Categorical Predictors Flashcards

1
Q

what is the f statistic?

A

ratio –> variance explained by the model : variance unexplained by the model

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

what is dummy coding?

A

coding any categorical predictor

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

what are the dummy coding labels?

A

b0 = control / b1 = control and variable 1 / b2 = control and variable 2

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

what are the three ways to test for homogeneity of variance?

A

Levene’s, variance ration, robust F statistic

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

when and how would you use a Levene’s test?

A

shouldn’t due to problems with he sample size

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

when and how would you use a variance ration?

A

divide the largest variance by the smallest variance / any number <2 is good

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

when and how would you use the robust F statistics?

A

the Welch and Brown-Forsythe should share a similar statistic and significance

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

what does a symbol mean if it has “^” above it?

A

an estimate of

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

what is cohen’s d?

A

a measure of effect size

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

what do you do if you are able to use a control group?

A

^d = the difference between the two means / SD of control

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

what do you do if there is no control but the two groups have equal variances?

A

^d = the difference between the two means / SD of either group

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

what do you do if there is no control and the two groups have unequal variances?

A

a pooled estimate to create the number that the difference between the two means is divided by

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

how do you calculate the pooled estimate?

A

(sample 1 - 1) x s1^2 (sample 2 - 1) x s2^2 / (sample 1 + sample 2) - 1
square root the answer

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