Logistic Regression Flashcards

1
Q

What is centring?

A

Taking the mean value and subtracting the score from each value to centre the data, which is useful when the data set does not contain a 0

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

What are the conditions and use of a logistic regression?

A

when there is a binary dv, with continuous or binary ivs, used to answer diff questions than multiple regression e.g. group membership

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

What shape is a logistic regression distribution?

A

s-shaped, logarithmic, non-linear

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

What is a quadratic function?

A

u-shaped, parabella

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

What is a binomial logistic regression?

A

1 or 0 values, yes/no, is/is not

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

What is a multinomial logistic regression?

A

categorical, 1/2/3 options, you’re a dog, cat, or a frog, w/ no order

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

What is an ordinal logistic regression?

A

Categorical but with an order e.g. high/med/low

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

What are standard, sequential, or statistical logistic regressions?

A

standard is all entered at the same time, sequential is variables entered in sequence/blocks, statistical is forward or backwards entry

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

What is coding in logistic regression?

A

assigning a group, the higher value, as the target outcome, and the lower value as the reference group, ref group is group of not primary interest, if more than 2 cats, dummy coding is used

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

What are the assumptions of logistic regression?

A

independent errors, multicolinearity and singularity, linearity, outliers, sufficient data/5 cases at least per cell of contingency table, and data is not clustered/errors not related

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

What do you use to test model improvement for logistic regression?

A

chi-square test

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

What is good classifcation accuracy for logistic regression?

A

closer to 100%, the better, lower than 50%, not good

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

What is the odds ratio value for logistic regression?

A

change in the likelihood of dv in change of iv

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