Advanced Research Methods

What is the main goal of psychology as a science?

To understand the mind by studying observable behavior scientifically.

What makes psychology a science?

It relies on systematic observation, measurement, hypothesis testing, and statistical analysis.

What is the difference between basic and applied research?

Basic research expands theoretical knowledge; applied research solves practical problems.

Define a hypothetical construct.

An unobservable mental concept (e.g., intelligence, motivation, memory).

Define an operational definition.

A specific, measurable way of defining a construct (e.g., motivation measured by persistence time).

What three components must align in measurement?

Hypothetical construct + Operational definition + Measurement tool.

What is a latent variable?

A hidden psychological trait inferred from observable indicators.

What is an experimental method?

Manipulates an independent variable to observe its causal effect on a dependent variable.

What is a survey method?

Collects self-reported data through questionnaires to identify relationships (correlational).

What is an observational method?

Systematically watching and recording behavior in natural or lab settings

What is an interview method?

Direct questioning to gather qualitative data (structured, semi-structured, or unstructured).

Which two methods cannot occur together?

Experimental and survey (cannot manipulate variables in a survey).

Define independent variable (IV).

The factor the researcher manipulates to examine its effect.

Define dependent variable (DV).

The measured outcome affected by the IV.

What are the scales of measurement (lowest → highest)?

Nominal → Ordinal → Interval → Ratio.

Give an example of each scale.

Nominal: gender

Ordinal: satisfaction rank

Interval: temperature (°C)

Ratio: height, reaction time

Why is the distinction between interval & ratio important?

Ratio scales have a true zero → allow ratio statements (“twice as fast”).

Difference between descriptive and inferential statistics?

Descriptive → summarize sample data.

Inferential → use sample data to infer about population.

What are measures of central tendency?

Mean, median, mode.

When should you use the median instead of the mean?

When data are skewed or have outliers.

What are measures of variability?

Range, variance, standard deviation, quartile deviation.

Formula for variance?

Var = Σ(x – M)² / N

Formula for standard deviation?

SD = √Var

What percentage of data fall within ±1 SD in a normal distribution?

~68%. (95% within ±2 SD; 99.7% within ±3 SD)

Formula for z-score?

z = (x – M) / SD

Why are z-scores useful?

They standardize data → compare scores across different measures.

What is correlation?

When two variables vary together; one increases as the other increases/decreases.

What is causation?

When one variable directly influences another.

List Mill’s three criteria for causality.

(1) Temporal precedence, (2) Covariation, (3) Elimination of other causes.

What is a spurious correlation?

An apparent relationship caused by an unseen third variable.

Example of spurious correlation?

Ice cream sales and drowning rates (both due to summer heat).

Define reliability.

Consistency of measurement results across time or items.

Define validity.

Accuracy — whether the tool measures what it claims to measure

Relationship between reliability & validity?

A test can be reliable but not valid; cannot be valid if not reliable.

What is the experimenter effect?

Researcher expectations unintentionally influence results.

How can experimenter effects be reduced?

Use automation or double-blind design.

What is the double-blind procedure?

Neither participant nor experimenter knows who’s in which condition.

What is informed consent?

Participants are told the study’s nature and their rights before participating.

When is deception allowed in research?

Only when necessary and justified → must include debriefing

What is debriefing?

Explaining true purpose of study to participants after participation.

Ethical principles (APA):

Beneficence, Respect, Justice, Integrity, Fidelity & Responsibility.

What are language limitations in research?

When participants cannot communicate (e.g., infants, animals) or language causes bias.

What is social desirability bias?

Participants answer in ways they think are socially acceptable.

How to reduce language or response bias?

Use nonverbal measures or anonymous responses.

When do you use a bar chart vs a histogram?

Bar chart → qualitative (categorical) data; Histogram → continuous numeric data.

What’s the difference between a frequency table and relative frequency table?

Frequency shows counts; relative frequency shows proportions/percentages.

Difference between inductive and deductive reasoning?

Inductive: data → theory (bottom-up).

Deductive: theory → hypothesis → test (top-down).

Why is theory important in research?

It organizes findings, generates predictions, and guides data interpretation.

How do you report descriptive stats in APA?

“M = , SD = ”; italicize symbols.

What is required when using AI tools like ChatGPT in writing?

Must cite properly (APA 7 reference: ChatGPT, OpenAI, 2025)

What is a between-subjects design?

Different participants experience different conditions (e.g., Group A = music | Group B = silence)

What is a within-subjects design?

The same participants experience all conditions → controls for individual differences

Main advantage of within-subjects?

Reduces variability due to individual differences → higher statistical power.

Main disadvantage of within-subjects?

Order or carry-over effects (fatigue, practice, memory).

How do you control order effects?

Use counterbalancing (randomize the order of conditions).

Define random assignment.

Each participant has equal chance of being in any condition → minimizes confounding variables.

What are confounding variables?

Uncontrolled factors that co-vary with IV and can produce false results.

Difference between random sampling and random assignment?

Sampling = who gets selected; Assignment = who goes into which group.

Define population.

Entire group of interest (e.g., all university students).

Define sample.

Subset of population used in the study.

Why sample instead of testing whole population?

Practical limits (time, cost) — samples approximate population behavior.

What is random sampling?

Every member of population has equal chance of inclusion.

What is stratified sampling?

Population divided into strata (e.g., gender, major) → random sample drawn from each.

What is convenience sampling?

Participants chosen based on easy access (e.g., students in class).

What bias can convenience sampling create?

Low generalizability → limits external validity.

Define internal validity.

The degree to which the study truly shows a cause-effect relationship (free from confounds).

Define external validity.

Extent to which results generalize to other people, settings, or times.

Define construct validity.

Whether the test actually measures the theoretical construct intended.

Define ecological validity.

Whether the setting and task represent real-life situations.

How to improve internal validity?

Use random assignment, control extraneous variables, keep procedures consistent

Types of reliability?

Test-retest, inter-rater, internal consistency (Cronbach’s α).

What is test-retest reliability?

Consistency of scores across time.

What is inter-rater reliability?

Agreement between different observers or judges.

What is internal consistency?

Extent to which items on a scale measure the same construct.

Can something be reliable but not valid?

Yes — a bathroom scale always 5 kg off is consistent (reliable) but inaccurate (invalid).

Can something be valid but unreliable?

No — lack of consistency prevents true accuracy.

Example: “Students take a memory test in silence and with music, one week apart.” → Design?

Within-subjects design (counterbalance order).

Example: “Group A studies with music; Group B in silence.” → Design?

Between-subjects design.

If participants are all psychology majors, what’s the limitation?

Low external validity due to convenience sampling.

If participants guess the purpose of the study, what threat occurs?

Demand characteristics → threat to internal validity.

What is risk–benefit analysis?

Weigh potential harm against expected scientific or social benefit.

Role of IRB (Institutional Review Board)?

To evaluate and approve research proposals for ethical compliance.

When must deception be justified?

When truth would alter behavior and no alternative exists; must debrief later.

Why does correlation not equal causation?

Third variables and reverse causality can explain the relationship

Why use both inductive and deductive reasoning in science?

Induction builds theory from data; deduction tests predictions → iterative refinement.