Scribd
Upload
54 views7 pages

Salary Variance Analysis

This document summarizes the results of one-way and two-way ANOVA tests examining the effect of job category and gender on employee salary. The one-way ANOVA found a significant effect of job category on salary. Post hoc comparisons showed significant differences in salary between all job categories. The two-way ANOVA found significant main effects of both job category and gender on salary, with managers earning significantly more than other categories and males earning more than females.

Uploaded by

Mc Evan
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
54 views7 pages

Salary Variance Analysis

This document summarizes the results of one-way and two-way ANOVA tests examining the effect of job category and gender on employee salary. The one-way ANOVA found a significant effect of job category on salary. Post hoc comparisons showed significant differences in salary between all job categories. The two-way ANOVA found significant main effects of both job category and gender on salary, with managers earning significantly more than other categories and males earning more than females.

Uploaded by

Mc Evan
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd

1.

Uji Anova one way

Levene's Test of Equality of Error Variancesa,b


Levene Statistic df1 df2 Sig.
SALARY Based on Mean 59.733 2 471 .000
Based on Median 51.189 2 471 .000
Based on Median and with 51.189 2 240.176 .000
adjusted df
Based on trimmed mean 56.201 2 471 .000
Tests the null hypothesis that the error variance of the dependent variable is equal across groups.
a. Dependent variable: SALARY
b. Design: Intercept + JOBCAT

Hasil uji levene test menunjukan bahwa nilai F test sebesar 59.733 dan signifikan pada 0,00 (p < 0,05)
yang berarti variance tidak sama (berbeda).

Tests of Between-Subjects Effects


Dependent Variable: SALARY
Type III Sum of
Source Squares df Mean Square F Sig.
Corrected Model 8943848392594 2 4471924196297 434.481 .000
.256a .128
Intercept 2914860905204 1 2914860905204 2832.005 .000
5.690 5.690
JOBCAT 8943848392594 2 4471924196297 434.481 .000
.264 .132
Error 4847801151039 471 10292571445.9
.699 44
Total 6994674369250 474
0.000
Corrected Total 1379164954363 473
3.955
a. R Squared = .648 (Adjusted R Squared = .647)
Multiple Comparisons
Dependent Variable: SALARY

Mean Difference 95% Confidence Interval


(I) JOBCAT (J) JOBCAT (I-J) Std. Error Sig. Lower Bound Upper Bound
Tukey HSD CLERICAL CUSTODIAL -$31,003.49 $20,237.602 .277 -$78,585.03 $16,578.05
MANAGER -$361,392.58* $12,283.518 .000 -$390,272.91 -$332,512.25
CUSTODIAL CLERICAL $31,003.49 $20,237.602 .277 -$16,578.05 $78,585.03
MANAGER -$330,389.09* $22,444.085 .000 -$383,158.39 -$277,619.79
MANAGER CLERICAL $361,392.58* $12,283.518 .000 $332,512.25 $390,272.91
CUSTODIAL $330,389.09* $22,444.085 .000 $277,619.79 $383,158.39
Bonferroni CLERICAL CUSTODIAL -$31,003.49 $20,237.602 .379 -$79,625.59 $17,618.61
MANAGER -$361,392.58* $12,283.518 .000 -$390,904.49 -$331,880.66
CUSTODIAL CLERICAL $31,003.49 $20,237.602 .379 -$17,618.61 $79,625.59
MANAGER -$330,389.09* $22,444.085 .000 -$384,312.40 -$276,465.78
MANAGER CLERICAL $361,392.58* $12,283.518 .000 $331,880.66 $390,904.49
CUSTODIAL $330,389.09* $22,444.085 .000 $276,465.78 $384,312.40
Based on observed means.
The error term is Mean Square(Error) = 10292571445.944.
*. The mean difference is significant at the ,05 level.
Levene's Test of Equality of Error Variancesa,b
Levene Statistic df1 df2 Sig.
SALARY Based on Mean 119.669 1 472 .000
Based on Median 51.603 1 472 .000
Based on Median and with 51.603 1 310.594 .000
adjusted df
Based on trimmed mean 95.446 1 472 .000
Tests the null hypothesis that the error variance of the dependent variable is equal across groups.
a. Dependent variable: SALARY
b. Design: Intercept + GENDER

Tests of Between-Subjects Effects


Dependent Variable: SALARY
Type III Sum of
Source Squares df Mean Square F Sig.
Corrected Model 2791853302883 1 2791853302883 119.798 .000
.252a .252
Intercept 5352592999663 1 5352592999663 2296.792 .000
8.520 8.520
GENDER 2791853302883 1 2791853302883 119.798 .000
.271 .271
Error 1099979624075 472 23304653052.4
0.703 38
Total 6994674369250 474
0.000
Corrected Total 1379164954363 473
3.955
a. R Squared = .202 (Adjusted R Squared = .201)
2. Uji Anova Two ways dan Main effects

Levene's Test of Equality of Error


Variancesa
Dependent Variable: SALARY
F df1 df2 Sig.
32.580 4 469 .000
Tests the null hypothesis that the error variance of
the dependent variable is equal across groups.
a. Design: Intercept + GENDER + JOBCAT

Tests of Between-Subjects Effects


Dependent Variable: SALARY
Type III Sum of
Source Squares df Mean Square F Sig.
Corrected Model 9520867441836 3 3173622480612 349.257 .000
.700a .233
Intercept 2322227547746 1 2322227547746 2555.614 .000
9.164 9.164
GENDER 577019049242. 1 577019049242. 63.501 .000
446 446
JOBCAT 6729014138953 2 3364507069476 370.264 .000
.440 .720
Error 4270782101797 470 9086770429.35
.255 6
Total 6994674369250 474
0.000
Corrected Total 1379164954363 473
3.955
a. R Squared = .690 (Adjusted R Squared = .688)
Multiple Comparisons
Dependent Variable: SALARY

Mean Difference 95% Confidence Interval


(I) JOBCAT (J) JOBCAT (I-J) Std. Error Sig. Lower Bound Upper Bound
Tukey HSD CLERICAL CUSTODIAL -$31,003.49 $19,015.243 .234 -$75,711.39 $13,704.41
MANAGER -$361,392.58* $11,541.588 .000 -$388,528.71 -$334,256.45
CUSTODIAL CLERICAL $31,003.49 $19,015.243 .234 -$13,704.41 $75,711.39
MANAGER -$330,389.09* $21,088.454 .000 -$379,971.44 -$280,806.74
MANAGER CLERICAL $361,392.58* $11,541.588 .000 $334,256.45 $388,528.71
CUSTODIAL $330,389.09* $21,088.454 .000 $280,806.74 $379,971.44
Bonferroni CLERICAL CUSTODIAL -$31,003.49 $19,015.243 .311 -$76,689.14 $14,682.16
MANAGER -$361,392.58* $11,541.588 .000 -$389,122.17 -$333,662.98
CUSTODIAL CLERICAL $31,003.49 $19,015.243 .311 -$14,682.16 $76,689.14
MANAGER -$330,389.09* $21,088.454 .000 -$381,055.80 -$279,722.38
MANAGER CLERICAL $361,392.58* $11,541.588 .000 $333,662.98 $389,122.17
CUSTODIAL $330,389.09* $21,088.454 .000 $279,722.38 $381,055.80
Based on observed means.
The error term is Mean Square(Error) = 9086770429.356.
*. The mean difference is significant at the ,05 level.

SALARY
Subset
JOBCAT N 1 2
Tukey HSDa,b,c CLERICAL 363 $278,385.40
CUSTODIAL 27 $309,388.89
MANAGER 84 $639,777.98
Sig. .187 1.000
Means for groups in homogeneous subsets are displayed.
Based on observed means.
The error term is Mean Square(Error) = 9086770429.356.
a. Uses Harmonic Mean Sample Size = 58.031.
b. The group sizes are unequal. The harmonic mean of the group sizes is used.
Type I error levels are not guaranteed.
c. Alpha = ,05.
3. Uji Anova Two Ways dengan Main Effect dan Interaction Effect

Levene's Test of Equality of Error Variancesa,b


Levene Statistic df1 df2 Sig.
SALARY Based on Mean 33.383 4 469 .000
Based on Median 30.319 4 469 .000
Based on Median and with 30.319 4 218.439 .000
adjusted df
Based on trimmed mean 31.727 4 469 .000
Tests the null hypothesis that the error variance of the dependent variable is equal across groups.
a. Dependent variable: SALARY
b. Design: Intercept + GENDER + JOBCAT + GENDER * JOBCAT

Tests of Between-Subjects Effects


Dependent Variable: SALARY
Type III Sum of
Source Squares df Mean Square F Sig.
Corrected Model 9645635728510 4 2411408932127 272.780 .000
.354a .588
Intercept 1772719430719 1 1772719430719 2005.313 .000
2.676 2.676
GENDER 524744073156. 1 524744073156. 59.359 .000
799 799
JOBCAT 3231633204129 2 1615816602064 182.782 .000
.792 .896
GENDER * JOBCAT 124768286673. 1 124768286673. 14.114 .000
662 662
Error 4146013815123 469 8840114744.40
.602 0
Total 6994674369250 474
0.000
Corrected Total 1379164954363 473
3.955
a. R Squared = .699 (Adjusted R Squared = .697)

You might also like