Brainscape's Knowledge GenomeTM

Browse over 1 million classes created by top students, professors, publishers, and experts.


See full index

Quantitative research > Multiple Regression > Flashcards

Multiple Regression Flashcards

1
Q

regression allows us to…

A

predict a score for one variable based on their score on another variable

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

criterion variable

A

DV

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

predictor variable

A

IV

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

DV

A

criterion variable

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

IV

A

predictor variable

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

data requirements for multiple regression

A

Explores linear relationship between criteria and predictor variables

Criterion measured on a continuous scale

Predictors measured on a ratio, interval or ordinal scale

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

assumptions of MR

A

sample size
multicollinearity
normality
homoscedasticity
linearity

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

hypotheses of MR

A

H0 = null = no difference/no linear relationship

H1 = alternate = linear relationship with at least one predictor

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

Sample size assumption

A

Tabachnick and Fidell (2007)
N>50+8M

N is number of ppts
M is number of predictor variables

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

normality assumption

A

normality of residuals
use histogram line of best fit and pplots

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

what to use to test normality assumption

A

histogram and line of best fit
p-plots

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

residual

A

difference between predicted and observed value

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

linearity assumption

A

predictor and criterion lineally related
pplot

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

what to use to test linearity assumption

A

p-plot

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

multicollinearity assumption

A

strong correlation between C&P is wanted but not between P&P

high intercorrelation (r>+/-.90) among predictors shows multicollinearity which is bad

singularity = perfect linear relationship which is bad

VIF >0.50
Tolerance<10
these show no multicolloinearity

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

what to use to test multicollinearity assumption

A

VIF>0.50
tolerance<10
these show multicollinearity is met

17
Q

VIF value for multicollinearity assumption to be met

A

> 0.5

18
Q

tolerance value for multicollinearity assumption to be met

A

<10

19
Q

homoscedasticity assumption

A

assuming similar variances
use scatterplot

20
Q

what to use to test homoscedasticity assumption

A

scatterplot

residuals spread evenly from the line

21
Q

types of multiple regression

A

standard
hierarchical
stepwise

Quantitative research (11 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2024 Bold Learning Solutions. Terms and Conditions