AP Psych Test 9/11

Hypothesis

A testable prediction.

Operational definitions

Defining variables in measurable terms (e.g., “intelligence” as IQ test score).

Wording effects

Subtle changes in wording can influence survey results.

Likert scale

A scale (1–5, strongly disagree → strongly agree) often used in surveys.

Generalizability

Extent findings apply to other groups/situations

Social desirability bias

Participants answer in ways that make them look good.

Sampling bias

Sample not representative of the population.

Representative sample

Sample accurately reflects the population.

Random sample

Each member of population has equal chance of selection.

Population

Entire group being studied

Correlation

Relationship between two variables

Correlational coefficient

Number between –1 and +1 showing strength and direction of correlation

Scatterplots

Graphs showing relationship between two variables

Illusory correlation

Believing a relationship exists when it doesn’t (e.g., superstitions)

Experimental group

Receives the treatment

Control group

Does not receive treatment; baseline for comparison

Random assignment

Randomly putting participants into groups

Double-blind study

Neither participants nor researchers know group assignments

Placebo effect

Improvement due to expectations, not actual treatment

Independent variable

What researcher manipulates

Dependent variable

What is measured

Confounding variable

Extra factor that could influence results

Validity

The experiment measures what it is supposed to measure

Experimenter bias

Researcher’s expectations influence results

Descriptive statistics

Summarize data (mean, median, mode)

Measures of central tendency

Mean, median, mode

Range

Difference between highest and lowest scores

Positive and negative skews

Skewed distributions (tail to right = positive skew, tail to left = negative skew)

Standard deviation

Measure of how spread out data is from the mean

z score

Number of standard deviations a score is from the mean

Inferential statistics

Determine if results can be generalized to a larger population

Statistical significance (p-value)

Likelihood results are not due to chance (usually p < .05)

Identify the advantages and disadvantages of

Case Studies

Give deep, detailed information about one person or group; not always generalizable

Identify the advantages and disadvantages of

Surveys

Quick, large samples; wording effects and self-report bias can distort results

Identify the advantages and disadvantages of

Experiments

Show cause-and-effect by manipulating variables; can be artificial

Identify the advantages and disadvantages of

Meta-analysis

Combines results of many studies for stronger conclusions; limited by the quality of the studies included.

Identify the advantages and disadvantages of

Naturalistic Observation

Observes behavior in real settings; lacks control over variables

Describe positive and negative correlations and explain how correlational measures can aid the process of prediction

Positive correlation

As one variable increases, so does the other (e.g., studying ↑, grades ↑).

Describe positive and negative correlations and explain how correlational measures can aid the process of prediction

Negative correlation

As one variable increases, the other decreases (e.g., exercise ↑, stress ↓)

IMPORTANT

Correlations help predict outcomes but do not prove causation.

Describe the relationship between correlation and causation

Correlation ≠ causation. Just because two things occur together doesn’t mean one causes the other

Example: Ice cream sales ↑ and drowning deaths ↑ → both are influenced by hot weather, not each other

Explain why the double-blind procedure and random assignment build confidence in research findings

Double-blind procedure

Neither participants nor researchers know who gets treatment vs. placebo → reduces bias

Explain why the double-blind procedure and random assignment build confidence in research findings

Random assignment

Participants are randomly placed in experimental or control groups → balances out differences

Discuss the ethics of experimentation with both animals and humans

Human ethics

informed consent, right to withdraw, protection from harm, confidentiality, debriefing

Discuss the ethics of experimentation with both animals and humans

Animal ethics

humane treatment, minimize suffering, only use when benefits outweigh costs

Discuss how hindsight bias…in random events illustrate why science-based answers are more valid than those based on intuition and common sense

Hindsight Bias ("I-knew-it-all-along" phenomenon)

After something happens, people think they could have predicted it. This makes intuition feel more reliable than it really is

Example: After a game, saying “Of course that team was going to win” even though the outcome wasn’t obvious before