Exam 2: A Guide to Multivariate Techniques

The most basic statistical test that measures group difference is the T-test.

Significance of group differences is evaluated by discriminant analysis and logistic regression.

Factorial multivariate analysis of variance (factorial MANOVA) extends MANOVA to research scenarios with two or more DVs that are categorical.

Factorial multivariate analysis of covariance (MANCOVA) extends factorial MANCOVA to research scenarios that require the adjustment of one or more covariates on the IV.

In binary logistic regression, the DV is a dichotomous variable.

One-way multivariate analysis of covariance (MANCOVA) investigates group differences among several IVs, while also controlling for covariates that may influence the DVs.

Discriminant analysis seeks to identify which combination of quantitative IVs best predicts group membership by a single DV that has two or more categories.

The primary factor that determines the statistical test students should use is the number of independent and dependent variables.

One-way multivariate analysis of variance (MANOVA) is utilized to simultaneously study two or more related IVs, while controlling for the correlations among the IVs.

Factorial analysis of variance (factorial ANCOVA) examines group differences in a single quantitative dependent variable based upon two or more categorical independent variables, while controlling for a covariate that may influence the DV.

The Pearson correlation coefficient measures the association between two quantitative variables, distinguishing between the independent and dependent variables.

Discriminant analysis and logistic regression are appropriate statistical techniques when the DV is categorical.

Principal components analysis is generally used to reduce the number of IVs, which is advantageous when conducting multivariate techniques in which the IVs are not correlated.

Multiple regression is used when there are several dependent variables and one independent quantitative variable.

One-way analysis of variance (ANOVA) only determines the significance of group differences and does not identify which groups are significantly different.

One-way analysis of covariance (ANCOVA) is similar to ANOVA but additionally controls for a variable that may influence the DV.

In path analysis, path coefficients are calculated:

When investigating the relationship between two or more quantitative variables, the T-test is the appropriate test.

Factorial analysis of variance (factorial ANOVA) extends ANOVA to research scenarios with two or more IVs that are categorical.

The primary purpose of predicting group membership is to identify specific IVs that best predict group membership as defined by the IVs.