In: Statistics and Probability
This question shows 3 possible models. Delta R^2 is the adjusted R^2 value. Then F is the test statistic for adjusted R^2. The significance columns show the p-values for each measurement. The best model is the one with the lowest p-value for F.
The table below summarizes nested multiple regression models used to predict a person’s quality of life score.
Model 1 | Model 2 | Model 3 | ||||
---|---|---|---|---|---|---|
est. | sig. | est. | sig. | est. | sig. | |
intercept | 16.68 | <.001 | 9.16 | <.001 | 7.57 | <.001 |
size of social network | 0.59 | 0.027 | 0.44 | 0.076 | 0.43 | 0.059 |
college degree | — | 3.73 | 0.014 | 3.87 | 0.030 | |
time (yrs) at current job | — | — | 0.91 | 0.046 | ||
# of siblings | — | — | –0.68 | 0.146 | ||
R2R2 | 3.65% | 8.01% | 9.60% | |||
ΔR2ΔR2 | 3.65% | 4.36% | 1.59% | |||
FF (for ΔR2ΔR2) | 5.00(1,132) | 0.027 | 6.20(1,131) | 0.014 | 1.13(2,129) | 0.325 |
Using the model information (parameter estimates and comparative
model fit), provide a prediction for the quality of life score for
a person with a social network of size 8, a college degree, 4 years
at current job, and 3 siblings.
QOL = ˆy=y^=
Report answer accurate to 2 decimal places.
Be prepared to briefly justify your model choice.