1. No. 15, hal. 364 – A recent survey ...

A recent survey compared the costs of adoption through public and private
agencies. For a sample of 16 adoptions through a public agency, the mean
cost was $21,045, with a standard deviation of $835. For a sample of 18
adoptions through a private agency, the mean cost was $22,840, with a
standard deviation of $1,545. Can we conclude the mean cost is larger for
adopting children through a private agency? Use the .05 significance level.

Jawab:

Step 1: State the null hypothesis and the alternate hypothesis.

µ1 = Privat agency
µ2 = Public agency

H0 : µ1 ≤ µ2
H1 : µ1 > µ2
(Kata kunci: Biaya rata-rata privat agency lebih besar daripada
public agency)

Step 2: Select the level of significance.

∝ = 0,05 seperti yang tertera di soal

Step 3: Select the test statistic.

Menggunakan statistik uji t beda variansi.

Step 4: Formulate the decision rule.

𝑠12 𝑠22 2
( + )
𝑛1 𝑛2
Df =
𝑠12 2 𝑠22 2
( ) ( )
𝑛1 + 𝑛2
𝑛1−1 𝑛2−1

8352 1.5452 2
( + )
16 18
=
8352 1.5452
( 16 )2 ( 18 )2
+
16−1 18−1

1
Universitas Indonesia
 697.225 2.387025 2
( + )
16 18
= 697.225 2.387025 2
( 16 )2 ( 18 )
+
15 17

(43.576,5625+132.612,5)2
= 1.898.916.799 17.586.075.156
+
15 17

31.042.585.745
=
1.161.069.462

df = 26,736 ≈ 27
Critical t value = 1,706
Ho ditolak jika t27 > 1,706

Step 5: Make a decision and interpret the result.

𝑥𝑏𝑎𝑟 1−𝑥𝑏𝑎𝑟 2
t =
2 2
√𝑠1 +𝑠2
𝑛1 𝑛2
22.840−21.840
=
2 2
√835 +1.545
16 18
1.795
=
√697.225+2.387025
16 18
= 4,27637

Keputusan =
Ho ditolak. Hal ini disebabkan t value sebesar 4,27637 > tdf = 1,706.
Berada di wilayah Ho ditolak
Kesimpulan =
Rata-rata biaya privat agency lebih besar daripada rata-rata biaya
public agency.

2
Universitas Indonesia
2. No. 19, hal. 370-371 – The management of Discount Furniture
The management of Discount Furniture, a chain of discount furniture stores in
the Northeast, designed an incentive plan for salespeople. To evaluate this
innovative plan, 12 sales people were selected at random, and their weekly
incomes before and after the plan were recorded.

Salesperson Before ($) After ($)

Sid Mahone 320 340
Carol Quick 290 285
Tom Jackson 421 475
Andy Jones 510 510
Jean Sloan 210 210
Jack Walker 402 500
Peg Mancuso 625 631
Anita Loma 560 560
John Cuso 360 365
Carl Utz 431 431
A. S. Kushner 506 525
Fern Lawton 505 619

Was there a significant increase in the typical salesperson’s weekly income

due to the innovative incentive plan? Use the .05 significance level. Estimate
the p-value, and interpret it.

Jawab:
Step 1: State the null hypothesis and the alternate hypothesis.
H0 : µd ≤ 0
H1 : µd > 0
(Kata kunci: increase)

Step 2: Select the level of significance.

∝ = 0,05 seperti yang tertera di soal
df = n-1 = 12-1 = 11
Critical t value = 1,796

Step 3: Select the test statistic.

Menggunakan statistik uji t paired obsevartion

3
Universitas Indonesia
Step 4: Formulate the decision rule.
Ho ditolak jika tdf > 1,796

Step 5: Make a decision and interpret the result.

Salesperson After ($) Before ($) Difference (d) (d-d bar) (d-d bar)^2
Sid Mahone 340 320 20 -5,9167 35,0069
Carol Quick 285 290 -5 -30,9167 955,8403
Tom Jackson 475 421 54 28,0833 788,6736
Andy Jones 510 510 0 -25,9167 671,6736
Jean Sloan 210 210 0 -25,9167 671,6736
Jack Walker 500 402 98 72,0833 5.196,0069
Peg Mancuso 631 625 6 -19,9167 396,6736
Anita Loma 560 560 0 -25,9167 671,6736
John Cuso 365 360 5 -20,9167 437,5069
Carl Utz 431 431 0 -25,9167 671,6736
A. S. Kushner 525 506 19 -6,9167 47,8403
Fern Lawton 619 505 114 88,0833 7.758,6736
Total 311 0,0000 18.302,9167

∑𝑑
D bar =
𝑛
311
=
12
= 25,91667
∑(𝑑−𝑑 𝑏𝑎𝑟)^2
Sd =√ 𝑛−1

18.302,9167
=√ 11

= 40,7909489
𝑑 𝑏𝑎𝑟
T = 𝑠𝑑
√𝑛

25,91667
= 40,7909489
√12

= 2,2009286

Keputusan =
Ho ditolak. Hal ini disebabkan t12 = 2,2009286 > t df = 1,796.
Berada di wilayah Ho ditolak.

4
Universitas Indonesia
 Kesimpulan =
Inovative plan mengalami peningkatan untuk pendapatan harian.

Step 6: Estimate the p-value.

P value dari -2,2009286 berada pada line df 11, diantara significant
level 0,05 dan 0,025.
Dapat disimpulkan bahwa P value kurang dari 0,025.

3. No. 9, hal. 394 – A real estate developer ...

A real estate developer is considering investing in a shopping mall on the

outskirts of Atlanta, Georgia. Three parcels of land are being evaluated. Of
particular importance is the income in the area surrounding the proposed
mall. A random sample of four families is selected near each proposed mall.
Following are the sample results. At the .05 significance level, can the
developer conclude there is a difference in the mean income? Use the usual
six-step hypothesis testing procedure.

Southwyck Area Franklin Park Old Orchard

($000) ($000) ($000)
64 74 75
68 71 80
70 69 76
60 70 78

Jawab:
Step 1: State the null hypothesis and the alternate hypothesis.
S = Southwyek Area
F = Franklin Park
O = Old Orchard
H0 : µS = µF = µO
H1 : Semua nilai rata-rata income tidak sama.

Step 2: Select the level of significance.

∝ = 0,05 seperti yang tertera di soal

5
Universitas Indonesia
Step 3: Select the test statistic.
Menggunakan statistik uji tabel distribusi f.

Step 4: Formulate the decision rule.

k=3
df1 = (k-1) = 3-1 = 2
n = 4+ 4 + 4 = 12
df2 = 12-3 = 9
df = 4,26
Ho ditolak jika f > 4,26

Step 5: Make a decision and interpret the result.

Pertama kita menghitung coloum mean dan grand mean.

Southwyck Area Franklin Park Old Orchard

($000) ($000) ($000)
64 74 75
68 71 80
70 69 76
60 70 78
Total per Coloum 262 284 309
Coloum Mean 65,5 71 77,25
Total 855
Grand Mean 71,25

Selanjutnya menghitung SS Total dengan cara menjumlahkan semua

(x-Grand mean)2 atau dengan rumus sebagai berikut:

SS Total = ∑ (X-Grand mean)2

Perhitungannya sebagai berikut

6
Universitas Indonesia
 Southwyck Area Franklin Park Old Orchard
($000) ($000) ($000)
64 74 75
68 71 80
70 69 76
60 70 78
Total per Coloum 262 284 309
Coloum Mean 65,5 71 77,25
Total 855
Grand Mean 71,25
(x - Grand Mean)^2 52,5625 7,5625 14,0625
10,5625 0,0625 76,5625
1,5625 5,0625 22,5625
126,5625 1,5625 45,5625
SS Total 364,25

Selanjutnya menghitung SSE dengan cara menjumlahkan semua (x-

coloum mean)2 atau dengan rumus sebagai berikut:

SSE = ∑ (X-coloum mean)2

Perhitungannya sebagai berikut:

Southwyck Area Franklin Park Old Orchard

($000) ($000) ($000)
64 74 75
68 71 80
70 69 76
60 70 78
Total per Coloum 262 284 309
Coloum Mean 65,5 71 77,25
Total 855
Grand Mean 71,25
(x - Grand Mean)^2 52,5625 7,5625 14,0625
10,5625 0,0625 76,5625
1,5625 5,0625 22,5625
126,5625 1,5625 45,5625
SS Total 364,25
(x - Coloum Mean)^2 2,25 9 5,0625
6,25 0 7,5625
20,25 4 1,5625
30,25 1 0,5625
SSE 87,75

7
Universitas Indonesia
Selanjutnya menghitung SST dengan rumus sebagai berikut:

SST = SS Total – SSE

Perhitungannya sebagai berikut:

Southwyck Area Franklin Park Old Orchard

($000) ($000) ($000)
64 74 75
68 71 80
70 69 76
60 70 78
Total per Coloum 262 284 309
Coloum Mean 65,5 71 77,25
Total 855
Grand Mean 71,25
(x - Grand Mean)^2 52,5625 7,5625 14,0625
10,5625 0,0625 76,5625
1,5625 5,0625 22,5625
126,5625 1,5625 45,5625
SS Total 364,25
(x - Coloum Mean)^2 2,25 9 5,0625
6,25 0 7,5625
20,25 4 1,5625
30,25 1 0,5625
SSE 87,75
SST 276,5

Selanjutnya menghitung nilai F2,9

𝑆𝑆𝑇/(𝑘−1)
F2,9 =
𝑆𝑆𝐸/(𝑛−𝑘)
276,5/(3−1)
=
87,75/(12−3)

= 14,17948718

Dari perhitungan di atas dapat dibuat tabel anova sebagai berikut

Source of Variation Sum of Squares Degrees of Freedom Mean Square F
Treatment 276,5 2 138,25 14,1795
Error 87,75 9 9,75
Total 364,25 11

Jika kita mencari menggunakan data analysis di excel, kita akan

melihat hasil sebagai berikut:

8
Universitas Indonesia
 Anova: Single Factor

SUMMARY
Groups Count Sum Average Variance
Column 1 4 262 65,5 19,6667
Column 2 4 284 71 4,66667
Column 3 4 309 77,25 4,91667

ANOVA
Source of Variation SS df MS F P-value F crit
Between Groups 276,5 2 138,25 14,1795 0,00165 4,25649
Within Groups 87,75 9 9,75

Total 364,25 11

Keputusan =
Ho ditolak. Hal ini disebabkan F2,9 = 14,17948718 > F0,05;2;9 =
4,26. Berada di daerah Ho ditolak.
Kesimpulan =
Semua nilai rata-rata income tidak sama.

4. No. 17, hal. 403 – Chapin Manufacturing Company ...

Chapin Manufacturing Company operates 24 hours a day, 5 days a week. The

workers rotate shifts each week. Management is interested in whether there is
a difference in the number of units produced when the employees work on
various shifts. A sample of five workers is selected and their output recorded
on each shift. At the .05 significance level, can we conclude there is a
difference in the mean production rate by shift or by employee?
Units Produced
Employee Day Afternoon Night
Skaff 31 25 35
Lum 33 26 33
Clark 28 24 30
Treece 30 29 28
Morgan 28 26 27

9
Universitas Indonesia
Jawab:
Step 1: State the null hypothesis and the alternate hypothesis.
Waktu Shift:
1 = Day
2 = Afternoon
3 = Night
Employee:
S = Skaff
L = Lum
C = Clark
T = Treece
M = Morgan

Hipotesis 1 (treatment):
H0 : µ1 = µ2 = µ3
H1 : Semua nilai rata-rata produksi berdasarkan waktu shift
(treatment) tidak sama.

Hipotesis 2 (block):
H0 : µS = µL = µC = µT
H1 : Semua nilai rata-rata produksi berdasarkan employee (block)
tidak sama.

Step 2: Select the level of significance.

∝ = 0,05 seperti yang tertera di soal

Step 3: Select the test statistic.

Menggunakan statistik uji tabel distribusi f.

Step 4: Formulate the decision rule.

Rule 1 (treatment):
k=3
df1 = (k-1) = 3-1 = 2

10
Universitas Indonesia
 df2 = (k-1)(b-1) = (3-1)(5-1) = 8
df2;8 = 4,46
Ho ditolak jika f > 4,46

Rule 2 (block):
b=5
df1 = (b-1) = 5-1 = 4
df2 = (k-1)(b-1) = (3-1)(5-1) = 8
df4;8 = 3,84
Ho ditolak jika f > 3,84

Step 5: Make a decision and interpret the result.

Pertama kita menghitung coloum mean, block mean dan grand mean.

Units Produced Total per Block

Employee Day Afternoon Night Blok Mean
Skaff 31 25 35 91 30,3333333
Lum 33 26 33 92 30,6666667
Clark 28 24 30 82 27,3333333
Treece 30 29 28 87 29
Morgan 28 26 27 81 27
Total per Coloum 150 130 153
Coloum Mean 30 26 30,6
Total 433
Grand Mean 28,8666667

Selanjutnya menghitung SS Total dengan cara menjumlahkan semua

(x-Grand mean)2. . Rumus SS Total adalah sebagai berikut:

SS Total = ∑ (X-Grand mean)2

Perhitungannya sebagai berikut

11
Universitas Indonesia
 Units Produced Total per Block
Employee Day Afternoon Night Blok Mean
Skaff 31 25 35 91 30,3333333
Lum 33 26 33 92 30,6666667
Clark 28 24 30 82 27,3333333
Treece 30 29 28 87 29
Morgan 28 26 27 81 27
Total per Coloum 150 130 153
Coloum Mean 30 26 30,6
Total 433
Grand Mean 28,8666667
(x - Grand Mean)^2 4,55111111 14,9511111 37,6177778
17,0844444 8,21777778 17,0844444
0,75111111 23,6844444 1,28444444
1,28444444 0,01777778 0,75111111
0,75111111 8,21777778 3,48444444
SS Total 139,733333

Selanjutnya menghitung SSB dengan cara rumus berikut:

SSB = ∑ k(X block mean-Grand mean)2

Perhitungannya sebagai berikut:

Units Produced Total per Block

Employee Day Afternoon Night Blok Mean
Skaff 31 25 35 91 30,3333333
Lum 33 26 33 92 30,6666667
Clark 28 24 30 82 27,3333333
Treece 30 29 28 87 29
Morgan 28 26 27 81 27
Total per Coloum 150 130 153
Coloum Mean 30 26 30,6
Total 433
Grand Mean 28,8666667
(x - Grand Mean)^2 4,55111111 14,9511111 37,6177778
17,0844444 8,21777778 17,0844444
0,75111111 23,6844444 1,28444444
1,28444444 0,01777778 0,75111111
0,75111111 8,21777778 3,48444444
SS Total 139,733333
k(X block mean- Skaff 6,45333333
Grand mean)^2 Lum 9,72
Clark 7,05333333
Treece 0,05333333
Morgan 10,4533333
SSB 33,7333333

12
Universitas Indonesia
Selanjutnya menghitung SST dengan rumus berikut:

SST = ∑ (x - Coloum Mean)2

Perhitungannya sebagai berikut:

Units Produced Total per Block

Employee Day Afternoon Night Blok Mean
Skaff 31 25 35 91 30,3333333
Lum 33 26 33 92 30,6666667
Clark 28 24 30 82 27,3333333
Treece 30 29 28 87 29
Morgan 28 26 27 81 27
Total per Coloum 150 130 153
Coloum Mean 30 26 30,6
Total 433
Grand Mean 28,8666667
(x - Grand Mean)^2 4,55111111 14,9511111 37,6177778
17,0844444 8,21777778 17,0844444
0,75111111 23,6844444 1,28444444
1,28444444 0,01777778 0,75111111
0,75111111 8,21777778 3,48444444
SS Total 139,733333
k(X block mean- Skaff 6,45333333
Grand mean)^2 Lum 9,72
Clark 7,05333333
Treece 0,05333333
Morgan 10,4533333
SSB 33,7333333
(x - Coloum Mean)^2 Day 6,42222222
Afternoon 41,0888889
Night 15,0222222
SST 62,5333333

Selanjutnya menghitung SSE

SSE = SS Total – SSB - SST

Perhitungannya sebagai berikut:

13
Universitas Indonesia
 Units Produced Total per Block
Employee Day Afternoon Night Blok Mean
Skaff 31 25 35 91 30,3333333
Lum 33 26 33 92 30,6666667
Clark 28 24 30 82 27,3333333
Treece 30 29 28 87 29
Morgan 28 26 27 81 27
Total per Coloum 150 130 153
Coloum Mean 30 26 30,6
Total 433
Grand Mean 28,8666667
(x - Grand Mean)^2 4,55111111 14,9511111 37,6177778
17,0844444 8,21777778 17,0844444
0,75111111 23,6844444 1,28444444
1,28444444 0,01777778 0,75111111
0,75111111 8,21777778 3,48444444
SS Total 139,733333
k(X block mean- Skaff 6,45333333
Grand mean)^2 Lum 9,72
Clark 7,05333333
Treece 0,05333333
Morgan 10,4533333
SSB 33,7333333
(x - Coloum Mean)^2 Day 6,42222222
Afternoon 41,0888889
Night 15,0222222
SST 62,5333333
SSE 43,4666667

Selanjutnya menghitung nilai F

𝑆𝑆𝑇/(𝑘−1)
F1 =
𝑆𝑆𝐸/(𝑘−1)(𝑏−1)
62,5333/(3−1)
=
43,46667/(3−1)(5−1)
31,26667
=
5,43333
= 5,7546012

𝑆𝑆𝐵/(𝑏−1)
F2 =
𝑆𝑆𝐸/(𝑘−1)(𝑏−1)
33,7333/(5−1)
=
43,46667/(3−1)(5−1)

14
Universitas Indonesia
 8,43333
=
5,43333
= 1,5521472

Dari perhitungan di atas dapat dibuat tabel anova sebagai berikut

Degrees of
Source of Variation Sum of Squares Mean Square F
Freedom
Shift / Treatment 62,53333333 2 31,26666667 5,754601227
Employee / Block 33,73333333 4 8,433333333 1,552147239
Error 43,46666667 8 5,433333333
SS Total 139,7333333 6

Jika kita mencari menggunakan data analysis di excel, kita akan

melihat hasil sebagai berikut:
Anova: Two-Factor Without Replication

SUMMARY Count Sum Average Variance

Row 1 3 91 30,33333 25,3333
Row 2 3 92 30,66667 16,3333
Row 3 3 82 27,33333 9,33333
Row 4 3 87 29 1
Row 5 3 81 27 1

Column 1 5 150 30 4,5

Column 2 5 130 26 3,5
Column 3 5 153 30,6 11,3

ANOVA
Source of Variation SS df MS F P-value F crit
Columns (Shit/Treatment) 62,5333 2 31,26667 5,7546 0,02827 4,45897
Rows (Employee/Block) 33,7333 4 8,433333 1,55215 0,27615 3,83785
Error 43,4667 8 5,433333

Total 139,733 14

Keputusan
- Untuk waktu shift (treatment/column), Ho ditolak.
Hal ini disebabkan F = 5,7546 > Fdf = 4,4589. Berada di daerah
Ho ditolak.

15
Universitas Indonesia
- Untuk employee (block/rows), Ho tidak ditolak
Hal ini disebabkan F = 1,55215 < Fdf = 3,83785. Berada di
daerah Ho tidak ditolak.

Kesimpulan
Terdapat perbedaan nilai rata-rata produksi berdasarkan waktu shift,
namun tidak terjadi perbedaan nilai rata-rata produksi berdasarkan
pekerja (employee).

16
Universitas Indonesia