multicolinearity
Differences
This shows you the differences between two versions of the page.
Both sides previous revisionPrevious revisionNext revision | Previous revision | ||
multicolinearity [2018/12/26 02:41] – hkimscil | multicolinearity [2018/12/26 02:49] (current) – [regression test with factors] hkimscil | ||
---|---|---|---|
Line 24: | Line 24: | ||
$ sector | $ sector | ||
$ marr : int 1 1 0 0 1 0 0 0 1 0 ... | $ marr : int 1 1 0 0 1 0 0 0 1 0 ... | ||
+ | > head(cps) | ||
> head(cps) | > head(cps) | ||
education south sex experience union wage age race occupation sector marr | education south sex experience union wage age race occupation sector marr | ||
Line 34: | Line 34: | ||
6 13 | 6 13 | ||
</ | </ | ||
- | |||
- | < | ||
- | > cps$sex <- factor(cps$sex) | ||
- | > cps$union <- factor(cps$union) | ||
- | > cps$race <- factor(cps$race) | ||
- | > cps$sector <- factor(cps$sector) | ||
- | > cps$occupation <- factor(cps$occupation) | ||
- | > cps$marr <- factor(cps$marr) | ||
- | > str(cps) | ||
- | ' | ||
- | $ education : int 8 9 12 12 12 13 10 12 16 12 ... | ||
- | $ south : int 0 0 0 0 0 0 1 0 0 0 ... | ||
- | $ sex : Factor w/ 2 levels " | ||
- | $ experience: int 21 42 1 4 17 9 27 9 11 9 ... | ||
- | $ union : Factor w/ 2 levels " | ||
- | $ wage : num 5.1 4.95 6.67 4 7.5 ... | ||
- | $ age : int 35 57 19 22 35 28 43 27 33 27 ... | ||
- | $ race : Factor w/ 3 levels " | ||
- | $ occupation: Factor w/ 6 levels " | ||
- | $ sector | ||
- | $ marr : Factor w/ 2 levels " | ||
- | > </ | ||
- | |||
< | < | ||
Line 67: | Line 44: | ||
Residuals: | Residuals: | ||
| | ||
- | -2.36167 -0.27926 | + | -2.16246 -0.29163 -0.00469 0.29981 1.98248 |
Coefficients: | Coefficients: | ||
- | | + | Estimate Std. Error t value Pr(> |
- | (Intercept) | + | (Intercept) |
- | education | + | education |
- | south -0.09290 | + | south -0.102360 |
- | sex1 | + | sex -0.221997 |
- | experience | + | experience |
- | union1 | + | union |
- | age -0.05858 | + | age -0.085444 |
- | race2 -0.03345 | + | race 0.050406 |
- | race3 0.07973 | + | occupation |
- | occupation2 -0.36440 | + | sector |
- | occupation3 -0.20964 | + | marr 0.076611 |
- | occupation4 -0.38345 0.08105 | + | |
- | occupation5 | + | |
- | occupation6 -0.26555 0.08002 | + | |
- | sector1 | + | |
- | sector2 | + | |
- | marr1 0.06335 | + | |
--- | --- | ||
Signif. codes: | Signif. codes: | ||
- | Residual standard error: 0.4281 on 517 degrees of freedom | + | Residual standard error: 0.4398 on 523 degrees of freedom |
- | Multiple R-squared: | + | Multiple R-squared: |
- | F-statistic: | + | F-statistic: |
- | + | ||
- | > | + | |
</ | </ | ||
Line 248: | Line 217: | ||
> </ | > </ | ||
+ | ====== regression test with factors ====== | ||
< | < | ||
+ | > cps$sex <- factor(cps$sex) | ||
+ | > cps$union <- factor(cps$union) | ||
+ | > cps$race <- factor(cps$race) | ||
+ | > cps$sector <- factor(cps$sector) | ||
+ | > cps$occupation <- factor(cps$occupation) | ||
+ | > cps$marr <- factor(cps$marr) | ||
+ | > str(cps) | ||
+ | ' | ||
+ | $ education : int 8 9 12 12 12 13 10 12 16 12 ... | ||
+ | $ south : int 0 0 0 0 0 0 1 0 0 0 ... | ||
+ | $ sex : Factor w/ 2 levels " | ||
+ | $ experience: int 21 42 1 4 17 9 27 9 11 9 ... | ||
+ | $ union : Factor w/ 2 levels " | ||
+ | $ wage : num 5.1 4.95 6.67 4 7.5 ... | ||
+ | $ age : int 35 57 19 22 35 28 43 27 33 27 ... | ||
+ | $ race : Factor w/ 3 levels " | ||
+ | $ occupation: Factor w/ 6 levels " | ||
+ | $ sector | ||
+ | $ marr : Factor w/ 2 levels " | ||
</ | </ | ||
< | < | ||
+ | > lm4 = lm(log(cps$wage) ~ . -age, data = cps) | ||
+ | > summary(lm4) | ||
+ | |||
+ | Call: | ||
+ | lm(formula = log(cps$wage) ~ . - age, data = cps) | ||
+ | |||
+ | Residuals: | ||
+ | | ||
+ | -2.36103 -0.28080 | ||
+ | |||
+ | Coefficients: | ||
+ | | ||
+ | (Intercept) | ||
+ | education | ||
+ | south | ||
+ | sex1 -0.216934 | ||
+ | experience | ||
+ | union1 | ||
+ | race2 | ||
+ | race3 0.079851 | ||
+ | occupation2 -0.364444 | ||
+ | occupation3 -0.210295 | ||
+ | occupation4 -0.383882 | ||
+ | occupation5 -0.050664 | ||
+ | occupation6 -0.265348 | ||
+ | sector1 | ||
+ | sector2 | ||
+ | marr1 0.062211 | ||
+ | --- | ||
+ | Signif. codes: | ||
+ | |||
+ | Residual standard error: 0.4278 on 518 degrees of freedom | ||
+ | Multiple R-squared: | ||
+ | F-statistic: | ||
+ | |||
+ | > | ||
+ | |||
</ | </ | ||
- | < | + | <code>> lm5 = lm(log(cps$wage) ~ . -age -race, data = cps) |
+ | > summary(lm5) | ||
+ | |||
+ | Call: | ||
+ | lm(formula = log(cps$wage) ~ . - age - race, data = cps) | ||
+ | |||
+ | Residuals: | ||
+ | | ||
+ | -2.34366 -0.28169 -0.00017 | ||
+ | |||
+ | Coefficients: | ||
+ | | ||
+ | (Intercept) | ||
+ | education | ||
+ | south | ||
+ | sex1 -0.213602 | ||
+ | experience | ||
+ | union1 | ||
+ | occupation2 -0.355381 | ||
+ | occupation3 -0.209820 | ||
+ | occupation4 -0.385680 | ||
+ | occupation5 -0.047694 | ||
+ | occupation6 -0.254277 | ||
+ | sector1 | ||
+ | sector2 | ||
+ | marr1 0.065464 | ||
+ | --- | ||
+ | Signif. codes: | ||
+ | |||
+ | Residual standard error: 0.4283 on 520 degrees of freedom | ||
+ | Multiple R-squared: | ||
+ | F-statistic: | ||
+ | |||
+ | > | ||
</ | </ | ||
+ | < | ||
+ | > summary(lm6) | ||
+ | Call: | ||
+ | lm(formula = log(cps$wage) ~ . - age - race - occupation - marr - | ||
+ | sector, data = cps) | ||
+ | |||
+ | Residuals: | ||
+ | | ||
+ | -2.13809 -0.28681 -0.00078 | ||
+ | |||
+ | Coefficients: | ||
+ | | ||
+ | (Intercept) | ||
+ | education | ||
+ | south | ||
+ | sex1 -0.231978 | ||
+ | experience | ||
+ | union1 | ||
+ | --- | ||
+ | Signif. codes: | ||
+ | |||
+ | Residual standard error: 0.4433 on 528 degrees of freedom | ||
+ | Multiple R-squared: | ||
+ | F-statistic: | ||
+ | |||
+ | > </ |
multicolinearity.txt · Last modified: 2018/12/26 02:49 by hkimscil