Chapter 2: The Science of Psychology: Research Methods and Statistics: Introduction

Scientific Method

Use evidence to determine whether an idea has merit, needs to be changed and refined, or should just be discarded altogether.

Steps of the Scientific Method

1. Observe a pattern

2. Generate a hypothesis

3. Scientifically test the hypothesis (R: reliable, O: observable, T: testable, V: valid)

4. Interpret results, refine hypothesis

Hypothesis

a specific statement about the study’s expected outcome

Constructs

An abstract concept or variable within a research study.

Operationalization

specifying how we are going to define and measure a particular variable

Archival Studies

analyze materials that were originally gathered, produced, or published for some other purpose
Pro: Data are publicly available and usually inexpensive

Con: Data are limited to what already exists

Naturalistic Observation

Watching and recording people’s behavior where they would have happened anyway, but for research purposes.

Pro: Behavior is authentic and honest

Con: Reactivity and uncontrolled environment

Surveys

Asking questions directly to participants to collect information.

Pro: Large samples can be gathered relatively quickly

Con: Answers may not be honest

Experiments

Pro: Random assignment to condition allows for causal conclusions

Con: Relatively expensive, time-consuming, and/or slow

research designs in which two or more groups are compared to see how they differ by the end of the study. In psychology, there are generally two kinds of experiments—quasi and true.

Reactivity

when people change their behavior when they believe they’re being watched

participant observation

When researchers, like spies, go “undercover” pretending to be part of the natural environment

social desirability

Tendency for participants to provide dishonest survey answers because they want to look good to the researchers or to themselves

Quasi-Experiments

compare preexisting groups; necessary when researchers want to compare groups in interesting ways but can’t create the groups because they have already formed themselves

True Experiments

Compare groups created by the researcher using random assignment.

Random Assignment

gives each participant an equal chance of being put in any of the experimental conditions

between-participants designs

you have multiple groups and each group receives a different treatment.

within-participants design

you have a single group of people who experience multiple treatments or conditions, then you compare their reaction to each condition

Confounding Variables

alternative explanations for the outcomes in an experiment; they are anything that resulted in group differences besides the independent variable

Correlation Analysis

tests whether two constructs (or variables) you’re measuring are systematically tied to each other.

Scatterplots

Graphs used to show patterns between two continuous variables; visual representations of a correlation

Causation

Correlation does not imply causation.

If two things keep happening at the same time, it does not mean that one is causing the other. A third variable could also be the cause.

Spurious correlations

there are unlimited combinations of spurious, or false, correlations where variables appear related but actually represent meaningless patterns

Calculating correlations involves manipulating variables.

False

Scatterplots show patterns between ______.

two continuous variables

t-test

compares averages and ranges of two groups, to see if they are different from each other

Analysis of Variance (ANOVA)

compares three or more groups and tells us if one group is significantly different than the others

ANOVA and t-tests differ in that ______.

an ANOVA examines differences in three or more groups, but t-tests investigate differences in two groups only

Random Sampling

the people in the study were randomly chosen from the larger population of interest; everyone has an equal chance of being selected

allows for generalization

Reliability

whether the measurements were consistent

Internal Validity

the internal structure of the study was set up correctly; the results mean what we think they mean

construct validity

whether methods are measuring the concept that we started with

external validity

whether the results apply to other people or settings

Results that are true for the broader population are said to be ______.

generalizable

Reliability refers to ______ in results.

consistency

Replication

getting the same findings over and over again

Replication Crisis

Only 40% of several classic psychology studies replicated years later.

Open Science Movement

a movement to make scientific research transparent, accessible, cooperative, reproducible, and honest

Preregistration

sharing hypotheses, procedures, and statistical plan for analyses in advance of collecting data

Exploratory research

occurs when a scientist doesn’t have a hypothesis—they’re just curious about some variables that might be related

Results-Blind Peer Review

Peer reviewers assess a study’s procedures before it is conducted—if they agree it has merit, then they accept it for publication

Publication Badges

Incentives for participating in the open science movement

The file drawer problem occurs when ______.

statistically nonsignificant results are not published or shared with others

Deception

Participants should be told the purpose and nature of the study. Deception is only allowed when knowing the truth would change how participants responded.

Debriefing

After the study, all participants can ask about the hypotheses, see the results, understand any deceptions, and receive contact information for their local ethics committee if they want to report concerns or ask questions.

Justification

Research should have a clear purpose and provide results that will increase understanding of the species and/or benefit humans or other animals.

Procedures

Experiments should minimize discomfort; if surgery is needed, animals must be given anesthesia. If animals are observed in their natural field environments, researchers should take care not to disturb the area.

Institutional Review Boards (IRB)

review proposed studies with human participants.

Institutional animal care and use committees (IACUCs)

review proposed studies with nonhuman animals

Created in the 1970s, the ______ contains the strict ethical guidelines that psychologists still follow today.

Belmont Report

Psychologists have always used scientific, ethical approaches to research.

False

Exploratory research lacks ______.

a hypothesis

Why is it difficult to determine why groups differ within quasi-experiments?

There are multiple uncontrolled variables in place within this type of study.

When does the first round of peer review occur for preregistered studies?

once a methodological plan has been submitted

Quasi-experiments compare pre-existing groups.

True

The open science movement strives to increase the number of studies focused on replication of previous work.

True

What is one of the goals of the open science movement?

ensuring more reproducible results

Calculating correlations involves measuring variables and determining how they are tied to one another.

True

W.E.I.R.D.

• W – Western

• E – Educated

• I – Industrialized

• R – Rich

• D – Democratic

The independent variable in a true experiment is the variable manipulated by the researcher.

True

How are participants divided into groups in a true experiment?

through random assignment