day6lm

# Thus taking the log means that high values will be

This preview shows page 1. Sign up to view the full content.

This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: 2200354 .0201541 -10.92 0.000 -.2595428 -.180528! hisp | -.06267 .0342564 -1.83 0.067 -.1298217 .0044816! femalehd | -.2448488 .0245195 -9.99 0.000 -.2929136 -.196784! marriedhd | .6268674 .0234924 26.68 0.000 .5808161 .6729188! hsdropout | -.3733824 .0257042 -14.53 0.000 -.4237695 -.3229954! somecoll | .2201835 .0232687 9.46 0.000 .1745706 .2657964! collgrad | .4488191 .0249016 18.02 0.000 .4000055 .4976328! _cons | 9.943852 .0925671 107.42 0.000 9.762396 10.12531! ------------------------------------------------------------------------------! 7 2/17/12 More about logs •  How the log transforma:on works: –  On a log- scale, the distance between 1 and 2 is the same as the distance between 2 and 4, and the distance between 4 and 8, etc. –  Thus, taking the log means that high values will be more bunched together and low values will be more spread apart. –  This means that in some cases, if the rela:onship between X and Y is curved, then the rela:onship between log(X) and Y will be close to linear. •  Note that log(0)=- ∞, and log(1)=0. So all values (from the original variable) below 1 should be converted to 0 aeer the log transforma:on. Inverse transforma:ons 1 yi = β 0 + β1 + ε i •  Func:onal Form: x •  This is useful when we think that the i rela:onship looks like: Y Y X X 8 2/17/12 Using categorical independent variables •  The independent variables we’ve been using are all interval level (age, number of :mes aZended church, etc.) •  A lot of social science variables are categorical (gender, race, region, etc.) •  To include these, we create “dummy” variables (0/1 variables). One category must be omiZed to serve...
View Full Document

## This note was uploaded on 03/28/2012 for the course PADP 8130 taught by Professor Fertig during the Spring '12 term at LSU.

Ask a homework question - tutors are online