How Psychologists Do Research

How Psychologists Do Research

Chapter 2

How Psychologists Do Research What makes psychological research scientific? Research Methods

Descriptive studies Correlational Studies Experiments

Evaluating the findings Keeping the enterprise ethical

Making Psychological Research Scientific

Precision Scepticism Reliance on empirical evidence Willingness to make risky predictions Openness

Precision Theories:

organized systems of assumptions that purport to explain phenomena and their interrelationships.

Hypotheses: attempt to predict or account for a set of phenomena;

specify relationships among variables, and are empirically tested.

Operational definitions: define terms in hypotheses by specifying the operations

for observing and measuring the process or phenomenon.

Scepticism Scientists do not accept ideas on faith or

authority. Scepticism means treating conclusions, both old

and new, with caution.

Willingness to Make “Risky Predictions” Confirmation bias

Tendency to look for or pay attention only to information that confirms one’s own belief.

Principle of Falsifiability A scientific theory must make predictions that are

specific enough to expose the theory to the possibility of disconfirmation; that is, the theory must predict not only what will happen, but also what will not happen.

Reliance on empirical evidence A scientist relies on

empirical evidence to determine whether a hypothesis is true.

Openness Scientists must be willing to tell others where

they got their ideas, how they tested them and what the results were.

Peer review, publishing and replicating research gives science a built-in system of checks and balances.

Descriptive Methods Methods that yield descriptions of behaviour but

not necessarily causal explanations. Include:

Case studies. Observational studies. Psychological tests. Surveys.

Case Studies A detailed description of a particular individual

being studied or treated which may be used to formulate broader research hypotheses.

More commonly used by clinicians; occasionally used by researchers.

Observational Studies Researchers carefully and systematically observe

and record behaviour without interfering with behaviour. Naturalistic observation

Purpose is to observe how people or animals behave in their natural environment.

Laboratory observation Purpose is to observe people or animals in a more

controlled setting.

Psychological Tests Procedures used to measure and evaluate

personality traits, emotional states, aptitudes, interests, abilities, and values.

Psychological tests can be objective or projective. Characteristics of a good test include:

Standardization. Reliability. Validity.

Standardization The test is constructed to include uniform

procedures for giving and scoring the test. In order to score tests in a standardized way, an

individual’s outcome or score is compared to norms. To establish norms, the test is given to a large group

of people who are similar to those for whom the test is intended.

By having norms or established standards of performance, we know who scores low, average or high.

Reliability When constructing a

test, the scores achieved on the test at one time and place should be consistent with the scores achieved at another time and place.

Validity

Content validity The test broadly

represents the trait in question.

Criterion validity The test predicts other

measures of same trait in question.

The ability of a test to measure what it was designed to measure.

Surveys Questionnaires and interviews that ask people

directly about their experiences, attitudes, or opinions.

Should have a representative sample: A group of subjects, selected from the population for

study, which matches the population on important characteristics such as age and sex.

Popular polls and surveys use volunteers rather than representative samples. Leads to volunteer bias or the belief that volunteers may

differ from those who did not volunteer.

Correlational Studies Defining a correlational study Understanding directions of correlations Reading Scatterplots Evaluating Correlations

Correlational Study A descriptive study that looks for a consistent

relationship between two phenomena. Correlation

A statistical measure of how strongly two variables are related to one another.

Correlational coefficients can range from - 1.0 to 1.0. Variables

Characteristics of behaviour or experiences that can be measured or described by a numeric scale;

variables are manipulated and assessed in scientific studies.

Direction of Correlations Positive correlations

An association between increases in one variable and increases in another, or decreases in one variable and decreases in another.

Negative correlations An association between

increases in one variable and decreases in another.

Scatterplots Correlations can be represented by

scatterplots.

Explaining Correlations Start with 3 variables,

(X, Y, & Z) where X and Y are correlated: X might cause Y Y might cause X X might be correlated

with Y, which causes Z

Correlations show patterns, not causes

An Experiment A controlled test of a hypothesis in which the

researcher manipulates one variable to discover its effect on another.

An experiment includes: Variables of interest. Control conditions. Random assignment.

Variables of Interest Independent variables are variables the

experimenter manipulates. Dependent variables are variables that the

experimenter predicts will be effected by manipulations of the independent variable or variables.

Control Conditions In an experiment, a comparison condition in

which subjects are exposed to the same treatment as in the experimental condition.

In some experiments, the control group is given a placebo which is an inactive substance or fake treatment.

Random assignment In order for experiments to have experimental

and control groups composed of subjects similar in characteristics that may effect their results, random assignment should be used.

Each individual participating in the study has the same probability as any other of being assigned to a given group.

Experimenter Effects Unintended changes in subject’s behaviour due to

cues inadvertently given by the experimenter. Strategies for preventing experimenter effects

include single and double-blind studies.

Descriptive Statistics

Statistical procedures that organize and summarize research data.

Examples include: Arithmetic mean Standard deviation

Inferential Statistics Statistical procedures that allow researchers to

draw inferences about how statistically meaningful a study’s results are.

The most commonly used inferential statistics are significance tests: Statistical tests that show how likely a study’s results

occurred merely by chance.

Choosing the Best Explanation Interpretation of results may depend on how the

research was conducted. Cross-sectional studies involve subjects of different

ages being compared at a given time. Longitudinal studies involve subjects who are

periodically reassessed over a period of time.

Judging the Result’s Importance Statistical techniques such as effect size and meta-

analysis can help us determine if results are really important. Effect size is the amount of variance among scores in the

study accounted for by the independent variable. Meta-analysis is a procedure for combining and analyzing

data from many studies. It determines how much of the variance in scores across all studies can be explained by a particular variable.

Ethical Dilemmas Ethics Considerations in Human Research Ethics Considerations in Animal Research

The Ethics of Studying Humans Informed consent

Prospective participants should receive enough information to let them decide freely whether to participate.

Freedom to withdraw at any time Minimize discomfort Keep data confidential If deception is necessary, debriefing must occur

The Ethics of Studying Animals Animals have always been used in a small

percentage of psychological studies. To conduct basic research. To discover practical applications. To study issues that cannot be studied.

experimentally with human beings. To clarify theoretical questions. To improve human welfare.