RESEARCH METHODS IN SOCIAL PSYCHOLOGY 1. Introduction 2. Ways of Knowing 3. Goals of Research 4. The Scientific Method 5. Research Settings 6. Research Methods 1. Descriptive/Correlational 2. Experimental 7. Theory in Science 8. Research Ethics

Ways of Knowing Tenacity (Faith) Authority Consensus Reason Observation

Goals of Research To “understand” human behaviour Describe Identify and classify regularly occurring sequence of events Explain Suggest why events occurred. Predict Find regularities and predictable relationships that exist between variables Control Regulate the occurrence of the phenomenon

The Scientific Method Observation and Discovery Exploration of a phenomenon which helps to generate hypotheses. Demonstration Gather data to demonstrate, confirm, or support the hypothesis. Refutation Gather data to refute, disconfirm, reject a hypothesis. Replication Repeat the study to examine generalizability, understand contrary evidence, etc.

Research Settings Laboratory Studies Field Studies

Descriptive/Correlational Methods Goals: 1. systematically describe social behaviour 2. systematically describe relations between variables. Some types of descriptive/correlational methods include: 1. Observation studies 2. Archival studies 3. Survey studies

Descriptive/Correlational Methods, cont. Observational Studies Obtrusiveness (Natural Observation to Participant Observation)

Descriptive/Correlational Methods, cont. Archival Studies Archival analysis is a form of the observational method whereby the researcher examines the accumulated documents, or archives of a culture (e.g., diaries, novels, magazines, and newspapers). Inter-judge reliability is the level of agreement between two or more people who independently observe and code a set of data.

Descriptive/Correlational Methods, cont. Survey Studies Verbal (self-) reports Types include Written questionnaire Personal interview Telephone interview

Descriptive Statistics Central Tendency Mean Median Variability Standard deviation

Correlation Correlation Coefficient Scatterplot A measurement of the degree to which two variables are related. Ranges from –1.00 to +1.00. Scatterplot A graphic representation of a correlation; one value is plotted against the horizontal axis and the other against the vertical axis.

Causation Covariation Temporal precedence Third variable The presumed cause (X) and effect (Y) are related to each other. Temporal precedence The X occurred before the resumed effect Y Third variable The relationship between X and Y is not explained by the presence of other plausible causal agents.

Experimental Methods Independent Variable The factor that is systematically manipulated so that the researcher can examine its effect on a dependent variable. Dependent Variable The variable (usually a behaviour) that is affected by the independent variable.

Experimental Methods, continued Random selection or random sampling Every person in a given population has an equal chance of being selected for the sample Random assignment to condition All participants have an equal chance of taking part in any condition of an experiment.

Experimental Methods, continued An operational definition is the specification of how variables are measured, or manipulated. Construct Validity The degree to which both the independent and dependent variables accurately reflect or measure the constructs of interest.

Experimental Methods, cont. Internal Validity The extent to which conclusions can be drawn about the causal effects of one variable on another. See also “experimental realism”

Experimental Methods, cont. External Validity The extent to which the results of a study can be generalized to the larger context Generalizability across situations Generalizability across people Generalizability across cultures See also “mundane realism”

Inferential Statistics Statistical Significance The likelihood that an observed relation or difference between two variables is not due to chance factors. Probability level (p-value): a numerical indicator of how likely it is that the results of an experiment occurred by chance and not because of the independent variable (p < .05 means that there is less than a 5 in 100 probability that the results may be due to chance.)

Bias in Psychological Research Random Error Causes random variability in DV Systematic Error or Bias Causes nonrandom variability in DV other than that caused by the IV.

Types of Bias Sample Bias Measurement Bias Observer’s (Researcher’s) Bias Subject’s Bias

Sample and Measurement Biases Sample Biases Random assignment Measurement Biases Validity Reliability

Observer’s and Subject’s Biases Observer-Expectancy Effects (experimenter/Rosenthal effect) Subject-Expectancy Effects (demand characteristics) Preventing Biases Single-blind study Double-blind study Placebo

What is a Theory (and Related Constructs)? A symbol or an analogy of an observable phenomenon. 2. Model A constructed representation of a part of the universe. 3. Theory A theory attempts to explain a phenomenon. It contains constructs of that phenomenon and describes the relations among these constructs. It incorporates relations between the theoretical constructs and observable variables that can be used to measure those constructs. A theory is not necessarily supported by research findings. Theories are usually partial, incomplete explanations of a phenomenon, subject to expansion and revision. (Continued next slide)

What is a Theory (Continued) 4. Hypothesis A simple declarative statement derived from a theory, usually regarding the nature of a construct and/or its relation to other constructs.

CRITERIA FOR EVALUATING SCIENTIFIC THEORIES 1. Comprehensiveness Explains a wide range of phenomena 2. Internal Consistency Propositions and assumptions are consistent and fit together in a coherent manner. 3. Parsimony Contains only those concepts and assumptions essential for the explanation of a phenomenon. 4. Testability Concepts and relational statements are precise. (Continued next slide)

Criteria for Evaluating Scientific Theories (Continued) 5. Empirical Validity Holds up when tested in the real world. 6. Heuristic Value Stimulates thinking and research. 7. Applied Value Helps solve problems in the real world.

Ethics Informed Consent Risks and Benefits Deception Privacy, Confidentiality, and Anonymity Special Groups

Informed Consent A description of the study should be provided in advance, including mention of: the purpose of the research; expected benefits of the research; methods (tasks to be performed); any effects, risks or inconveniences of the procedure; rights of the participant; and any possible alternative procedures.

Risks and Benefits Protection from harm The onus is on the researcher to avoid or minimize risks to the subjects, both in carrying out the research and in publication of the results.

Deception Deception is a situation in which subjects have essential information withheld and/or are intentionally misled about procedures and purposes. A thorough debriefing is particularly important in studies involving deception.

Privacy, Confidentiality and Anonymity Right to privacy Personal information given by the subject will be confidential. Wherever possible, the researcher will take steps to ensure the anonymity of the subjects.

Vulnerable Groups Special care must be taken with vulnerable groups to ensure ethical treatment (e.g., prisoners, people with mental disabilities, other cultures, etc.)