0

We have a last assignment for my poli sci stat class and these two have really got me stumped. We really didn't go over multiple regression very well so if anybody can help, I appreciate it!

  1. Your dependent variable is “Child Deaths,” and your independent variables include a dummy variable called “Southern Hemisphere” (which is also your independent variable of interest) and an adequate set of seven control variables (including population). The regression coefficient for the “Southern Hemisphere” variable is -426. Write a single sentence expressing your interpretation of this coefficient. (Note: Please keep in mind that this is a multiple regression!).

  2. Your standard error of b from problem 9 above is 246. What are the implications of this?

gung - Reinstate Monica
  • 132,789
  • 81
  • 357
  • 650
Josh
  • 19
  • 1
  • 2
  • We welcome questions like this, @Sam, but we treat them differently. Please tell us what you understand thus far, what you've tried & where you are stuck, & we'll try to provide hints to get you unstuck. To better understand the process, you should read the [wiki](http://stats.stackexchange.com/tags/self-study/info) for the `[self-study]` tag. – gung - Reinstate Monica Dec 07 '13 at 00:59
  • I'm probably wrong because I just do not get this, I was good until we started regression haha. For the first one I have: "The coefficient indicates that for every child death interval number, you can expect the number for Southern Hemisphere to decrease by an average of -426. A negative number would also make a downward slope, or a strong negative relationship." and the second one I have: "Such a large difference between the two could indicate a sampling error." I'm sure I'm wrong but everywhere I look doesn't really explain how to interpret the data, just the formulas for getting there. – Josh Dec 07 '13 at 01:02
  • That seems decent to me. What do you make of the `Please keep in mind that this is a multiple regression` in the 1st question? – gung - Reinstate Monica Dec 07 '13 at 01:08
  • Well since this is the variable of interest, those others should be controlled for already so they don't have an effect...right? – Josh Dec 07 '13 at 01:14
  • I wonder if you should incorporate something like that idea in your answer to the first question. – gung - Reinstate Monica Dec 07 '13 at 01:23
  • I will, thanks @gung for validating what I thought haha! – Josh Dec 07 '13 at 01:25

0 Answers0