MR Flashcards Preview

Stats > MR > Flashcards

Flashcards in MR Deck (22)
Loading flashcards...

What are the approaches to multiple regression? Describe them

-Standard: all predictors are entered at the same time (produces one model)

-Sequential: predictors are entered in steps (produces multiple models) - can be either data driven (frowned upon) or model drive


Why is data drive/stepwise approaches frowned upon?

because they are specific to your dataset


What is multicollinearity?

When a combination of one or more of the predictor variables are highly correlated with another set of predictor variables within the same multiple regression model


What is perfect collinearity?

+1 or -1 (perfect negative or positive correlation) 0 = no relationship


What indicates multicollinearity is probably an issue in standard regression?

excessively large standard errors


What indicates multicollinearity is probably an issue in hierarchical regression?

large changes in regression coefficients and/or associated error terms as predictor variables are added or removed from the analysis


What is mediation?

when the relationship between a predictor variable and an outcome variable can be explained by their relationship to a third variable (the mediator)


What is moderation?

combined effect of two variables on an outcome -> known as a statistical interaction


What are the 4 conditions of mediation?

1. the predictor variable must significantly predict the outcome variable in model 1;
2. the predictor variable must significantly predict the mediator in model 2;
3. the mediator must significantly predict the outcome variable in model 3; and
4. the predictor variable must predict the outcome variable less strongly in model 3 than in model 1.

Where model 1 refers to the simple/direct relationship and model 2 refers to the mediation model


What does R squared represent

the amount of variance explained by a model


What does the beta value represent in multiple regression?

the total effect of a predictor variable given the presence of other predictor variables


What is a disturbance term in AMOS and why is it needed?

A disturbance term represents the variability in a predicted variable that is not accounted for by the predictor variable


In path analysis, which variables require disturbance terms?

every predicted variable needs a disturbance term


What is confirmatory factor analysis

verifying the ability of a theoretical model to explain the common variance among several variables using previously identified latent variables


in SEM what are exogenous variables?

Variables that are not influenced by any other variables in a model


in SEM what are endogenous variables?

variables that are influenced by other variables in a model


What is a latent variable

A variable that is not directly measured


What are the steps in structural equation modelling? (6)

1. Construction of a theoretical model
2. Formalization of the model
3. Estimation of the model
4. Identification of the model
5. Interpretation of the model -> 6. can lead to modification of the theoretical model


What is communality in Exploratory Factor Analysis

the proportion of common variance that is shared with other variables


In structural equation modeling what is the measurement model?

The model that relates measured variables to the latent variables


In structural equation modeling what is the structural model?

relates latent variables to one another


which indices does the prof consider mandatory to report in CFA?

Chi squared, CFI, RMSEA