publish
These linear models try to see if there’s any relation between Women working and being involve and politics and Child mortality. I got all my the data from http://statusofwomendata.org
## State Labor..participation.White Labor.participation.Hispanic
## 1 Alabama 0.51 0.54
## 2 Alaska 0.67 0.77
## 3 Arizona 0.54 0.56
## 4 Arkansas 0.53 0.59
## 5 California 0.56 0.58
## 6 Colorado 0.63 0.62
## Labor.participation.Black Labor.participaton.All.Women Score Grade
## 1 0.59 0.53 3.77 D
## 2 n/a 0.67 4.22 B
## 3 0.62 0.55 3.99 C+
## 4 0.60 0.54 3.47 F
## 5 0.59 0.58 4.14 B-
## 6 0.65 0.63 4.21 B
## All.Women White.Women Hispanic.Women Black.Women
## 1 37 6.8 5.2 13.3
## 2 12 3.2 N/A N/A
## 3 15 4.9 6.0 10.4
## 4 27 6.5 5.9 10.5
## 5 5 3.9 4.6 9.1
## 6 6 4.6 5.5 11.2##
## Call:
## lm(formula = All.Women ~ Labor.participaton.All.Women + Score,
## data = FullData1)
##
## Residuals:
## Min 1Q Median 3Q Max
## -16.3037 -7.7980 0.6553 5.5191 22.2687
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 96.4180 21.1891 4.550 3.55e-05 ***
## Labor.participaton.All.Women -124.9925 41.0167 -3.047 0.00371 **
## Score -0.6325 5.6189 -0.113 0.91083
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 8.857 on 49 degrees of freedom
## Multiple R-squared: 0.2336, Adjusted R-squared: 0.2024
## F-statistic: 7.47 on 2 and 49 DF, p-value: 0.001474## Loading required package: zoo
##
## Attaching package: 'zoo'
##
## The following objects are masked from 'package:base':
##
## as.Date, as.Date.numeric##
## studentized Breusch-Pagan test
##
## data: Out1
## BP = 8.3806, df = 2, p-value = 0.01514```
After testing for Heteroskedasticity we can see that the value we gotten states that yes there might be some heteroskdasticity in my data, which I assume will occur because of some outliers… Here is the plot:
Now let’s see what happens when we work with ethnicities, this time I’m going to try with White women.
FullData1 <-read.csv("FullData.csv")
Out2 <-lm(White.Women~Labor..participation.White, data = FullData1)
summary(Out2)##
## Call:
## lm(formula = White.Women ~ Labor..participation.White, data = FullData1)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.94552 -0.62496 -0.06983 0.70494 1.47222
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 12.038 1.532 7.856 2.78e-10 ***
## Labor..participation.White -11.682 2.585 -4.518 3.83e-05 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8888 on 50 degrees of freedom
## Multiple R-squared: 0.2899, Adjusted R-squared: 0.2757
## F-statistic: 20.42 on 1 and 50 DF, p-value: 3.828e-05bptest(Out2)##
## studentized Breusch-Pagan test
##
## data: Out2
## BP = 0.024295, df = 1, p-value = 0.8761splot <- ggplot(aes(FullData1$Labor..participation.White,FullData1$White.Women),data = FullData1)
splot + geom_point() + geom_smooth(method="lm")
Now let us see with Black Women.
FullData1 <-read.csv("FullData.csv")
FullData1$Black.Women <- as.numeric(FullData1$Black.Women)
Out3 <-lm(Black.Women~Labor.participation.Black, data = FullData1)
summary(Out3)##
## Call:
## lm(formula = Black.Women ~ Labor.participation.Black, data = FullData1)
##
## Residuals:
## Min 1Q Median 3Q Max
## -18.1818 -3.4000 0.8333 2.5750 17.0000
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 31.0000 7.6475 4.054 0.000249 ***
## Labor.participation.Black0.56 -23.0000 10.8152 -2.127 0.040184 *
## Labor.participation.Black0.58 -10.0000 10.8152 -0.925 0.361155
## Labor.participation.Black0.59 -9.6667 8.8306 -1.095 0.280733
## Labor.participation.Black0.60 -21.6667 8.8306 -2.454 0.018975 *
## Labor.participation.Black0.61 -11.5000 8.2603 -1.392 0.172172
## Labor.participation.Black0.62 -16.0000 8.0612 -1.985 0.054617 .
## Labor.participation.Black0.63 -12.0000 8.8306 -1.359 0.182402
## Labor.participation.Black0.64 -23.3333 8.8306 -2.642 0.011998 *
## Labor.participation.Black0.65 -19.8000 8.3775 -2.363 0.023468 *
## Labor.participation.Black0.67 -7.0000 9.3663 -0.747 0.459569
## Labor.participation.Black0.68 -22.0000 10.8152 -2.034 0.049151 *
## Labor.participation.Black0.69 -24.0000 9.3663 -2.562 0.014600 *
## Labor.participation.Black0.71 -20.0000 10.8152 -1.849 0.072424 .
## Labor.participation.Blackn/a -0.8182 7.9876 -0.102 0.918967
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 7.648 on 37 degrees of freedom
## Multiple R-squared: 0.6007, Adjusted R-squared: 0.4497
## F-statistic: 3.976 on 14 and 37 DF, p-value: 0.0003793bptest(Out3)##
## studentized Breusch-Pagan test
##
## data: Out3
## BP = 13.843, df = 14, p-value = 0.4615splot <- ggplot(aes(FullData1$Labor.participation.Black,FullData1$Black.Women),data = FullData1)
splot + geom_point() + geom_smooth(method="lm")## geom_smooth: Only one unique x value each group.Maybe you want aes(group = 1)?