hrdata <- read.csv("HR-Employee-Attrition.csv")
cor(
hrdata[ , c("Age", "DailyRate", "DistanceFromHome", "Education", "HourlyRate", "MonthlyIncome", "MonthlyRate", "NumCompaniesWorked", "TotalWorkingYears", "TrainingTimesLastYear")]
)
## Age DailyRate DistanceFromHome Education
## Age 1.00000000 0.010660943 -0.001686120 0.20803373
## DailyRate 0.01066094 1.000000000 -0.004985337 -0.01680643
## DistanceFromHome -0.00168612 -0.004985337 1.000000000 0.02104183
## Education 0.20803373 -0.016806433 0.021041826 1.00000000
## HourlyRate 0.02428654 0.023381422 0.031130586 0.01677483
## MonthlyIncome 0.49785457 0.007707059 -0.017014445 0.09496068
## MonthlyRate 0.02805117 -0.032181602 0.027472864 -0.02608420
## NumCompaniesWorked 0.29963476 0.038153434 -0.029250804 0.12631656
## TotalWorkingYears 0.68038054 0.014514739 0.004628426 0.14827970
## TrainingTimesLastYear -0.01962082 0.002452543 -0.036942234 -0.02510024
## HourlyRate MonthlyIncome MonthlyRate
## Age 0.024286543 0.497854567 0.028051167
## DailyRate 0.023381422 0.007707059 -0.032181602
## DistanceFromHome 0.031130586 -0.017014445 0.027472864
## Education 0.016774829 0.094960677 -0.026084197
## HourlyRate 1.000000000 -0.015794304 -0.015296750
## MonthlyIncome -0.015794304 1.000000000 0.034813626
## MonthlyRate -0.015296750 0.034813626 1.000000000
## NumCompaniesWorked 0.022156883 0.149515216 0.017521353
## TotalWorkingYears -0.002333682 0.772893246 0.026442471
## TrainingTimesLastYear -0.008547685 -0.021736277 0.001466881
## NumCompaniesWorked TotalWorkingYears
## Age 0.29963476 0.680380536
## DailyRate 0.03815343 0.014514739
## DistanceFromHome -0.02925080 0.004628426
## Education 0.12631656 0.148279697
## HourlyRate 0.02215688 -0.002333682
## MonthlyIncome 0.14951522 0.772893246
## MonthlyRate 0.01752135 0.026442471
## NumCompaniesWorked 1.00000000 0.237638590
## TotalWorkingYears 0.23763859 1.000000000
## TrainingTimesLastYear -0.06605407 -0.035661571
## TrainingTimesLastYear
## Age -0.019620819
## DailyRate 0.002452543
## DistanceFromHome -0.036942234
## Education -0.025100241
## HourlyRate -0.008547685
## MonthlyIncome -0.021736277
## MonthlyRate 0.001466881
## NumCompaniesWorked -0.066054072
## TotalWorkingYears -0.035661571
## TrainingTimesLastYear 1.000000000
pairs(~MonthlyIncome+Age+TotalWorkingYears+Education,data = hrdata,
main = "Scatterplot Matrix")
yes_age <- hrdata[(hrdata$Attrition=="Yes"),'Age']
no_age <- hrdata[(hrdata$Attrition=="No"),'Age']
t.test(yes_age, no_age)
##
## Welch Two Sample t-test
##
## data: yes_age and no_age
## t = -5.828, df = 316.93, p-value = 1.38e-08
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -5.288346 -2.618930
## sample estimates:
## mean of x mean of y
## 33.60759 37.56123
boxplot(EmployeeNumber~Attrition,data=hrdata, main="Who Got Fired", xlab="Attrition", ylab="EmployeeNumber")
yes_number <- hrdata[(hrdata$Attrition == "Yes"), 'EmployeeNumber']
no_number <- hrdata[(hrdata$Attrition =="No"), 'EmployeeNumber']
t.test(yes_number,no_number)
##
## Welch Two Sample t-test
##
## data: yes_number and no_number
## t = -0.41725, df = 342.33, p-value = 0.6768
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -98.91087 64.29061
## sample estimates:
## mean of x mean of y
## 1010.346 1027.656
model1 = lm(MonthlyIncome ~ Age, data = hrdata)
summary(model1)
##
## Call:
## lm(formula = MonthlyIncome ~ Age, data = hrdata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -9990.1 -2592.7 -677.9 1810.5 12540.8
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -2970.67 443.70 -6.695 3.06e-11 ***
## Age 256.57 11.67 21.995 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 4084 on 1468 degrees of freedom
## Multiple R-squared: 0.2479, Adjusted R-squared: 0.2473
## F-statistic: 483.8 on 1 and 1468 DF, p-value: < 2.2e-16
model2 = lm(MonthlyIncome ~ Age + TotalWorkingYears, data = hrdata)
summary(model2)
##
## Call:
## lm(formula = MonthlyIncome ~ Age + TotalWorkingYears, data = hrdata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -11310.8 -1690.8 -91.4 1428.3 11461.5
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1978.08 352.36 5.614 2.36e-08 ***
## Age -26.87 11.63 -2.311 0.021 *
## TotalWorkingYears 489.13 13.65 35.824 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 2984 on 1467 degrees of freedom
## Multiple R-squared: 0.5988, Adjusted R-squared: 0.5983
## F-statistic: 1095 on 2 and 1467 DF, p-value: < 2.2e-16