Statistical Inference – Quiz 6

Quiz Question Explanations

Question 1

You can use the ttesti command to calculate the p-value:

ttesti 50 10.8 3.4 9.6

The p-value from a two-sided test is 0.016 < 0.05, and so you can reject the null hypothesis that the true population mean is 9.6 at the 5% significance level.

Question 2

After loading the EG DIB data you can run the command:

ttest total_ely1 == 10

The p-value on a two-sided hypothesis test is ~0.00 < 0.05, and so you can reject the null hypothesis that the Year 1 endline test score average for this sample of students is 10.0 at the 5% significance level. Note that your sample mean is very precisely estimated because the sample size (4,069 students) is very large. However, this estimate fails to account for the fact that sampling took place in two stages: first schools were sampled and then students were sampled. We will see in the Sampling lesson that adjustments for clustering yield much less precise estimates.