Fundamental Concepts - Multiple Regression

13 important questions on Fundamental Concepts - Multiple Regression

What are zero-order correlations?

Correlations that not control for intercorrelation.

How is Y in MR also called?

Composite, as it is a weighted linear combination of predictors.

Why is OLS a partial-information method?

It analyzes the equation for only one criterion at a time.
  • Higher grades + faster learning
  • Never study anything twice
  • 100% sure, 100% understanding
Discover Study Smart


What is the multiple correlation between the predictors and the criterion?

The pearson correlation between the observed and the predicted scores. Ry12 = ryydakje


What does it mean that OLS "capatilizes on chance"?

(1). (R²y12) tends to overestimate the proportion of explained variance.
(2). It is hard to find similair values for B1, B2 and A in a replication of the sample.


What can you do to downward the adjusted R² values?

Use the equation of Wherry (1931) in which  R²dakje is the adjusted estimate of p² and k is the number of predictors.


What are the assumptions of Multiple Regression? (MR)

(1). Linearity
(2). Homoscedasticity (normal distribution with uniform variances)
(3). No measurement error
(4). Omitted predictors are not correlated with the measured or used predictors.

What is the specification error in MR?

That an omitted predictors account for some unique proportion of explained variance.


What is negative suppression?

Predictors have positive correlations with the criterion and each other but receives a negative Beta weight in the analysis.


What is classical suppresion?

One predictor is uncorrelated with  the criterion but receives a non zero beta weight controlling for another predictor.


What is reciprocal suppresion?

When two predictors correlate positively  with the criterion but negative with each other.


What are the two ways to enter predictors into the equation?

1. Simultaneous entry (all in one)
2. Sequantial entry (in steps)


How can the entry order for a MR equation be determined?

1. Theoretical (rational) --> Hierarchical regression
2. Empirical (statistical) --> Stepwise / Forward inclusion / Backward Elimination

The question on the page originate from the summary of the following study material:

  • A unique study and practice tool
  • Never study anything twice again
  • Get the grades you hope for
  • 100% sure, 100% understanding
Remember faster, study better. Scientifically proven.
Trustpilot Logo