Lecture 1: Scientific Methods, Knowledge Acquisition, Validity & Reliability, and Experimental Design

A comprehensive set of Q&A flashcards covering the lecture notes on scientific methods, knowledge acquisition, validity/reliability, and experimental design.

What is the scientific method?

A systematic approach to researching and understanding the world using empirical data collection, hypothesis testing, and a commitment to objectivity.

What are the main aims of the scientific method?

Description, pattern identification, prediction, understanding cause-and-effect, and control of phenomena.

What are the four core principles of the scientific approach?

Objectivity (bias minimization), empiricism (data-based evidence), publicness and replicability, and falsifiability with skepticism.

What does skepticism mean in science?

A critical mindset that questions claims and requires evidence that can be tested against reality.

What is empiricism?

Reliance on observations and measurements rather than intuition or authority.

What is a paradigm in science?

A overarching framework or worldview that guides how researchers interpret data and design studies.

What is an axiom in science?

A foundational assumption that follows from a paradigm and is not directly tested in every study.

Which is NOT a central function of a scientific theory?

Proving the absolute, ultimate truth about a phenomenon.

What is a theory in science?

A framework that organizes findings, explains phenomena, guides hypotheses, and may evolve with new evidence.

What is a hypothesis?

A specific, testable prediction derived from theory.

What is operationalization?

Translating abstract constructs into measurable variables or manipulable procedures.

What is the difference between nominal and operational definitions?

Nominal definitions describe the concept (dictionary-like); operational definitions specify how to measure or manipulate it.

What are the two main forms of operational definitions?

Conceptual (measurement of the construct) and experimental/manipulative (how the variable is applied or controlled).

What is reliability in measurement?

The consistency or stability of a measure across time, items, and raters.

What is test–retest reliability?

Stability of scores when the same test is administered to the same people on two occasions.

What is inter-rater reliability?

The degree to which different raters give consistent scores.

What is Cronbach’s alpha (internal consistency)?

A statistic that measures how well items on a scale measure the same construct; higher values indicate greater consistency.

What is validity in measurement?

The extent to which a measure actually assesses what it is intended to measure.

What is content validity?

Expert judgment that the instrument covers the full domain of the construct.

What is convergent validity?

High correlations between measures that are supposed to assess the same construct.

What is discriminant (divergent) validity?

Low correlations between measures of different constructs.

What is predictive validity?

The extent to which a measure predicts future outcomes.

What is concurrent (simultaneous) validity?

The extent to which a measure correlates with a criterion measured at the same time.

What is face validity?

The extent to which a test appears to measure the intended construct to non-experts.

What is construct validity?

The overall validity of a measurement in terms of whether it truly measures the underlying theoretical construct.

What are common threats to internal validity?

History, maturation, instrumentation, regression to the mean, testing, selection, attrition, and interactions among them.

What is randomization in experiments?

Random assignment of participants to conditions to create equivalent groups and reduce bias.

What characterizes a true experimental design?

Manipulation of at least one independent variable, control of extraneous variables, and random assignment.

What is a pretest–posttest with control group design?

Participants are randomized, measured before and after; a control group provides a baseline for comparison.

What is a posttest-only with control group design?

Participants are randomized and measured only after the intervention—no pretest measurement.

What is the Solomon four-group design?

A design that combines pretests and treatments across four groups to control for pretesting and treatment effects.

What is a before-after with control randomized design?

Two groups randomized; measure before, apply treatment to one group, then measure after.

What is Measures repeated (within-subjects) design?

All participants experience every condition, increasing sensitivity but risking order effects.

What is a mixed design?

A design that mixes between-subjects and within-subjects manipulations (at least one IV between and one within).

What is a PV (participant variable) in factorial designs?

A measured attribute of participants (e.g., age, gender, personality) that is not manipulated.

What is an IV × PV design?

A factorial design that includes a manipulated IV and a measured PV to test for differential effects.

In IV × PV designs, can you infer causal effects for PV?

No; causality is inferred for the manipulated IV; PV is correlational.

What is the difference between between-subjects and within-subjects design?

Between-subjects uses different participants in each condition; within-subjects uses the same participants across conditions.

What is matching in experimental design?

Pairing participants on relevant variables and then randomly assigning within each pair to conditions.

What is holding a variable constant (constant variable design)?

Restricting the sample to a fixed value of a potential confounding variable to reduce variance.

What is a main effect in a factorial design?

The overall effect of one independent variable on the dependent variable, averaged across levels of the other IV.

What is an interaction effect?

A situation where the effect of one IV depends on the level of another IV.

What are simple main effects?

The effect of one IV at a specific level of the other IV, used to interpret interactions.

What is an ordinal interaction vs a disordinal interaction in a graph?

Ordinal: lines do not cross (parallel slopes); disordinal: lines cross, indicating a qualitative change in effect.

What is a three-way interaction?

An interaction among three IVs where the two-way interaction between two factors changes across levels of the third.

What is statistical power?

The probability of correctly rejecting a false null hypothesis (1 minus beta), increasing with sample size, effect size, and alpha.

What is a Type I error (alpha)?

Rejecting a true null hypothesis (a false positive).

What is a Type II error (beta)?

Failing to reject a false null hypothesis (a miss).

How do alpha and beta relate in hypothesis testing?

Lowering alpha reduces Type I errors but can increase Type II errors; increasing power reduces the chance of Type II errors.