Demographic Differences Across Race and Sex

Race

Age

y = MeasurementData1$Age0
x = MeasurementData1$Race
t.test(y~x)
## 
##  Welch Two Sample t-test
## 
## data:  y by x
## t = 0.307, df = 1868, p-value = 0.7589
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -0.6803  0.9328
## sample estimates:
## mean in group 0 mean in group 1 
##           47.90           47.77

Depression

y = MeasurementData1$CES
x = MeasurementData1$Race
t.test(y~x)
## 
##  Welch Two Sample t-test
## 
## data:  y by x
## t = -0.8975, df = 1829, p-value = 0.3696
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -1.4522  0.5404
## sample estimates:
## mean in group 0 mean in group 1 
##           14.51           14.96

Education

fit <- aov(Educ ~ Race, data=MeasurementData1)
summary(fit)
##               Df Sum Sq Mean Sq F value  Pr(>F)
## Race           1    115   115.3    12.9 0.00034
## Residuals   2075  18546     8.9

Employment

fit <- aov(Employment01 ~ Race, data=MeasurementData1)
summary(fit)
##               Df Sum Sq Mean Sq F value Pr(>F)
## Race           1      2   1.664    6.84  0.009
## Residuals   2075    504   0.243

Neighborhood

fit <- aov(Neighborhood02 ~ Race, data=MeasurementData1)
summary(fit)
##               Df Sum Sq Mean Sq F value Pr(>F)
## Race           1      0   0.097    0.09   0.77
## Residuals   2075   2360   1.137

Income

fit <- aov(acasiIncomx01 ~ Race, data=MeasurementData1)
summary(fit)
##               Df Sum Sq Mean Sq F value Pr(>F)
## Race           1     20   20.40    85.1 <2e-16
## Residuals   2075    497    0.24

Self-Rated Health

fit <- aov(sHealthNum ~ Race, data=MeasurementData1)
summary(fit)
##               Df Sum Sq Mean Sq F value Pr(>F)
## Race           1      1   0.588    1.02   0.31
## Residuals   2075   1201   0.579

MacArthur Social Status Ladder

#ANOVA
fit <- aov(MCLcountry ~ Race, data=MeasurementData1)
summary(fit)
##               Df Sum Sq Mean Sq F value Pr(>F)
## Race           1     26   25.57    6.42  0.011
## Residuals   2075   8266    3.98
#t-test
y = MeasurementData1$MCLcountry
x = MeasurementData1$Race
t.test(y~x)
## 
##  Welch Two Sample t-test
## 
## data:  y by x
## t = 2.559, df = 1953, p-value = 0.01058
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  0.05245 0.39679
## sample estimates:
## mean in group 0 mean in group 1 
##           4.460           4.236

Sex

Age

y = MeasurementData1$Age0
x = MeasurementData1$Sex
t.test(y~x)
## 
##  Welch Two Sample t-test
## 
## data:  y by x
## t = -0.5605, df = 1940, p-value = 0.5752
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -1.0289  0.5715
## sample estimates:
## mean in group 0 mean in group 1 
##           47.75           47.98

Depression

y = MeasurementData1$CES
x = MeasurementData1$Sex
t.test(y~x)
## 
##  Welch Two Sample t-test
## 
## data:  y by x
## t = 3.307, df = 2034, p-value = 0.0009598
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  0.6619 2.5909
## sample estimates:
## mean in group 0 mean in group 1 
##           15.40           13.78

Education

fit <- aov(Educ ~ Sex, data=MeasurementData1)
summary(fit)
##               Df Sum Sq Mean Sq F value Pr(>F)
## Sex            1      1    0.89     0.1   0.75
## Residuals   2075  18660    8.99

Employment

fit <- aov(Employment01 ~ Sex, data=MeasurementData1)
summary(fit)
##               Df Sum Sq Mean Sq F value  Pr(>F)
## Sex            1      3    3.43    14.1 0.00017
## Residuals   2075    503    0.24

Neighborhood

fit <- aov(Neighborhood02 ~ Sex, data=MeasurementData1)
summary(fit)
##               Df Sum Sq Mean Sq F value Pr(>F)
## Sex            1      5    4.74    4.18  0.041
## Residuals   2075   2355    1.14

Income

fit <- aov(acasiIncomx01 ~ Sex, data=MeasurementData1)
summary(fit)
##               Df Sum Sq Mean Sq F value  Pr(>F)
## Sex            1      3   2.725      11 0.00094
## Residuals   2075    515   0.248

Self-Rated Health

fit <- aov(sHealthNum ~ Sex, data=MeasurementData1)
summary(fit)
##               Df Sum Sq Mean Sq F value Pr(>F)
## Sex            1      2   1.984    3.43  0.064
## Residuals   2075   1199   0.578

MacArthur Social Status Ladder

#ANOVA
fit <- aov(MCLcountry ~ Sex, data=MeasurementData1)
summary(fit)
##               Df Sum Sq Mean Sq F value Pr(>F)
## Sex            1      8    7.87    1.97   0.16
## Residuals   2075   8284    3.99
#t-test
y = MeasurementData1$MCLcountry
x = MeasurementData1$Sex
t.test(y~x)
## 
##  Welch Two Sample t-test
## 
## data:  y by x
## t = -1.403, df = 1919, p-value = 0.1607
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -0.29806  0.04942
## sample estimates:
## mean in group 0 mean in group 1 
##           4.312           4.436