Module 10: Multiple Regression Flashcards

1
Q

What is PROC GLM?

A

Its a SAS procedure used for the analysis of variance and regression analysis.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

Write the general syntax for PROC GLM.

A

proc glm data=dataset;
model y-var = list-of-x-var;
run;

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

How do you write an interaction term in PROC GLM?

A

var1 x var2

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

What does the class statement do in PROC GLM?

A

Specifies one or more categorical variables that you want to include in the regression

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

T/F: When the class variables are used, the parameter estimates are generated.

A

False: They are not generated. Need to use the SOLUTION model option.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

T/F: By default SAS keeps the last level of the categorical variable as the reference group.

A

True

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

How do you specify another level of a categorical variable as the reference group?

A

Use the option REF = ‘ref-level in the class statement.
Ex. class eeogroup (ref = ‘1M’);

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

Given the following code, explain each line.

proc glm data=one;
1) class eeogroup;
2) model salary = eeogroup timeinjob othertime/solution;
3) output = out=oneout predicted=yhat residual= diff student =sigma

A

1) specifies eeogroup as categorical
2) specifies the model to use
3) Creates a new dataset called oneout that has the variables named yhat, diff, and sigma based on the outputs for predicted, residual, and student

Note: sigma is std. deviations

How well did you know this?
1
Not at all
2
3
4
5
Perfectly