In examples like the Guber study on the funding of education, we frequently speak of variables like PctSAT as “nuisance variables.” In what sense is that usage reasonable here, and in what sense is it somewhat misleading?
Answer to relevant QuestionsIn several places in the chapter I have shoved aside the intercept by saying that we really don’t care about it. If we don’t care about it, why do we include it? Using the following (random) data, demonstrate what happens to the multiple correlation when you drop out cases from the data set (e.g., use 15 cases, then 10, 6, 5, 4). Compute 95% confidence limits on m for the data in Exercise 12.11. In Exercise 12.11. I drew 50 samples of 5 scores each from the same population that the data in Exercise 12.1 came from, and calculated the mean of each sample. The means are shown below. Plot the distribution of these means. You would probably be nervous about inferring a population estimate and a confidence interval for the mean U.S. SAT Combined score from the data in Table 11.1, but you are probably much less worried about your confidence ...
Post your question