Psych2019 revision

One sample t-test

Tests whether a sample mean is different from the population mean, when the population standard deviation is unknown

Paired samples t-test

Compares the mean difference between pairs of measurements to determine whether there is a difference

When to use paired samples t-test

• One continuous outcome variable (DV)

• One categorical predictor variable (IV) with 2 levels in which the same participants are exposed to both levels

• Data meets parametric assumptions

Independent samples t-test

Compares two sample means from unrelated groups to determine whether there is a difference between groups

When to use independent samples t-test

• One continuous outcome variable (DV)

• One categorical predictor variable (IV) with two levels in which difference participants are exposed to separate levels

• Data meets parametric assumptions

One-way ANOVA

Tests whether there is a difference between the means of 3 or more independent groups

When to use one-way ANOVA

• One continuous outcome variable (DV)

• One categorical predictor variable (IV) with 3 or more levels in which different participants are exposed to separate levels

• The data meets parametric assumptions

Repeated measures ANOVA

Tests whether there are any differences between three or more related samples

When to use repeated measure ANOVA

• One continuous outcome variable (DV)

• One categorical predictor variable (IV) with three or more levels in which the same participants are exposed to all levels

• Data meets parametric assumptions

Factorial ANOVA

Tests whether there are differences between the means of groups that are categorised by two or more independent variables (factors)

When to use factorial ANOVA

• Two or more IVs (IVs can vary within subjects, between subjects, or both between and within subjects)

• Data meets parametric assumptions

Main effects

The overall effect of a single IV on the DV

Interaction

Means the effect of one IV on the DV depends on another IV or set of IVs.

Interactions accentuate, reduce or eliminate the effect of IVs on the DV - must compute simple effects test to determine how the factors interact with one another

Simple effects tests

Tells you whether there is a significant difference between any conditions of one IV at one level of another IV/set of IVs

Correlation

Examines the relationship between two variables to see if they change together, and if so, how strong that relationship is and what direction it takes

When to use correlation

• Want to examine the relationship between groups

• Are not controlling for the effect of additional variables

• Data meets parametric assumptions

Partial correlation

Measures the strength of the relationship between two variables while controlling for the effects of one or more other variables

When to use partial correlation

• Want to measure the relationship between groups

• Want to control for the effect of additional variables

• Data meets parametric assumptions

Regression

Tests the relationship between a dependent variable and one or more independent variables

Simple regression

Examines the linear relationship between two continuous variables, aims to find the line of best fit

When to use simple regression

• One continuous outcome variable (DV)

• One continuous predictor variable (IV) that can be used to predict the outcome variable

• Data meets parametric assumptions

What is the predictor variable

The IV

What is the outcome variable

The DV

What are coefficients

The numbers in the regression equation that define the line (slope and intercept)

What is the slope

Indicates the steepness of the line and the change in the dependent variable for each unit change in the independent variable

What is the intercept

The point where the line crosses the y-axis (dependent variable axis)

Multiple regression

Tests the relationship between one DV and two or more IVs

When to use a multiple regression

• One continuous outcome variable (DV)

• Two or more continuous predictor variables that can be used to predict the outcome variable

• Data meets parametric assumptions

Chi-square

Determines if there is a significant difference between observed and expected frequencies in one or more categories. Used for categorical data. Goodness of fit test and contingency tables (multi-dimensional chi-square)

Goodness of fit test

Also known as one sample chi-square or one-dimensional chi-square because there is only one IV, compares observed frequencies with theoretically predicted frequencies

When to use goodness of fit test

• One categorical variable with two or more levels

• Participants may be distributed based on their responses

Contingency tables

Thought of as a test of association or a test of differences between independent groups. Compares observed frequencies with theoretically predicted frequencies

When to use contingency tables

• Two categorical variables

• Both with two or more levels

• Participants may be distributed based on their responses