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 02:21] – hkimscil | multicolinearity [2018/12/26 02:49] (current) – [regression test with factors] hkimscil | ||
---|---|---|---|
Line 1: | Line 1: | ||
- | ====== Multi-colinearity ====== | + | ====== Multi-colinearity |
+ | required library: | ||
+ | * corrplot | ||
+ | * mctest | ||
+ | * omcdiag | ||
+ | * imcdiag | ||
+ | |||
< | < | ||
> cps <- read.csv(" | > cps <- read.csv(" | ||
Line 70: | Line 77: | ||
> library(corrplot) | > library(corrplot) | ||
> cps.cor = cor(cps) | > cps.cor = cor(cps) | ||
- | > corrplot.mixed(cps.cor, | + | > corrplot.mixed(cps.cor, |
</ | </ | ||
- | {{cps.corplot.png}} | + | {{cps.corrplot.png?500}} |
< | < | ||
Line 178: | Line 185: | ||
F-statistic: | F-statistic: | ||
- | > anova(lm1, lm2) | + | > summary(lm1) |
- | Analysis of Variance Table | + | |
- | Model 1: log(cps$wage) ~ education + south + sex + experience + union + | + | Call: |
- | age + race + occupation + sector + marr | + | lm(formula = log(cps$wage) ~ ., data = cps) |
- | Model 2: log(cps$wage) ~ (education | + | |
- | age + race + occupation + sector + marr) - age | + | Residuals: |
- | Res.Df RSS Df Sum of Sq F Pr(>F) | + | |
- | 1 523 101.17 | + | -2.16246 -0.29163 -0.00469 |
- | 2 524 101.28 -1 -0.11518 0.5954 0.4407 | + | |
+ | Coefficients: | ||
+ | | ||
+ | (Intercept) | ||
+ | education | ||
+ | south -0.102360 | ||
+ | sex -0.221997 | ||
+ | experience | ||
+ | union | ||
+ | age | ||
+ | race | ||
+ | occupation | ||
+ | sector | ||
+ | marr | ||
+ | --- | ||
+ | Signif. codes: | ||
+ | |||
+ | Residual standard error: 0.4398 on 523 degrees of freedom | ||
+ | Multiple R-squared: | ||
+ | F-statistic: | ||
+ | |||
+ | > | ||
> </ | > </ | ||
+ | ====== regression test with factors ====== | ||
< | < | ||
+ | > cps$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.1545758501.txt.gz · Last modified: 2018/12/26 02:21 by hkimscil