Experimental Design Flashcards

Flashcards covering Experimental Design, including Completely Randomised Design, Randomised Block Design, Matched Pairs Design, Operational Definitions, and types of Randomised Control Trials.

Completely Randomised Design

Researcher assigns subjects completely at random to experimental conditions.

Randomised Block Design

Researcher divides subjects into subgroups called blocks, then subjects within each block are randomly assigned to experimental conditions.

Matched Pairs Design

Used when the experiment has only two experimental conditions. Subjects can be grouped into pairs, based on some variables. Within each pair, subjects are randomly assigned to different experimental conditions.

Operational Definition

A process by which a psychologist defines how a concept/variable is observed (clearly, specifically) and measured (data).

Importance of Operational Definitions

Replication of the experiment and reliability.

Confounding Variable

Variable(s) that has/have affected the results (i.e. the dependent variable), apart from the independent variable.

Extraneous Variable

All variables, which are not the independent variable, but could affect the results (DV) of the experiment. Should be controlled where possible.

Independent Measures Design

Also known as between-groups, is an experimental design where different participants are used in each condition of the independent variable.

Random Allocation

Ensures that each participant has an equal chance of being assigned to one group or the other.

Kurtosis

A measure of whether the data are heavy-tailed or light-tailed relative to a normal distribution.

High Kurtosis

Data sets tend to have heavy tails, or outliers.

Low Kurtosis

Data sets tend to have light tails, or lack of outliers.

Matched Pairs Design

An experimental design where pairs of participants are matched in terms of key variables, such as age or socioeconomic status. One member is placed into the experimental group and the other into the control group.

Non-Parametric Stats Test

Methods of statistical analysis that do not require a distribution to meet the required assumptions to be analysed.

Distribution-free tests

Another name to call non-parametric stats tests

Parametric Stats Test

Makes an assumption about the population parameters and the distributions that the data came from.

Repeated Measures Design

An experimental design where the same participants take part in each condition of the independent variable.

Within-groups design

Alternative name for repeated measures design

Variable

A measure that is being manipulated or controlled to test a research hypothesis

Independent Measures

Where different subjects are used in each experimental condition

Between Subjects

Two groups in an experimental design

Repeated Measures

Experimental design where the same subjects take part in each experimental condition

Randomised Control Trial

Researcher randomly assigns participants into a treatment group or a control group

Open labelled RCT

Both parties know which treatment the participant is receiving

Single-blinded RCT

Only the researcher knows which treatment the participant is receiving

Double blinded RCT

Neither the researcher nor participant knows which treatment the participant is receiving

Experimental Design

Refers to how subjects, from the sample, are allocated to the different groups in an experiment

Experimental Design Types

Completely random, block random and matched pairs designs

Independent Measures (Between Subjects)

Different subjects are used in each condition

Repeated Measures (Within Subjects)

Same subjects are used in each condition

RCT Usefulness

Used to determine the effect of a treatment or intervention and have varying leveles of blinding

Between-groups design

Another name for independent measures design

Within- subjects design

Another name for repeated measures design

Experimental conditions

Different levels of the independent variable in an experiment

Nonparametric Tests

Serve as an alternative to parametric tests such as T-test or ANOVA that can be employed only if the underlying data satisfies certain criteria and assumptions