Multivariate Analysis – Questions With Solutions
Multivariate Analysis ✔️Ans - ability to examine several response variables
within single study; account for potential interrelationships in the analysis of
data; complex statistical procedures
Exploratory Factor Analysis (EFA) ✔️Ans - examines linear combinations of
underlying factors that explain a latent variable or construct
Confirmatory Factor Analysis (CFA) ✔️Ans - Confirm hypotheses about
structure of underlying constructs
Principal Component Analysis (PCA) ✔️Ans - Attempts to reduce data to
smaller set of summary variables of components
Latent traits ✔️Ans - constructs that cannot be directly measured but
influence behavior
Bartlett's test of sphericity ✔️Ans - A test statistic used to examine the
hypothesis that the variables are uncorrelated in the population. Uses chi-
square distribution to test null hypothesis that intercorrelations equal zero
Communalities ✔️Ans - measure of proportion of each variable's variance
that can be explained by factors
principal axis factoring ✔️Ans - defines factors based on their
intercorrelations
Eigenvalue ✔️Ans - how much of the total variance is explained by a factor
Structural Equation Modeling (SEM) ✔️Ans - statistical techniques that are
used to evaluate a proposed set of relationships among variables; illustrate
possible causal relationships; whether a pattern of intercorrelations among
variables "fit" underlying theory and directionality of those relationships;
combines factor analysis and multiple regression
exogeneous variable ✔️Ans - independent predictor variable, causes are
external to model, not included in theory
Multivariate Analysis ✔️Ans - ability to examine several response variables
within single study; account for potential interrelationships in the analysis of
data; complex statistical procedures
Exploratory Factor Analysis (EFA) ✔️Ans - examines linear combinations of
underlying factors that explain a latent variable or construct
Confirmatory Factor Analysis (CFA) ✔️Ans - Confirm hypotheses about
structure of underlying constructs
Principal Component Analysis (PCA) ✔️Ans - Attempts to reduce data to
smaller set of summary variables of components
Latent traits ✔️Ans - constructs that cannot be directly measured but
influence behavior
Bartlett's test of sphericity ✔️Ans - A test statistic used to examine the
hypothesis that the variables are uncorrelated in the population. Uses chi-
square distribution to test null hypothesis that intercorrelations equal zero
Communalities ✔️Ans - measure of proportion of each variable's variance
that can be explained by factors
principal axis factoring ✔️Ans - defines factors based on their
intercorrelations
Eigenvalue ✔️Ans - how much of the total variance is explained by a factor
Structural Equation Modeling (SEM) ✔️Ans - statistical techniques that are
used to evaluate a proposed set of relationships among variables; illustrate
possible causal relationships; whether a pattern of intercorrelations among
variables "fit" underlying theory and directionality of those relationships;
combines factor analysis and multiple regression
exogeneous variable ✔️Ans - independent predictor variable, causes are
external to model, not included in theory
