Lecture 4- Model Fit

Question 1

b1 estimates what

Answer 1

Parameter for a predictor

• Direction of relationship/effect
• Difference in means

Question 2

b0 estimates what

Answer 2

The value of the outcome when predictors =0 (intercept)

Question 3

Sums of squares represent

Answer 3

Total error

Question 4

Because sums of squares are totals they can only be compared when

Answer 4

They are based on the same number of scores

Question 5

df=

Degrees of freedom

Answer 5

N- p

Number of scores - number of parameters

Question 6

What is SST

Total sum of squares

Answer 6

Total variability (variability between scores and the mean)

Question 7

What is SSR

Residual sum of squares

Answer 7

• Total residual/error variability (variability between the model and the observed data)
• How badly the model fits (in total)

Question 8

What is SSM

Model sum of squares

Answer 8

• Total model variability (difference in variability between the model and the grand mean)
• How much better the model is at predicting Y than the mean
• How well the model fits (in total)

Question 9

Each sum of squared has

Answer 9

Associated degrees of freedom

Question 10

The df is what in relation to SS

Answer 10

The amount of independent information available to compute SS (Sum of squares)

Question 11

For each parameter estimated we lose

Answer 11

1 piece of independent information

Question 12

To get SST we estimate

Answer 12

1 parameter

Question 13

dfT=

Answer 13

N- p

Number of pieces of info - parameter

Question 14

To get SSR we estimate

Answer 14

2 parameters (b0 and b1)

Question 15

dfM=

Answer 15

dfT- dfR

Question 16

The null model and the estimated model are distinguished by

Answer 16

b1, the slope

Question 17

SST=

Answer 17

SSM + SSR

Question 18

MS=

Answer 18

SS/df

Mean squared= sum of squares/ degrees of freedom

Question 19

Sums of squares errors can’t compared based on

Answer 19

Different amounts of information

Question 20

The average or mean squared error can be computed by

Answer 20

Dividing a SS by the amount of information used to compute it

Question 21

The df quantifies

Answer 21

The amount of information used to compute a sum of squared errors

Question 22

The F statistic is the ratio of

Answer 22

MSM to MSR

Question 23

If the model results in better prediction than using the mean then

Answer 23

MSM should be greater than MSR

Question 24

What r2 represent

Answer 24

• The proportion of variance accounted for by the model

- The Pearson correlation coefficient between observed and predicted scores squared

Question 25

What does adjusted r2 represent

Answer 25

An estimate of r2 in the population (shrinkage)

Question 26

How to enter predictors when there is more than one predictors in a model

Answer 26

• Hierarchical
• Forced entry
• Stepwise

Question 27

What is hierarchical entrance to predictors

Answer 27

• Experimenter decides the order in which variables are entered into the model
• Best for theory testing

Question 28

What is forced entry to predictors

Answer 28

All predictors are entered simultaneously

Question 29

What is stepwise entrance to predictors

Answer 29

• Predictors are selected using their semi-partial correlation with the outcome
• Can produce spurious results
• Use only for exploratory analysis

Question 30

SST is made up of

Answer 30

SSM and SSR

Question 31

SSM is worked out by

Answer 31

Comparing the model to the null hypothesis

Slope- flat line