Data on fertility rates in different countries are contained in the UN2 dataset. We will fit two regression models to these data, and compare the fit of the models to see whether the (log) per person gross domestic product (logPPgdp) (only) or both the (log) per person gross domestic product (logPPgdp) and the percentage of the population that lives in an urban area (Purban) can be used to explain variability in the log fertility of the set of countries (logFertility). In what follows, let denote the log fertility rate, denote log per person GDP and denote the percentage in urban areas:
(0.7) | |||||
(0.8) |
Least squares estimates
The least squares coefficients for the logPPgdp covariate are
[marks: 2]
Sums of squares
The sums of squares for the two models are
56.24 and 53.91
62.43 and 56.16
62.40 and 61.27
65.72 and 63.63
72.25 and 68.55
[marks: 2]
Test statistic
What is the value of the test statistic to test the suitability of Model 0.7 against
Model 0.8?
2.459
2.676
2.874
3.091
3.494
[marks: 2]
Critical value
Assuming a 5% significance level, what is the critical value for this
test?
2.65
3.04
3.89
5.10
5.32
[marks: 2]
p value
What is the -value for your test?
0.063
0.036
0.079
0.097
0.044
[marks: 2]