Measuring Behaviour

How Do We Measure?

Psychologists use systematic methods to measure abstract concepts such as behaviour, thoughts, and emotions. Accurate measurement is essential for scientific research.

• Operational Definition: A concrete way to measure an abstract concept. It specifies the variable, event, situation, behaviour, or characteristic that varies and how it will be measured or observed.

• Operational definitions allow researchers to study something objectively and consistently.

• Some operational definitions are better than others, depending on clarity and replicability.

Operational Definitions

• Situational Variables: Characteristics of the environment or situation that can be measured or manipulated (e.g., room temperature, lighting).

• Response Variables: Behaviours or responses that can be measured, such as performance on tasks, reaction time, physiological responses, or self-report measures.

• Behavioural Variables: Actions that can be observed and measured, such as helping others, donating money, or smiling.

• Participant Variables: Characteristics that individuals bring with them, such as age, gender, or intelligence. These can be measured but not manipulated.

Two Things That Make a Good Measure

• Validity: The extent to which a measure assesses what it is supposed to measure (e.g., does a stress scale actually measure stress?).

• Reliability: The consistency or stability of a measure of a variable. Reliable measures yield similar results under consistent conditions.

Research in Psychology

Key Concepts

• Population: The entire group of individuals relevant to a particular study.

• Sample: A subset of the population selected for the study.

• Random Sampling: Every individual in the population has an equal chance of being selected, increasing representativeness.

• Generalizability: The extent to which findings from a sample can be applied to the broader population.

• External Validity: The degree to which study findings can be generalized to other settings, people, or times.

• Ecological Validity: The extent to which study settings approximate real-world conditions.

Random Selection & Generalizability

• Random Selection: Ensures every member of the population has an equal chance of being included in the sample.

• Generalizability: Larger, more representative samples increase the likelihood that findings apply to the population.

• Non-random samples may limit generalizability.

Types of Generalizability

Validity Types

• External Validity: Can the results be generalized to other people, settings, or times?

• Ecological Validity: Does the study setting reflect real-world conditions?

• Internal Validity: The degree to which a study allows for a causal conclusion based on the manipulation of variables.

Case Studies

Case studies involve in-depth examination of a single person or a few select individuals. They are useful for generating new hypotheses and understanding rare conditions but have limited generalizability.

• Cannot generalize to other people easily.

• Cannot make causal claims (low internal validity).

Naturalistic Observation

Researchers observe participants' behaviour in their natural environments without intervention. This method provides high ecological validity but cannot establish causality.

• Useful for describing behaviour.

• Cannot make causal claims.

• Random sampling enhances generalizability.

Correlation Designs

Correlation studies examine the relationship between two or more variables without manipulating them.

• Correlation coefficient () quantifies the strength and direction of the relationship.

• ranges from -1 to 1.

• Correlation does not imply causation.

Correlation Coefficient ()

• Indicates the strength and direction of the relationship between two variables.

• Positive values indicate a direct relationship; negative values indicate an inverse relationship.

Experiments

Basic Experimental Design

Experiments involve manipulating one variable (independent variable) to observe its effect on another variable (dependent variable). Participants are randomly assigned to conditions to control for confounding variables.

Key Features of Experiments

• Internal Validity: The ability to infer that the independent variable caused changes in the dependent variable.

• Control of extraneous variables.

• Elimination of alternative explanations.

• Random assignment increases internal validity.

Ways to Increase Internal Validity

• Experimental Control: Keeping all variables except the independent variable constant.

• Random Assignment: Assigning participants to experimental and control groups by chance, reducing selection bias.

Confounds

• Variables that unintentionally vary with the independent variable and may impact the dependent variable.

• Confounds threaten internal validity.

Random Selection vs. Random Assignment

• Random Selection: How participants are chosen from the population.

• Random Assignment: How participants are assigned to experimental conditions.

Possible Pitfalls of Experiments

• Experimenter Effects: Unintentional cues from the researcher that influence participant behaviour.

• Demand Characteristics: Features of an experiment that inform participants of its purpose, potentially altering their behaviour.

• Deception: Sometimes necessary to prevent demand characteristics, but must be justified and followed by debriefing.

Quasi-Experimental Designs

Quasi-experiments lack random assignment to conditions. They are used when random assignment is not possible, but this limits internal validity.

Ethical Experiments

• Tri-Council Policy Statement: Guidelines for ethical research involving humans in Canada.

• Respect for Persons (Informed Consent): Participants must be informed about all aspects of the research that might influence their decision to participate.

• Risks and Benefits: Researchers must maximize benefits and minimize harm.

• Confidentiality: Protecting participants' privacy and data.

• Distributive Justice: Ensuring that the benefits and burdens of research are distributed fairly among participants.

Statistics

Purpose of Descriptive Statistics

• Summarize mass data for easier understanding and interpretation.

• Visual displays (e.g., graphs) help compare averages between groups.

• Descriptive statistics describe the magnitude and size of relationships between variables.

Measures of Central Tendency

• Mode: Most frequently occurring score.

• Median: The middle score when data are ordered from lowest to highest.

• Mean: The arithmetic average of all scores.

The Mean

• Uses all data points, but is affected by outliers (extreme scores).

• Has mathematical properties useful for statistical analysis.

How Spread Out Are Your Data?

• Variability: The spread in a distribution of scores.

• Measured by range (max - min) and standard deviation.

• Standard Deviation: Indicates how much scores deviate from the mean.

Main and Variability

• Standard Deviation ( or ): A measure of variability that enables reference to the normal distribution, making it meaningful.

• Defines what is "normal" for that variable.

Standard Deviation Formula

The standard deviation for a sample is calculated as:

• = each individual score

• = mean of the scores

• = number of scores