conducted in different environments.
- Experimenter Effects: experimenters may introduce bias by interpreting the data in a way that supports their hypothesis.
  - Clever Hans: the horse that could understand cues from audiences.
  - Greenspoon Effect: the guy that emphasized the syllables in nouns to demonstrate the experimenter effect.
  - Control by using single/double-blind designs, standardized instructions, and automated and objective measurements or multiple observers.
- Diffusion of Treatment: where treatment effects spread from the treatment to the control group.
Time: over time, time variables may influence the study.
- Sequence/Order Effects: experience with other conditions influences performance in each condition.
  - Control by counterbalancing the order of conditions across participants.
- Practice Effects: experience with a study can influence the performance.
  - Control with counterbalancing.
- Maturation: participants get older and mature during the experiment.
- History: events outside the study that influence a participant’s behaviour.
- Instrumentation: where the instrument used to assess, measure, or evaluate the participant changes over the course of the study.
- Regression to the Mean: where the scores tend to regress to the mean after practice or time.

There are three ways to control confounds:

Holding the variable constant: where we make sure the confound is the same for everyone.
- Con: limits external validity.
Matching: where we match the level of the confound across groups.
- Participants: match by number/proportion or by average. (E.g., each group has 50% males and 50% females, or the average IQ of each group is 120.)
- Environment: (e.g., have each experimenter work is 50% of participants from each group.)
- Time: counterbalance the order of conditions, the time between groups, etc.
- Con: can be intrusive to participants and time consuming (you have to measure the confound ).
Random Assignment: randomly assign participants to treatment and non-treatment groups.
- Advantages: allows us to control many variable simultaneously.
- Disadvantages: only works with large groups – make sure you do a check to compare groups on potential confounds because it may not be ‘random’.

PSYC 2001: Ethics in Research

1. Ethical Guidelines

1. Ethical Guidelines

Ethical guidelines are present in any type of research:

Human: focuses on protecting the rights of participants.
Animal: focuses on proper care and minimizing pain.
- Animals cannot give informed consent.
- This type of research tends to be more invasive.

1.1. Human Research Ethics

All research proposals must be approved by a Research Ethics Board (REB). The first safeguard is an informed consent form. Though we focus on protecting the rights of participants, ethics also applies to the storage of data, anonymity of files, adequate supervision, plagiarism, and honesty with data.

We also have to ensure that our research includes a diverse sample of people, that is, our studies should include all ages, all sexes, and all ethnicities. Before, the majority of research was done on adult, white males.

1.2. General Ethical Guidelines

There are many facets of the guidelines (this is just a sample):

Honesty
Objectivity
Carefulness
Openness
Respect for intellectual property
Confidentiality
Responsible publication
Social responsibility
Non-discrimination
Competence
Legality
Animal care
Human subjects protection

And there are many ethical principles (this is just a sample):

Protection from harm (physical, psychological, and social/economical)
Respect for human dignity and privacy
Minimize use of deception (active and passive)
Free and informed consent
Debriefing

Consent Forms: these are designed to inform the participant of their involvement in the research. When participants give their consent, it must be given intelligently, knowingly, and voluntarily:

Freely: informed consent must be voluntarily given, without manipulation, undue influence or coercion.
Maintained: no undue influence or coercion to continue the study
- Participants always have the right to withdraw but they should also be informed of the consequences beforehand (e.g., what will happen to data already collected, and compensation)

1.3. Ethical Checks

Will the study have informational value?
Does the study pose risks to participants? If so, are there sufficient controls for those risks?
Is there a provision for informed consent?
Is there a provision for adequate feedback?
Do I accept full responsibility for the ethical conduct of the study?
Has the proposal been approved by the REB?

PSYC 2001: Introduction to Research

1. What is Research?

Normally I post notes in the order of the lecture but seeing as I took condensed lecture-book notes for the exam, they are in order of topic rather than lectures.

1. What is Research?

Inductive Reasoning is where you come up with a general theory from specific observations whereas Deductive Reasoning is where you use a general theory and apply it to specific observations.

Methods of Knowledge Acquisition:

Tenacity (habit or superstition)
Intuition (hunch or feeling)
Authority (expert)
Rationalism (reasoning)
Empiricism (direct sensory observation)
Science

Science is different from pseudoscience in that it must withstand rigorous tests.

The Scientific Method: first you develop interest through observation, form a tentative explanation (hypothesis), generate a testable prediction, test the prediction using systematic observations, and evaluate the hypothesis using observations.

Advantages: experimental findings and methods are precise and clear which makes it easier to replicate studies.
Good Science is empirical, public, and objective.

Basic research is done to advance our knowledge whereas applied research is done to help people (for society). Applied science is more funded and often builds on basic research.

Thursday, September 30, 2010

Condensed SOCI 2450 Notes (Criminology)

Normally I post each lecture separately but I found it easier to condense the notes and arrange the similar topics together. Below are the complete but condensed version of the notes from SOCI2450 – Criminology, with Darryl Davies. The class was from September 2010 to December 2010.

Though I am not posting the notes I took from the guest lectures, over the first 2 months we met Williams (Bill) Mullins-Johnson, Paul Kennedy (the chair of public complaints against the RCMP), Alain Olivier, Larry Comeau (retired RCMP officer), and two previous students (lawyer and police officer, Chris and Nick). We watched documentaries on Robert Dziekanski, Beyond Justice (CTV), Mayerthorpe, and Alain Olivier (Mistaken Identity – Operation Deception).

1. Sociological Perspectives of Crime
2. Foundations of Crime
3. Criminal Law
4. Policies on Crime
5. Deterrence
1. 5.1. Parole and Probation
6. Victimology
1. 6.1. Patterns of Victimization
2. 6.2. Perceptions of Victimization

1. Sociological Perspectives of Crime

1.1. Social Structure Perspective

Social Structure Perspective: where crime is a result of an individual’s location within the structure of society (a focus on group). This approach focuses on the social and economic conditions of life. This includes relative deprivation; differential opportunity; discrimination; social disorganization; personal frustration; alternative means to success and sub-cultural values that conflict with conventional values.

There are 3 social structure theories (ESC):

Ecological Perspective (Chicago School): this theory encompasses the geographic, demographic locations, delinquency areas, and concentric circles
1. Criminal Zones: there is more crime in the core of the city
  - Zone 1: businesses
  - Zone 2: residential and businesses
  - Zone 3: working-class homes
  - Zone 4: middle-class citizens (suburbs)
  - Zone 5: mostly suburbs
2. Criminology of Place: emphasizes the importance of geographic location and architectural features as they are associated with crime.
3. Broken Windows Theory: people will be more likely to commit crimes in neighbourhoods where laws are not heavily enforced.
4. Defenceable Space: where you take proactive actions in your neighbourhood to defend your neighbourhood – symbolic barriers to protect your property (e.g., fences, guard dogs) – i.e. making your property safe.

Strain Theory: where society encourages everyone to achieve the same goals without giving them equal opportunities to achieve them. The discrepancy between what society asks for and what the structure of our society permits is what causes crime. There are 5 ways of adapting to strain (CIRRR):

Adaptation	Means (Opportunity)	Goals	Example
Conformist	Accept	Accept	Regular people (middle-high class society)
Innovator	Reject	Accept	Criminals
Ritualist	Accept	Reject	Low-income families
Retreatist	Reject	Reject	Drug addicts
Rebel	Accepts new, rejects old	Accepts new, rejects old	Anarchists

Merton’s Differential Opportunity: where people are more likely to engage in criminal behaviour only if they have access to illegitimate opportunities, versus legitimate opportunities

Culture-Conflict Theory (Sellin): there are two types of conflicts
- Primary Conflict: a clash of cultures occurs in society.
- Secondary Conflict: when those clashes occur, the middle class defines what is and is not criminal.

1.2. Social Process Perspective

Social Processes Perspective: an ‘interactionist perspective’ (i.e., interactions with others) that places primary emphasis on the role of communication and socialization.

There are 4 theories. Social learning, labelling, social control, and social development theory.

Social Learning Theory:
1. Differential Association (Sutherland): people are likely to become deviant if they associate more with people who hold deviant ideas. There are 9 principles of criminal behaviour: it’s learned; it’s learned with others; it’s learned in intimate personal groups; techniques of crime are learned; you will commit a code based on whether you respect the legal code; and the process of learning by associating with criminals is the same as any other learning.
  - A person becomes criminal because of an excess of definitions that are favourable to violations of the law over definitions unfavourable to the law.
  - Differential association may vary in frequency, duration, priority, and intensity.
  - While criminal behaviour is an expression of generic needs and values, it’s not explained by these since non-criminals behaviour is also an expression of those same needs and values.
2. Techniques of Neutralization: techniques that rationalize why you commit crimes. (AC-3D)
  - Appeal to Higher Authorities: defending ourselves against an overzealous state (or defending you family honour)
  - Condemning the Condemners: blaming the people creating the laws
  - Denial of Responsibility: using poverty, abuse, lack of opportunity (external factors) as reasons
  - Denial of Injury: claiming they didn’t intend to cause harm
  - Denial of the Victim: claiming that the person deserved it
Labelling Theory:
1. Tannenbaum: two facets
  1. Tagging: powerful people can apply delinquent labels to less powerful people
  2. Dramatization of Evil: where a person is seen as irrevocably evil (!)
2. Becker: powerful people are more likely to apply delinquent labels to less powerful people and being labelled as such provokes people to live up to the label
  - Deviant: the person to which a deviant label has been applied.
  - Existence: deviance is not a quality that lies in behaviour itself but in the interaction between the person who commits the act and those who respond to it (deviant behaviour is only deviant because it is so labelled).
    - Once a rule is created, someone will eventually break it.
  - Creation: deviance is created by social groups that create rules and infractions that classify certain behaviours as deviant.
  - Consequence: deviance is a consequence of the application of rules and sanctions on offenders.
3. Lemert: the process of becoming deviant has 8 steps from primary to secondary deviance.
  - Primary Deviance: 1st time deviant act – only outsiders view it as deviant.
  - Secondary Deviance: fully-fledged career; you and outsiders view it as deviant.
  - Process from Primary to Secondary Deviance:
    - Primary deviation (primary deviance).
    - Social penalties.
    - Further primary deviation.
    - Stronger penalties and rejection.
    - Further deviation with hostility and resentment.
    - Stigmatized: deviant is labelled as deviant (you hit the tolerance quotient).
    - Your behaviour is strengthened.
    - Acceptance (secondary deviance).
      If you move into a deviant group, you rationalize your behaviour and you continue your behaviour because you fit into the group.
4. Braithwaite: where people are more likely to become delinquent if they are not made to feel ashamed and feel part of society.
  1. Disintegrative Shaming: they are shamed and stigmatized by society which destroys the bond between offender and society.
  2. Reintegrate Shaming: healing circles do shame them but also help reintegrate them back into society (i.e., strengthens the bond between the offender and the community).
Social Control Theory: a lack of social control causes deviance
1. Containment Theory: there are two types – (internal) some people can internally contain their desires (i.e., conscience); (external) some people need external help – the justice system acts as a deterrent.
2. Hirshi’s Social Bond, Self-Control and Control Balance Theory: where people are likely to become delinquent if their bond to society and self-control are weak or if they have a control surplus or deficit.
  There are 4 basic attachment values (BAIC): weak in…
  - Belief in moral values of community (e.g., society agrees on law).
  - Attachment to convention (e.g., attachment to people and institutions, it’s a part of how you define yourself).
  - Involvement in conventional activities (e.g., in prison, we keep offenders busy to prevent riots).
  - Commitment to conformity (e.g., out of fear, people don’t break the law).
Social Development Theory:
- Life-Course Theories: explanations for criminality that recognizes criminogenic influences as having the greatest impact during the early stages of childhood.
  - Development of offending and antisocial behaviour
    - Onset (at what age?)
    - Persistence (how long does it persist?)
    - Desistence (when do we stop?)
  - Risk and Protective factors at different ages
    - Individual risk factors (e.g., IQ, empathy, impulsivity, familial)
    - Protective risk factors
  - Effects of life events on the course of development (e.g., divorce)

1.3. Social Conflict Perspective

There are five fundamental assumptions within the social conflict perspective:

Society is divided by conflict rather than integration and consensus
Society is made up of groups based on political and economic power
Differences in social class and in particular those arrangements within society that maintain class differences are the focus of criminological study
Powerful groups make laws that protect and reflect their interest
Crime is an outcome of conflict between those who have, and those who have not

Social Conflict Perspective: where conflict is a fundamental aspect of life and can never fully be restored. There are 6 major fields of social conflict criminology, radical, critical, feminist, peace-making, restorative, and retributive.

Radical Criminology (Marxist - proactive): there are two fundamental social classes (the haves and the have not’s); the justice system is setup in such a way that supports the ruling class. (Read over the section that deals with Quinny)
Critical Criminology (reactive): emphasizes challenging existing understandings of crimes and uncovering false beliefs.
Feminist: women have been ignored within the field of criminology; this theory emphasizes the recognition of gender equality.
- Gender is not a natural fact but derived from biological sex differences.
- Systems of knowledge reflect men’s views of the natural and social world.
- Women should be at the centre, not at the periphery, of intellectual inquiry.
Peace-making Criminology: holds that crime control agencies and the citizens they serve should work together to alleviate social problems and human suffering; there are five issues:
- The perpetuation of violence through the continuation of social polices based on dominant forms of criminological theories.
- Role of education and peace-making.
- Common sense theories of crime.
- Crime control as human rights enforcement.
- Conflict resolution within a community setting.
Restorative Justice: stresses remedies and restoration rather than punishment.
Retributive Justice: stresses punishment.

The following table outlines the differences between restorative and retributive justice.

	Retributive	Restorative
Crime	An act against the State	An act against an individual
Offender	An individual act with individual responsibility who will be punished in order to deter and prevent future crimes (their punishment depends on past behaviour)	An individual act with social dimensions who must assume responsibility and take action to repair harm in order to reconcile both parties (their reparation depends on the harmful consequences)
Victim	A periphery entity	Central to resolving the crime
Community	A periphery entity and represented by the State	Controls and facilitates the process
Emphasis	Adversarial relationships	Restoration

2. Foundations of Crime

Classical School of Criminology: (reactive) this approach assumes that people have free will, and that punishment can be a deterrent for crime, so long as the punishment is proportional, fits the crime, and is carried out promptly. Jeremy Bentham and Cesare Beccaria were the major players.

There are 11 main points (PRESS-PINKRR):

*Proportionate: punishments must be proportionate to the crime committed and go no further than what’s necessary to deter the offender from injuring fellow citizens.
*Rational: criminal must be treated as a rational and responsible human being.
Exemplary: exemplary penalties are unjust.
*Speed and Certainty: punishments must be inflicted with speed and certainty.
Social Contract: law should be a form of written social contract between you and your justice system.
Prevention: crime prevention can be achieved with clear definitions and the penalties.
Infringe: punishment is justified only insofar as it infringers the rights of others.
Nature of Penalty: the nature of the penalty should correspond to the nature of the crime.
Knowledge: the law should give clear and precise information of what was forbidden and the penalties attached to the forbidden act.
Restrict: the law should restrict an offender as little as possible.
Rights: the law should guarantee the rights of the offender during every step of the justice process.

Becarria has 11 principles:

Law:
- Should be used to maintain the social contract.
- Only legislators should create law.
Judges:
- Should impose punishment in accordance with the law.
- Should not interpret the law.
Punishment should be:
- Based on the pleasure-pain principles.
- Based on the crime, not the offender.
- Determined by the crime.
- Prompt and effective.
Capital punishment should be abolished.
The use of torture to gain confessions should be abolished.
All people should be treated equally.

Positive School of Criminology: (proactive) this approach examines the psychology of criminal behaviour in order to determine how to deter the crimes. Lombroso, Enrico Ferri, and Raphael Garaphelo were the major players.

The following table summarizes the 7 main differences between the classical and positive schools of criminology.

	Classical	Positive
Focus	Offence (Justice)	Offender (Men)
Offender’s responsibility	Offender has free will and therefore is responsible and rational	Offender is influenced by their constitution and environment
Punishment	Strictly related to the crime	Strictly related to the offender
Sentence	Proportionate to the crime	A deterrent to future crimes
Adaptation of penalty to offender’s personality	Against	For
Reform	Against	For

3. Criminal Law

Criminology is the development of the body of knowledge of general and verified principles regarding the process of law, crime, and reactions to crime:

The Making of Law: (sociology of law) a systematic analysis of how crime develops.
The Breaking of Law: (criminal pathology) a scientific analysis of crime.
The Reaction to the Breaking: (penology) a scientific study of the punishment of crime.

In effect, criminal law is a body of specific rules (laws) regarding human conduct which are promulgated by authority (i.e., government) which apply uniformly to all citizens. These rules are enforced through punishment administered by the police, courts and prisons.
Related: criminal behaviour is the violation of criminal law, regardless of immorality or indecency.

There are 4 theoretical origins of the criminal law (CRCG):

Classical Theory: where crimes were against people (not the state) so their process involved 5 transitions (steps) to ensure that the wrong was righted (I-CLIC):
1. Intent: a requirement that the wronged intends to seek vengeance.
2. Consent: a requirement that the wronged secures the consent of the social group before seeking vengeance.
3. Limitation of Harm: the wronged can only apply a limited amount of injury to the wrongdoer.
4. Investigation: the public investigates the merits of the case to ensure all of the above steps were followed correctly.
5. Community Help: the social group may help the wronged get vengeance on the wrongdoer.
Rational Choice Theory: where criminality is a result of conscious choice – people choose to commit crimes when weighing the benefits and costs of disobeying the law. There are two subtypes:
1. Routine Activity: a person’s lifestyle contributes heavily to the volume and type of crime found in any society.
2. Situational Choice: criminal behaviour is a result of decisions and choices made within situational constraints and opportunities.
Crystallization of Mores: where over time, customs and traditions were created that took on the traditions of crimes – criminal law is believed to have originated in and is a crystallization of the Mores (social norms).
Group Theory: where criminal law is believed to have originated in the interests of different groups.

There are 4 characteristics of criminal law (PUPS):

Political: politicians decide what laws will pass; only violations of state-made rules are crimes (violations).
Uniformity: the rule of law is applied evenly to all citizens.
Penal Sanction: for each rule of law, there is a punishment.
Specificity of Deterrence: for each rule of law, the punishment is specific.
- Crimes are acts against the state, whereas
- Torts are actions against individuals, which is processed in civil court.

There are 4 sources of criminal law (CPSS):

Common Law: a judge’s decision in a court case becomes common law.
Procedural Law: provides a mechanism (rules and courts) for enforcing the rights and duties of those that are subject to statutory law. This is the process by which everyone has to follow.
Statutory Law: the written law passed by the legislature (e.g., statutes, Acts, codes).
Substantive Law: (similar to statutory) defines the rights and duties that exist that we expect everyone else to respect. A breach of these rights provides a basis for a lawsuit or criminal action.

There are 6 principles of law (MA-CLIP):

Mens rea: criminal intent must be present.
Actus rea: commission of the guilty act.
Consequences: external consequences must be present before an act can be defined criminal. An injured mental or emotional state is not enough – it has to have a harmful impact on social interests.
Legally Forbidden: the harm must be legally forbidden and prescribed in criminal law.
Intent or Recklessness: the act that creates the harm must be intentional or out of recklessness.
Punishment: there must be a legally prescribed punishment.

4. Policies on Crime

4.1. Policy-Makers

There are 3 entities (3P) that play a role in creating the criminal policies in Canada:

Politicians: elected officials who have the ultimate authority over policies in Canada.
Professionals: anyone that’s involved in the operation and evaluation of the justice system and law enforcement. There are two types:
- People with Operational Responsibilities such as ministerial officials, police chiefs, crown attorneys, judges, defence counsel, correctional authorities, and probation officers.
- People involved in Planning and Research, such as members of policy and research units in the government, as well as scholars and researchers outside the government.
Public: general public and the media, as well as public opinion polls. There are interest groups as well, such as NGOs.

4.2. Standards of Evidence-Based Policies

There are 3 standards of evidence-based policies that help make them effective (ERR):

Evidence: empirical evidence is required to determine the effectiveness of a policy.
Random Assignment: experimental or quasi-experimental research designs must be randomly assigned to treatment and control groups.
Replication: others must be able to replicate the study.

But there are obstacles. Many policies are never evaluated and some policies have harmful effects.

Examples of Ineffective Policies

These are 4 key principles of the “Get Tough on Crime” policy:

Swift, certain, severe punishments will deter crime.
By getting tough with criminals, we can reduce serious crime.
Police officers with more power and resources will reduce crime.
- Research is torn on whether more police increases or reduces crime (displacement effect – we want to be careful we’re not moving crime around).
Longer prison terms will reduce crime.

Scared Straight programs introduce children to offenders in prison to scare them into a life of obedience. Research suggested that they are ineffective (and most said that the program made children worse).

The DARE program is ineffective and costs $2 million/year.

When the Cambridge Summerville Youth Project (30s to 45) was evaluated, they found that for the majority of treatment groups, there was no effect. In the ones where there was an effect size, it demonstrated increased rates of recidivism.

4.3. War on Crime

There is no war on crime. The term itself is wrong (HIM):

High Expectations: by saying it’s a ‘war on crime’, we set our expectations high (e.g., war on crime, drugs, and prostitution).
Incorrect Metaphor: this metaphor is used incorrectly anyways because we’re not fighting a foreign entity – we’re fighting ourselves.
Manufactured Crime: the media manufacture news, thus they manufacture crime.

4.4. Political Ideologies

The role of political ideologies in our war on crime: a crime-control ideology is where a group propagates their beliefs (often religious) without basing them on evidence. There are two main groups in Canada:

Conservative Ideology: those who believe in this ideology contend that…

Criminals commit crimes because they have low impulse control and a low socio-economic status.
Criminals choose to offend and therefore must be punished
Long prison sentences and the death penalty are effective deterrents and decrease recidivism

Conservatives tend to emphasize the rules of substantive law (i.e., criminal law), using the Crime-Control Model, where we put a high priority on the effectiveness of crime control (e.g., arrest, charging, prosecutions, imprisonment).

Liberal Ideology: those who believe in this ideology contend that…

The social context of the crime is important
Criminal behaviour is largely the result of social influences (e.g. low SES, dysfunctional families)
Restorative justice is effective (i.e., treat criminals with rehabilitation)

Liberals tend to emphasize the criminal process (i.e., criminal procedure), using the Due-Process Model, where authorities (i.e., juries, judges, officers) have to try people fairly and assume innocence, i.e., we do our best to prevent the accused from moving forward.

Too much emphasis on criminal law can result in an overpowered government whereas too much emphasis on criminal procedure can result in overpowered criminals.

5. Deterrence

There are 6 common goals of sentencing (DDARRS):

Deterrence:
- Specific Deterrence: reducing the probability that an offender will reoffend in the future.
- General Deterrence: reducing the probability that other members of society will reoffend in the future.
- Absolute Deterrence: a particular punishment will deter a particular crime completely.
- Marginal Deterrence: a particular punishment will reduce a particular crime.
Denounce: to say that we don’t approve of a specific behaviour (e.g., by publishing it in the media).
Assist: to assist the offender with rehabilitation.
- Planned Interventions: programs that help offenders get back on the right path (e.g., CBT, employment programs, skills training)
Reparations/Restitution: to pay back money or society.
- Includes remediation programs – also known as reintegrative justice.
Retribution: balancing the harm done by the offender with punishment (the punishment must fit the type and severity of the crime) – also known as the Just Desserts Model.
Separation/Incapacitation: remove the offender from society to protect them and society.

Deterrence: the certainty of detection and conviction is more important. There are 4 major assumptions of deterrence:

Risk: offenders have to believe in the risk of arrest, conviction, and punishment.
Consequences: offenders have to view the consequences as something to be avoided.
Awareness: offenders have to be aware of the consequences.
Rational: offenders must be rational and weigh the costs and benefits of their actions in order to make decisions.

A Police Officers’ Role in Deterrence

Police officers as a deterrent: increasing the number of police officers arguably does not reduce crime in a community. From the perspective of a police officer:

Resources (police officers) are spread thin over a large area.
A lot of crime is impulsive.
Many crimes cannot be suppressed by police presence (e.g., rape).

For non-impulsive crimes that could be controlled by police, the target audience would need to perceive the threat of arrest, calculate the risk of arrest, understand that the consequences will be unpleasant, and make a rational decision not to commit a crime. This is unlikely.

Though problem-oriented policing can be effective. This is where police officers target hotspots in the community (a large percentage of 911 calls are made from the same individuals). This involves:

Careful planning, scanning, analysis, response, and assessment.
Partnerships with other government agencies and private groups.
Targeting individuals with restraining orders against them and using legal actions against community nuisances.
Independent and rigorous evaluation.

There are four reasons why we should be sceptical about deterrence policies (PLEC):

Psychology: we know little about the processes and perceptions of how risks are formed.
Long-Term Effects: we know little of the long-term effects of crime policies related to deterrence.
Effective Implementation: the impact of particular policies depend on how well they are implemented.
Consistent Implementation: laws and policies are not always implemented as intended.

Against the Death Penalty

There are 5 reasons against the death penalty (ABCD-W):

Attorneys: especially in the US, attorneys aren’t paid well and can’t (or won’t) defend their clients.
Bias: death penalty is biased against Black people and French Canadians.
Cost: less expensive than life sentences though people believe otherwise.
Deterrence:

Myth – offenders think about their crimes before they commit them (they don’t).
Myth – murder rates increase if we don’t have it (they don’t).
Myth – murderers will reoffend once released (they don’t).

Wrongful Convictions: death sentences can be given to the innocent.

For example, states with the death penalty have higher rates of homicide as compared with neighbouring states without the death penalty. And when homicide rates were examined 60-days pre and post executions there was no change in crime rates.

5.1. Parole and Probation

Parole is where an offender is released from their prison sentence early, as opposed to probation, where the offender is put on probation instead of being sentenced to prison. With both, the offender to supervisor ratio is too disproportionate.

Effectiveness of parole: this is measured by the degree of violent offences as compared with the original, and the number of re-offences.

Offenders on day and full parole are more successful than those on statutory release.
Most offenders have high recidivism rates.

Effectiveness of probation: probation is used because it is cheaper than incarceration but the number of salient offender-supervisor visits are particularly important.

Failure rates vary from 12 to 65%.
High recidivism rates.

6. Victimology

Lifestyle theories: important because they define who is at risk for victimization; based on specific propositions:

The probability of suffering a person victimization is directly related to the amount of time that a person spends in public places
The probability of being in public places at night varies as a function of lifestyle
Social contacts and interactions occur disproportionately among individuals who share similar lifestyles
An individual’s chances of personal victimization are dependent on the extent to which the individual shares demographic characteristics with offenders
The proportion of time that an individual spends with non-family members varies as a function of lifestyle

6.1. Patterns of Victimization

If we look at patterns of victimization, we find different types of crimes that are committed which involve different instigators (victim-precipitated and non-victim precipitated):

Victim-precipitated: where the victim instigates the crime but ends up a victim (e.g. wife attacks cheating husband but she is assaulted/dies)
Non-victim precipitated: where the offender instigates the crime

Both the Lifestyle Theory and Routine Activity Approach provide guidelines for reducing victimization.

6.2. Perceptions of Victimization

Media Overrepresentation: The media over-represents victimization, especially stranger-violence and homicide
Routines: lifestyle theories focus on people’s routines and daily activities
- Young lower-class males that work/drive/walk at night are in a higher victimization class
Demographics: lifestyle is influenced in part by demographics such as gender, age, and social status
- Men – victims of robbery and assault
- Women – victims of sexual assault and theft
Age: Age influences victimization
- Young people are the most victimized (15-24)
Social Status: Social status creates a lifestyle risk
- Lower-class Canadians are at a higher risk than affluent families
Single: Single people are at a higher risk of victimization because they participate in more public activities

Tl;dr: Risk of victimization is directly related to your lifestyle.

Saturday, September 04, 2010

WHMIS Training

1. What is WHMIS?
1. 1.1. Introduction to WHMIS
2. 1.2. History of WHMIS
2. Hazard Symbols
1. 2.1. Consumer Symbols
3. Supplier Labels
4. Responsibilities
1. 4.1. Transportation of Dangerous Goods (TDG)
5. Working Safely
1. 5.1. Decanting Flammable Liquids
2. 5.2. Unusual Situations

As a requirement for CHEM1001, we have to complete WHMIS training before our first lab. These are the notes I took (because, you know, safety is important).

1. What is WHMIS?

1.1. Introduction to WHMIS

WHMIS: Workplace Hazardous Materials Information Systems, also known as “Right to know” legislation because you have a right to know about the hazardous materials you work with.

The information about these hazardous materials comes from the supplier, is delivered to your employer who makes it available to you. It comes in three forms:

Supplier labels on product containers – they provide basic safety information;
Material safety data sheets (MSDS); and
Education and training supplied by your employer.

Purpose: to reduce the likelihood of disease or injury caused by hazardous materials while on the job.

1.2. History of WHMIS

WHMIS became law in Canada in 1988; it guarantees that you have the right to know the hazards of the materials that you work with and how to protect yourself from them. This applies only in the workplace.

Controlled Products: products classified under WHMIS laws.

Federal Law: covers the importation and sale of controlled products; this includes the Hazardous Products Act and the Controlled Products Regulations. All hazardous materials must have distinctive WHMIS labels and MSDS’ must be available to purchasers.

Provincial Law: covers the storage, handling and use of controlled products in the workplace. Your employer is responsible for:

Educating and training employees on the safe handling, use and storage of all controlled products in the workplace;
Labelling and identifying WHMIS products; and
Providing employees with easy access to MSDS’ for each controlled product in the workplace.

Partially or Completely Exempt Products: certain products are regulated under other laws and have their own specialized types of labels. Regardless, you have a right to know the hazards of the products in your workplace.

Example of partially exempt: medical devices, explosives and radioactive materials.
Example of completely exempt: wood, tobacco products and hazardous wastes.

3. Hazard Symbols

These are found on supplier labels and are not the same as the ones found on ‘consumer labels’.

	Compressed Gas: compressed, dissolved and liquefied gases; they are usually transported in metal cylinders. Handle carefully – never drop the cylinders! Store in approved areas only Keep cylinders away from heat and fire Examples: oxygen, helium, propane.
	Flammable/Combustible: solids, liquids and gases that catch fire/explode easily – flammables burn more easily than combustibles. Never smoke near these materials Store in approved, fire-protected areas Keep materials away from heat sources and other Flammable/Combustible or Oxidizing materials Containers may need to be grounded against static electric discharges Examples: propane, fire starter briquettes, gasoline.
	Oxidizing: increase the risk of fire if they come into contact with flammable/combustible materials; they may also burn your eyes and skin on contact. Wear protective clothing Do not smoke when handling Store in approved, fire-protected areas Keep materials away from heat sources, flammable/combustibles and other oxidizing materials. Examples: hydrogen peroxide, bleach, liquid chlorine.
	Immediate Toxic: can cause death or serious injury from exposure to small amounts. Handle with extreme caution – wear protective gear Read and follow all safety precautions Avoid skin contact or inhalation of materials – wash or shower thoroughly after using Store in approved areas only Example: cyanide, nerve gas, sulphuric acid.
	Other Toxic: poisonous materials that may cause immediate skin or eye irritation, permanent injury or death through repeated exposure to small amounts over a long period of time. Wear all recommended protective gear and respiratory equipment to protect yourself from skin contact or inhalation Store in approved areas only Example: mercury, coal dust, asbestos fibres.
	Bio-hazardous Infectious: materials that contain germs and micro-organisms that may cause a serious infection resulting in illness or death. Take all necessary precautions to prevent contamination Handle material in designated areas where precautions are in place to avoid exposure Store in approved areas only Example: Hepatitis B virus, contaminated blood, HIV.
	Corrosive: caustic materials and acids which can destroy your skin or eat through metals. The vapours from these materials may also burn your lungs. Wear complete protective equipment as directed Avoid inhalation; use in well ventilated areas and/or with approved respirator Keep containers tight closed and store in approved area Avoid all skin and eye contact Example: battery acid, many oven cleaners, chlorine.
	Dangerously Reactive: materials that undergo dangerous reactions if subjected to heat, shock, pressure to contact with water. Keep away from heat Don’t subject these containers to shocks or excessive movements Open carefully and don’t drop Example: acetylene gas, epoxy resins, butadiene.

3.1. Consumer Symbols

Your employer is discouraged from bringing these into the workplace; if they are poured out of their bottle, WHMIS labels must be applied.

	Poison: may be fatal or cause serious and permanents effects. Can be very toxic, toxic or just harmful. Don’t get in eyes or on skin Don’t breathe fumes Wear personal protective clothing and use safety equipment as indicated on the label
	Corrosive: causes burns to skin, eyes and lungs; may form dangerous vapours if mixed with other substances. Can be very corrosive, corrosive or just irritant. Don’t mix with other chemicals Don’t breathe fumes Don’t get in eyes or on skin Wear personal protective clothing and use safety equipment as indicated on the label
	Flammable: may ignite if exposed to a spark or flame. Can be very flammable, flammable or spontaneously combustible. Use only in well ventilated areas Read and follow instructions Keep away from open flame and other sources of ignition Store in safe location away from sources of ignition
	Explosive: contents under pressure may explode if heated; hazardous contents will escape if ruptured. Can be very toxic, toxic or harmful. Do not puncture or burn Store away from sources of ignition.

4. Supplier Labels

Supplier labels must be labelled before they are delivered to your employer; don’t handle improperly labelled products! They contain 7 types of information:

Product name: common code or chemical name.*
Risk phrases: warn of hazards.
Precautionary statement: tell you what action to take to avoid injury.
Hazard symbols: quick visual warning of dangers.*
First aid measures: outlines first aid measures.
Reference to MSDS*
Supplier name*

All supplier labels are surrounded by a cross-hatched border for easy identification.

Note: Only the product name, hazard symbols, reference to MSDS and supplier name are required on containers that contain 100ml or less.

Using new products: when a new product arrives, read all sections of the supplier label thoroughly. You may want to refer to your work procedures, MDSDS or contact the supplier directly for more information. Pay particular attention to the risk and precautions section.

If an accident occurs: first review the First Aid section of the supplier label and then the spill and leak procedures of the MSDS – if the MSDS is missing, contact the supplier directly.

4.1. Lab Labels

These may not contain the hazard symbols or supplier name. They may also not have the cross-hatched border around the information.

4.2. Lab Samples

If your company sends our lab samples, then you’re considered the supplier. You must supply a standard supplier label and MSDS sheet. If the properties of the sample are unknown and the MSDS label cannot be created, you must label it with a “Hazardous Lab Sample” label; if they are being analyzed for Research and Development, they must include the phrase: “Research and Development Sample. For Laboratory use only.”

4.3. Workplace Labels

These are labels created in the workplace by your employer or you – this often happens when you are transferring materials from a supplier container to a workplace container. If you are using the product immediately and completely, you don’t need to label it. If you are using it completely but over a long period of time, you must label it with the product name. If you are using the product throughout your shift or your coworkers are using it, it must be fully labelled.

If your supplier label is damaged, you can replace it with another supplier label or a workplace label.

You must include: product name, precautionary statements and reference to MSDS. You can include any other information you think is important.

Other means of identification: placards, codes, tags posters or colours are used when it’s not practical to place labels on the containers (such as in tanks or pipes). Examples include:

Controlled products without containers (such as piles of sulphur);
Controlled products just produced but not yet packaged and labelled;
Controlled products being made ready for export; and
Stored hazardous wastes which contain controlled products.

Your employer is responsible for labelling these.

4.4. Data Sheets

MSDS (Material Safety Data Sheet): a printed technical bulletin containing detailed hazard, precautionary and emergency information on a controlled product.

These include 9 sections (foreign products may contain 16 sections):

Production Identification and Use: identifies manufacturer and gives emergency contact information.
Hazardous Ingredients: only contains the hazardous ingredients contained in the substance.
Physical Data: tells you about the look, smell, boiling point, evaporation and specific gravity (where applicable).
Fire and Explosion Data: intended for fire-fighters and management for planning purposes.
Reactivity Data: provides information on the stability of the product and whether it may react when mixed with other chemicals. Refer to this section before using or storing the product near other products.
Toxicological Properties: provides information on the health hazards of the product and the damage it can cause to your body. Refer to this section for detailed view of the Risk Phrases.
Preventive Measures: provides information on preventive measures to take to prevent injury to your body from this product, how to clean up spills and waste disposal. Refer to this section for detailed view of Precautionary Statements.
First Aid Measures: you may refer to this after an accident occurs – you may want to provide medical personnel a copy of the MSDS.
MSDS Preparation Date: this date must be less than 3 years old.

5. Responsibilities

Suppliers must:

Send an MSDS on the first order of a product;
Create supplier labels and MSDS’;
Send an updated MSDS if production information changes; and
Attach supplier labels to containers before shipping.

Employers must:

Ensure supplier labels are attached to products delivered to the workplace;
Ensure labels are maintained and in good reading condition;
Ensure workplace labelling is done;
Ensure MSDS’ are up-to-date and readily available to all employees;
Provide education and training on the controlled products in the workplace and reviewed once a year; and
Provide safe work procedures for controlled products used in the workplace.

Employees must:

Apply the education, training and WHMIS information provided by your employer to protect yourself.
Notify your employer of any circumstances where you do not have adequate information.
Create a workplace label when necessary.

The Government must:

Administer and enforce WHMIS policies;
- Surprise inspections may be done (What are the hazards of the product? What precautions are required for the safe use of this product? What do you do in case of emergency? Where can you get further hazard information?)
- Non-compliance can result in fines and employer imprisonment.

5.1. Transportation of Dangerous Goods (TDG)

When a controlled product is at the supplier or your workplace, WHMIS laws apply. When it’s in transit, TDG laws apply.

6. Working Safely

If exposure to chemicals is unavoidable, you must use Personal Protective Equipment (PPE). Chemicals can enter your body through 5 ways:

Eye/Face: you must wear eye and face gear when you are working with liquid chemicals, gases, vapours, molten metal, certain types of light radiation and where the danger of flying particles exists. Hard hats must be worn if the potential for head injury exists.
Hands: hand protection is required whenever there is a risk of chemical absorption through the skin, cuts or punctures to hands, chemical burns and extreme heat or cold;
- Leather gloves are good for protecting against cuts, abrasions and heat/cold.
- Chemical resistant gloves offer protection from chemicals.
Skin/Body: skin and body protection is required if there’s a risk of exposure to dangerous chemicals, extreme heat or cold, flying particles, or radioactivity. Protection includes chemical overalls, aprons, and leggings; full body suits; leather outerwear; firefighting suits.
Feet: foot protection is required if there is a risk of chemical spillage, absorption from wet floors or puddles, or physical damage from heavy objects.
Respiratory: respiratory protection comes from either air respirators or self-contained breathing apparatus (SCBA); you must choose the proper respirator for the chemicals you are using.

The supplier label will tell you what protective gear to wear.

6.1. Decanting Flammable Liquids

Static electrical charge is created when there is any movement with flammable liquids. If the charge is not dissipated, flammable vapours may be suddenly ignited resulting in a fire or explosion. Before transferring flammable liquids, you must equalize static electricity by grounding and bonding containers.

Grounding cables conduct electrical charge to the ground.

Bonding cables equalize the electrical potential between the containers.

We use welding cables and alligator clamps to connect the ground rod to the dispensing container, and the dispensing container to the receiving container. Only then can you insert the transfer pump – try to minimize the free fall and sloshing of the liquid.

If there is no grounding rod available, attach a bonding cable from the dispensing container to the receiving container.

Plastic funnels and non-conducting metals can increase the generation of static electricity. Don’t use combined plastic/metal containers as they can hold different static charges for extended periods of time.

Use a long spout and if possible, keep the nozzle below the liquid to limit free fall and sloshing.

6.2. Unusual Situations

Follow your employers’ emergency safety guidelines; they take precedence over the information in this section.

Mixing Chemicals: avoid mixing chemicals; always read instructions and mix chemicals in well ventilated areas away from heat sources and open flames.
Spills: ensure the safety of you and your coworkers; immediately advise your supervisor and follow established company procedures.
Decanting Flammables:
Fugitive Emissions: review your company’s procedures for guidance on how to deal with fugitive emissions.
Emergencies: follow your company plan; advise your supervisor, evacuate and call the fire department.

Notes by Lecture Date

Contents

Developing Surveys and Questionnaires

Variance Between and Within Groups

Threats to Internal Validity

Applications

Contents

Contents

Contents

Contents

Examples of Ineffective Policies

A Police Officers’ Role in Deterrence

Against the Death Penalty

Contents