search

Watts-College / cpp-529-fall-2021

https://watts-college.github.io/cpp-529-fall-2021/
0 stars 0 forks source link

Question about Lab 05 Part 06-Effect Sizes #10

Open mtwelker opened 2 years ago

mtwelker commented 2 years ago

Prof. @AntJam-Howell , The directions for Part 06 say:

Calculate the effect size associated with each variable. Report the relative importance of each factor in predicting the outcome. You can calculate effect size as follows:

m <- lm( y ~ x )
x.75 <- quantile( x, p=0.75 )
x.25 <- quantile( x, p=0.25 )
beta.x <- m$coefficients[2]  # position of x in the model 

effect.size.x <- ( x.75 - x.25 ) * beta.x

Question 1: In calculating the effect size according to the code above, do we do so on one IV at a time as in the example code (i.e. run the regression 3 times, once with each variable)? Or should we run the regression with all variables included and then use that to come up with the three effect sizes?

Question 2: In Step 05, we were supposed to run the models 2 ways, once with mhv.change ($) as the DV and once with mhv.growth (%) as the DV. In Step 06, are we supposed to calculate the effect sizes on both mhv.change and mhv.growth as well? Or only on mhv.growth?

Thank you!

mbsaid commented 2 years ago

I have the same Question!!

AntJam-Howell commented 2 years ago

@mtwelker @mbsaid

Answer to question 1: You may run the three regressions, one for each IV separately. Answer to question 2: It is not specified, and is up to you whether you want to run the model on change or growth; or both, and compare and contrast the results.

Best,