Correlation and Regression

Question 1

The use of most correlation coefficients is based on three assumptions. They are…?

Answer 1

1. The relationship between variables is linear. (Nonlinear may underestimate relationship)
2. An unrestricted range of scores. (Restrictions underestimate the relationship)
3. Homoscedasticity

Question 2

This type of bivariate correlations coefficient is used when data on both variables is reported as ranks (ordinal).

Answer 2

Spearman rho (also known as Spearman rank coefficient)

Question 3

This type of bivariate correlations coefficient is used when both variables are measured on a continuous (interval or ratio scale) and the relationship is linear.

Answer 3

Pearson r (also known as Pearson product moment correlation)

eta may be used as an alternate if the relationship isn’t linear.

Question 4

This type of bivariate correlations coefficient is used when one variable is continuous interval or ratio scale) and the other is a true dichotomy (e.g., pregnant or not).

Answer 4

POINT biserial correlation coefficient

Question 5

This type of bivariate correlations coefficient is used when one variable is continuous and the other is an artificial dichotomy. An artificial dichotomy occurs when a continuous variable is dichotomized. (e.g., a range of test scores classified as pass/fail)

Answer 5

biserial correlation coefficient

Question 6

This type of bivariate correlations coefficient is used when both variables are nominal.

Answer 6

Contingency correlation coefficient

Question 7

The bivariate correlation coefficient can be interpreted directly as the degree of association between the predictor and criterion. Alternatively, it can be squared to derive a measure of shared variability and indicates the amount of variability in one variable that’s explained (accounted for) by variability in the other variable.

This is called _____?

Answer 7

Coefficient of determination

Question 8

Correlation is often of interest because the goal is to use obtained predictor scores to estimate criterion scores. Prediction is made possible through _____?

Answer 8

Regression analysis.

The accuracy of the prediction increases as the correlation between predictor and criterion increases.

Question 9

When two or more predictors will be used to estimate status on a single criterion that’s measured on a continuous scale, this is the appropriate technique.

Answer 9

Multiple regression

Question 10

What are the two forms of multiple regression?

Answer 10

Standard (simultaneous) multiple regression: entering all predictor data at once.

Stepwise multiple regression: adding or subtracting one predictor at a time to identify the fewest number or predictor needed to make accurate predictions.

Question 11

When two or more continuous predictors will be used to estimate status on two or more continuous criteria, this is the appropriate technique.

Answer 11

Canonical correlations

Question 12

When two or more predictors will be used to estimate status on a single criterion that’s measured on a nominal scale, this is the appropriate technique.

Answer 12

Discriminant function analysis

Question 13

When the assumptions for discriminant function analysis are not met (e.g., when scores on the predictors are not normally distributed), this is the alternative technique.

Answer 13

Logistic regression