Intro to Psychology basic processes - Chapter 2: Research

Research enterprise

A way of studying behavior in a systematic fashion.

Research

How we investigate questions about human behaviour

Research (con’t)

Uses specific strategies

e.g. The scientific approach/method (hypothesis and conclusion)

Participants

The persons or animals whose behaviour is systematically observed in a study

Experiment

A powerful research method in which the investigator manipulates a variable under care-fully controlled conditions and observes whether any changes occur in a second variable as a result

Experiment (con’t)

Allows researchers to detect cause-and-effect relationships, and is depended on more than any other method by researchers

Empirical approach

An objective and systematic fashion of observing behaviour.

Measurement and description

A goal of psychology that involves figuring out what is being measured and how to define or describe the behaviour being observed.

e.g. Developing a means of measuring emotions

Operational definition

The process of defining specific variables in an experiment that describes the actions or operations that will be used to measure or control a variable

e.g. determining how much and what kind of drug is being measured.

Understanding and predicting

A goal of the scientific enterprise is for researchers to make predictions about behaviour as a test of their understanding.

Hypothesis

A tentative statement about the relationship between two or more variables.

Variables

Any measurable behavior.

Application and control

The goal of taking research findings and using them to solve everyday problems or isolate the effects of specific variables.

Control

The ability in a research environment to account for other confounding variables or extraneous influences to clarify the understanding of behavior.

Theory

A system of integrated and interrelated ideas used to explain a set of behavioural observations.

Freudian theory

A theory that is challenging to test because concepts like unconscious motives are difficult to define, describe, or measure.

Testable

Scientific theories must be testable and must be able to have scientific methods applied to them in the practice of research

Replication

The requirement that research findings be reproducible to ensure a theory is correct.

Clarity and precision

An advantage of the scientific approach derived from its systematic nature and the exact formulation of hypotheses.

Intolerance of errors

A characteristic of the scientific approach's rigorous process, which uses controls to manage competing explanations for why variable $X$ is causing behavior $Y$.

Hypothesis

A formulated prediction based on theory, such as the statement that chocolate causes happiness.

Designing the study

Choosing a specific method to test the hypothesis

e.g. Surveys, experiments, case studies

Collecting data

Procedures for recording or measuring empirical behavioural observations

e.g. Direct observations, interviews, questionnaires, etc

Analyzing the data

Converting observations into numbers, and then analyzing the numbers using statistics to draw a conclusion

Reporting the findings

Writing a research article for a (usually rigourosly peer-reviewed) journal

Journal

A periodical that publishes technical and scholarly material, usually in a narrowly defined area of inquiry

Operational definition

The process of specifically defining concepts or constructs, such as happiness and chocolate, so they can be measured in a study.

Archival data

Existing data used by researchers to test out a particular hypothesis and theory.

Descriptive and inferential statistics

Statistical methods applied to analyze numerical data to determine if there is support for a research hypothesis.

Peer-reviewed articles

Research write-ups published in journals that are reviewed by university peers to determine if the findings are worthy of distribution to the academic community.

Constructs

Abstract concepts, such as happiness or chocolate, that must be represented by specific variables in an experiment.

Experimental Design

Considered the gold standard in psychological research designs for determining causal relationships.

Independent Variable (X)

The condition or event that an experimenter varies or manipulates to see what impact it has on another variable (Y).

Independent Variable (X) [con’t]

Is called such because it is free to be varied by the experimenter.

Dependent Variable (Y)

The variable that is observed and measured to see how it is affected by the manipulation or variation of the independent variable (X).

Dependent Variable (Y) [con’t]

Is called such because it is thought to depend (at least in part) on manipulations of the independent variable.

Experimental Group

The group of participants in a study who receive the treatment or event

e.g. Getting chocolate

Control Group

The group of participants who do not receive the treatment (no chocolate) and serve as a comparison to the experimental group.

Reactivity

When a participant’s behaviour is altered by the presence of the observer

Case studies

An in-depth investigation of an individual participant or group of participants

Case studies (con’t)

Are particularly well suited for investigating certain phenomena, such as psychological disorders and neuro-psychological issues.

Post-test

The reassessment of the dependent variable that’s conducted after the experimental group receives the treatment to determine if changes occurred compared to the pre-test

Causal Conclusion

The determination of whether the independent variable (X) directly caused a change in the dependent variable (Y).

Control Group

The group that does not receive the treatment or manipulation, serving as a baseline; in this study, the group that received no chocolate (the odd-numbered condition).

Random Assignment

A protocol where participants have an equal chance of being assigned to any condition to ensure groups are equal in demographic makeup and that no pre-existing differences impact the results.

Table of Random Numbers

A traditional tool used to assign participants into experimental groups before digital methods became common.

e.g. An even or odd number will determine which group a person will be assigned to

Pre-test

The initial measurement taken before the experimental event is performed

e.g. The subjective happiness scale administered at the start of the study.

Subjective Happiness Scale

The specific measurement tool used in the study where the sum scores of $4$ items are averaged for each person and group.

Extraneous Variables

Variables other than the independent variable that may influence the dependent variable, such as individual differences.

Confounding Variables

A subset of extraneous variables where two variables are linked in a way that their individual effects on the dependent variable can’t be distinguished, such as the sugar and cocoa powder in chocolate.

Between Subjects Design

An experimental design where the treatment and control groups consist of different participants who were randomly assigned to their respective conditions.

Between Subjects Design (con’t)

The groups AREN’T made up of the same people

Within Subjects Design

Also called a within-group design, this occurs when the same group of participants takes part in both the control and treatment conditions.

Interaction Effect

An effect that emerges in complex designs when the impact of one independent variable depends on the specific level of another independent variable

e.g. Chocolate and gender

Pseudo-independent Variable

A variable that cannot be randomly assigned, such as gender, but is included in a study to see how it interacts with other variables.

Generalizability

The degree to which the findings of an experiment can be applied to real-world situations, which can be limited if the experiment is too artificial or controlled.

Naturalistic Observation

A research design involving the careful observation of people's behaviors in their natural environment without manipulating variables.

e.g. Are people more or less happy

Research methods

Various approaches to the observation, measurement, manipulation, and control of variables in empirical studies

Surveys

A research method that gathers information and assesses people's behaviours through questionnaires or interviews rather than manipulation.

e.g. Does chocolate make you happy? Correlate how much chocolate’s eaten and the subjective happiness scale

Advantages of surveys

They give researchers a way to explore questions the could not examine with experimental procedures

e.g. After-the-fact analyses would be the only ethical way to investigate the possible link between poor maternal nutrition and birth defects in humans.

Disadvantages of surveys

Investigators can’t control events to isolate cause an effect; descriptive/correlational research can’t demonstrate conclusively that correlated variables are causally related.

e.g. correlational data from a study doesn’t let us conclude that larger plates caused people to consume more food as there could be other factors like hunger

Numerical Data

Information collected in numeric form that allows for the application of math to organize, summarize, and interpret findings.

Statistics

Use of math to organize, summarize, and interpret numerical data

Statistics (con’t)

They allow researchers to draw conclusions based on their observations.

Descriptive Statistics

Mathematical techniques used to organize and summarize data,

e.g. Measures of central tendency

Measures of Central Tendency

A single typical or prototypical score used to represent an entire data set.

Mean

The average score of an entire distribution of data.

Mean (con’t)

Is the most useful measure of central tendency because additional statistical manipulations can be performed on it that are not possible with the median or mode

Median

The score that falls exactly in the middle of a distribution.

Mode

The most frequently occurring score within a distribution of scores.

Normal Distribution

A symmetrical, bell-shaped curve where the mean, median, and mode are approximately the same.

Variability

A measure of how scores vary from each other and from the mean, representing the spread of the data.

Standard Deviation

An index of the amount of variability within a data set.

68% Rule

The principle that in a normal distribution, $68\%$ of scores fall within one standard deviation above and below the mean.

95% Rule

The principle that in a normal distribution, $95\%$ of scores fall within two standard deviations above and below the mean.

Inferential Statistics

Statistical methods used to analyze data relationships, such as correlations, to interpret findings beyond simple description.

Correlation

A statistical measure reflecting the relationship between two variables.

Positive Correlation

A relationship where scores on two variables increase together and co-vary in the same direction

Positive Correlation (con’t)

If a correlation is positive, a plus sign (+) may be placed in front of the coefficient, or the coefficient may be shown with no sign

Negative Correlation

A relationship where as one variable increases, the second variable decreases co-vary in the opposite direction;

Negative Correlation (con’t)

If a correlation is negative, a minus sign (–) is always placed in front of the coefficient.

Correlation Coefficient

A numerical value ranging from $-1$ to $+1$ (often the Pearson coefficient) where the sign reflects direction and the value reflects the strength of association between 2 variables

Correlation Coefficient (con’t)

• 0 = No relationship

• 1 = Perfect relationship

Correlation Coefficient (III)

The strength of a correlation depends only on the size of the coefficient. The positive or negative sign simply indicates the direction of the relationship.

e.g. A correlation of –0.60 reflects a stronger relationship than a correlation of +0.30.

Perfect relationship

The ability to predict with 100% accuracy one variable based on our knowledge of another variable

Causality (in Correlation)

A conclusion that cannot be drawn from correlational designs because the direction of the relationship is unknown.

i.e. We don’t know how X and Y are related. We don’t know whether X causes Y or Y causes X

Advantages of the scientific approach

• Clarity and precision as it requires that people specify exactly what they are talking about when they formulate hypotheses

• Has zero tolerance for errors

Disadvantages of the scientific approach

• Some variables like age or gender can’t be changed

• Experiments could be artificial and have limited generalizability into the world

Sample

The collection of participants selected for observation in an empirical study.

Population

The much larger collection of animals or people (from which the sample is drawn) that researchers want to generalize about

Sampling bias

Exists when a sample is not representative of the population from which it was drawn.

Placebo effect

Occurs when participants’ expectations lead them to experience some change even though they receive empty, fake, or ineffectual treatment

Self-report data

Participants’ verbal accounts of their behaviour.

Self-report data (con’t)

Is used whenever questionnaires, interviews, or personality inventories are used to measure variables.

Social desirability

A tendency to give socially approved answers to questions about oneself, and can complicate the interpretation of research results

Response set

A tendency to respond to questions in a particular way that is unrelated to the content of the questions.

e.g. Some people tend to agree with everything on a questionnaire

Replication (con’t)

The repetition of a study to see whether the earlier results are duplicated to get rid of inaccuracies

Experimenter bias

Occurs when a researcher’s expectations or preferences about the outcome of a study influence the results obtained.

Double-blind procedure

A research strategy in which neither participants nor experimenters know which participants are in the experimental or control groups