HR Analysis

hrdata <- read.csv("HR-Employee-Attrition.csv")

hrdata[ , c("Age", "DailyRate", "DistanceFromHome", "Education", "HourlyRate", "MonthlyIncome", "MonthlyRate", "NumCompaniesWorked", "TotalWorkingYears", "TrainingTimesLastYear")]

cor_matrix <- cor( hrdata[ , c("Age", "DailyRate", "DistanceFromHome", "Education", "HourlyRate", "MonthlyIncome", "MonthlyRate", "NumCompaniesWorked", "TotalWorkingYears", "TrainingTimesLastYear")] )

print(round(cor_matrix,2))

                        Age DailyRate DistanceFromHome Education HourlyRate MonthlyIncome MonthlyRate NumCompaniesWorked TotalWorkingYears TrainingTimesLastYear
Age                    1.00      0.01             0.00      0.21       0.02          0.50        0.03               0.30              0.68                 -0.02
DailyRate              0.01      1.00             0.00     -0.02       0.02          0.01       -0.03               0.04              0.01                  0.00
DistanceFromHome       0.00      0.00             1.00      0.02       0.03         -0.02        0.03              -0.03              0.00                 -0.04
Education              0.21     -0.02             0.02      1.00       0.02          0.09       -0.03               0.13              0.15                 -0.03
HourlyRate             0.02      0.02             0.03      0.02       1.00         -0.02       -0.02               0.02              0.00                 -0.01
MonthlyIncome          0.50      0.01            -0.02      0.09      -0.02          1.00        0.03               0.15              0.77                 -0.02
MonthlyRate            0.03     -0.03             0.03     -0.03      -0.02          0.03        1.00               0.02              0.03                  0.00
NumCompaniesWorked     0.30      0.04            -0.03      0.13       0.02          0.15        0.02               1.00              0.24                 -0.07
TotalWorkingYears      0.68      0.01             0.00      0.15       0.00          0.77        0.03               0.24              1.00                 -0.04
TrainingTimesLastYear -0.02      0.00            -0.04     -0.03      -0.01         -0.02        0.00              -0.07             -0.04                  1.00

pairs(~MonthlyIncome+Age+TotalWorkingYears+Education,data = hrdata, main = "Scatterplot Matrix")

boxplot(Age~Attrition,data=hrdata, main= "Who Got Fired", xlab="Attrition", ylab="Age")

boxplot(Age ~ Attrition, data = hrdata, 
        main = "Who Got Fired", xlab = "Attrition", ylab = "Age")

# Add jittered points
stripchart(Age ~ Attrition, data = hrdata, 
           vertical = TRUE, method = "jitter", pch = 21, col = 'blue', bg = 'lightblue', add = TRUE)

yes_age <- hrdata[(hrdata$Attrition == "Yes"),'Age'] 
no_age <- hrdata[(hrdata$Attrition != "Yes"),'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 

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