Minggu, 09 Juli 2017

analisis regresi hal 222 pertemuan 14

Halaman 222

ESTIMASI MODEL 1 : CHOL = 203.123 + 0.127 TRIG

ANOVA b

Model Sum of

Squares

df Mean Square F Sig.

1 Regression 1181.676 1 1181.676 1.850 .181 a

Residual 27464.768 43 638.716

Total 28646.444 44

a. Predictors: (Constant), trigliserida

b. Dependent Variable: cholesterol

Coefficients a

Model Unstandardized

Coefficients

Standardized

Coefficients

t Sig.

B Std. Error Beta

1 (Constant) 203.123 17.156 11.840 .000

trigliserida .127 .093 .203 1.360 .181

a. Dependent Variable: cholesterol

ESTIMASI MODEL 2 : CHOL = 204.048 + 0.445 UMUR

ANOVA b

Model Sum of

Squares

df Mean Square F Sig.

1 Regression 655.625 1 655.625 1.007 .321 a

Residual 27990.819 43 650.949

Total 28646.444 44

a. Predictors: (Constant), umur

b. Dependent Variable: cholesterol

Coefficients a

Model Unstandardized

Coefficients

Standardized

Coefficients

t Sig.

B Std. Error Beta

1 (Constant) 204.048 22.093 9.236 .000

Umur .445 .444 .151 1.004 .321

a. Dependent Variable: cholesterol

Coefficients a

Model Unstandardized

Coefficients

Standardized

Coefficients

t Sig.

B Std. Error Beta

1 (Constant) 203.123 17.156 11.840 .000

trigliserida .127 .093 .203 1.360 .181

a. Dependent Variable: cholesterol

ESTIMASI MODEL 3 : CHOL = 217.420 + 0.003 UMQS

ANOVA b

Model Sum of

Squares

df Mean Square F Sig.

1 Regression 396.227 1 396.227 .603 .442 a

Residual 28250.217 43 656.982

Total 28646.444 44

a. Predictors: (Constant), umur kuadrat

b. Dependent Variable: cholesterol

Coefficients a

Model Unstandardized

Coefficients

Standardized

Coefficients

t Sig.

B Std. Error Beta

1 (Constant) 217.420 11.555 18.816 .000

umur kuadrat .003 .004 .118 .777 .442

a. Dependent Variable: cholesterol

ESTIMASI MODEL 4 : CHOL = 192.155 + 0.292 UM + 0.108 TRIG

ANOVA b

Model Sum of

Squares

df Mean Square F Sig.

1 Regression 1437.719 2 718.860 1.110 .339 a

Residual 27208.725 42 647.827

Total 28646.444 44

a. Predictors: (Constant), trigliserida, umur

b. Dependent Variable: cholesterol

Coefficients a

Model Unstandardized

Coefficients

Standardized

Coefficients

t Sig.

B Std. Error Beta

1 (Constant) 192.155 24.554 7.826 .000

Umur .292 .464 .099 .629 .533

trigliserida .108 .098 .173 1.099 .278

a. Dependent Variable: cholesterol

ESTIMASI MODEL 5 : CHOL = - 25.670 + 9.838 UM - 0.093 UMQS

ANOVA b

Model Sum of

Squares

df Mean Square F Sig.

1 Regression 3678.335 2 1839.167 3.094 .056 a

Residual 24968.110 42 594.479

Total 28646.444 44

a. Predictors: (Constant), umur kuadrat, umur

b. Dependent Variable: cholesterol

Coefficients a

Model Unstandardized

Coefficients

Standardized

Coefficients

T Sig.

B Std. Error Beta

1 (Constant) -25.670 104.039 -.247 .806

umur 9.838 4.187 3.342 2.350 .024

umur kuadrat -.093 .041 -3.207 -2.255 .029

a. Dependent Variable: cholesterol

ESTIMASI MODEL 6 : CHOL = - 21.969 + 9.220 UM + 0.079 TRIG - 0.088 UMQS

ANOVA b

Model Sum of

Squares

df Mean Square F Sig.

1 Regression 4086.344 3 1362.115 2.274 .094 a

Residual 24560.100 41 599.027

Total 28646.444 44

a. Predictors: (Constant), umur kuadrat, trigliserida, umur

b. Dependent Variable: cholesterol

Coefficients a

Model Unstandardized

Coefficients

Standardized

Coefficients

T Sig.

B Std. Error Beta

1 (Constant) -21.969 104.532 -.210 .835

umur 9.220 4.269 3.132 2.160 .037

trigliserida .079 .095 .126 .825 .414

umur kuadrat -.088 .042 -3.035 -2.103 .042

a. Dependent Variable: cholesterol

Kita lakukan uji parsial F seperti berikut (berdasarkan hasil-hasil yang sudah kita lakukan diatas)

ANOVA Tabel untuk TRIG dengan CHOL dan UM , UMSQ

Sumber Df SS MS F r 2

X1 1 1181.676 1181.676 1.97266 0.143

Regresi X2│X1 1 1.21668 1.21668 0.00203

X3│X1, X2 1 2.84224 2.84224 0.00474

Residual 41 24560.100 599.027

Total 44 28646.444

Nilai F untuk penambahan independent variabel X 3 = 0.00474 < F 4.08 ini berarti hipotesa H 0 :

β 3 = 0 diterima atau gagal ditolak artinya penambahan third order ( X 3 ) tidak secara bermakna

dapat memprediksi Y.

Kita bersimpulan bahwa :

a. Penambahan “ second order” sesuai (fit) dengan nilai r 2 = 0.128

b. Penambahan nilai r 2 menjadi 0.143 pada “ thind order” hanya sebesar 0.015 adalah kecil

c. Kurva yang ada cukup diterangkan dengan “second order”

TUGAS HALAMAN 223

Source df SS MS F

X 1 174.473,96 174.473,96 429,1691

Regresi X 2 │X 1 10.515,44 10515,44 25,8658

X 3 │X,X 2 1 415,19 415,19 1,02128

Residual 15 6098,08 406,539

Total 18 190.502,93

Model regresi :

Model estimasi 1 : Y = - 122.345 + 6.227 X

Model estimasi 2 : Y = 32.091 – 3.051 X + 0.1176 X 2

Model estimasi 3 : Y = 114.621 – 10.620 X + 0.3247 X 2 + 0.00173 X 3

Jawaban :

1. Nilai r 2 1 :

2. Nilai r 2 2 :

3. Nilai r 2 3 :

4. Nilai F model estimasi 1: 429.19 > F tabel 4.54, maka kesimpulan perubahan

penambahan independen variabel X secara bermakna meningkatkan prediksi Y.

5. Nilai F model estimasi 2 : 25.87 > F tabel 4.54, maka kesimpulan perubahan

penambahan independen variabel X 2 secara bermakna meningkatkan prediksi Y.

Sabtu, 08 Juli 2017

ANALISIS REGRESI HALAMAN 221

Analisis Regresi pertemuan 13

TUGAS ANALISIS REGRESI HALAMAN  221
Lakukan prediksi TRI dengan variabel independen IMT, Umur dan Umur kuadrat
Bekerja bersama di Laboratorium
  1. Lakukan analisa regresi masing-masing independen variabel
  2. Hitung SS for Regression (X3|X1,X2)
  3. Hitung SS for Residual
  4. Hitung mean SS for Regression (X3|X1,X2)
  5. Hitung mean SS for Residual
  6. Hitung nilai F parsial
  7. Hitung nilai r2
Buktikan penambahan X3 berperan dalam prediksi Y

ANOVAb
Model
Sum of Squares
df
Mean Square
F
Sig.
1
Regression
601.667
1
601.667
.371
.547a
Residual
48697.302
30
1623.243
Total
49298.969
31
a. Predictors: (Constant), indeks massa tubuh
b. Dependent Variable: trigliserida
Coefficientsa
Model
Unstandardized Coefficients
Standardized Coefficients
t
Sig.
B
Std. Error
Beta
1
(Constant)
167.677
46.066
3.640
.001
indeks massa tubuh
-.792
1.300
-.110
-.609
.547
a. Dependent Variable: trigliserida
ESTIMASI MODEL 2 : TRIG = 149.943 - 0.177 UMUR
ANOVAb
Model
Sum of Squares
Df
Mean Square
F
Sig.
1
Regression
212.189
1
212.189
.130
.721a
Residual
49086.780
30
1636.226
Total
49298.969
31
a. Predictors: (Constant), umur
b. Dependent Variable: trigliserida
Coefficientsa
Model
Unstandardized Coefficients
Standardized Coefficients
t
Sig.
B
Std. Error
Beta
1
(Constant)
149.943
28.605
5.242
.000
umur
-.177
.492
-.066
-.360
.721
a. Dependent Variable: trigliserida
ESTIMASI MODEL 3 : TRIG = 142.230 + 0.000 UMUR KUADRAT
ANOVAb
Model
Sum of Squares
df
Mean Square
F
Sig.
1
Regression
85.385
1
85.385
.052
.821a
Residual
49213.584
30
1640.453
Total
49298.969
31
a. Predictors: (Constant), umur kuadrat
b. Dependent Variable: trigliserida
Coefficientsa
Model
Unstandardized Coefficients
Standardized Coefficients
t
Sig.
B
Std. Error
Beta
1
(Constant)
142.230
12.226
11.634
.000
umur kuadrat
.000
.003
-.042
-.228
.821
a. Dependent Variable: trigliserida
ESTIMASI MODEL 4 : 167.688 - 0.784 IMT - 0.005 UMUR
ANOVAb
Model
Sum of Squares
df
Mean Square
F
Sig.
1
Regression
601.777
2
300.889
.179
.837a
Residual
48697.191
29
1679.213
Total
49298.969
31
a. Predictors: (Constant), umur, indeks massa tubuh
b. Dependent Variable: trigliserida
Coefficientsa
Model
Unstandardized Coefficients
Standardized Coefficients
t
Sig.
B
Std. Error
Beta
1
(Constant)
167.688
46.872
3.578
.001
indeks massa tubuh
-.784
1.628
-.109
-.482
.634
Umur
-.005
.613
-.002
-.008
.994
a. Dependent Variable: trigliserida
ESTIMASI MODEL 5 : 168.623 - 0.841 IMT + 0.000 UMUR KUADRAT
ANOVAb
Model
Sum of Squares
df
Mean Square
F
Sig.
1
Regression
609.613
2
304.806
.182
.835a
Residual
48689.356
29
1678.943
Total
49298.969
31
a. Predictors: (Constant), umur kuadrat, indeks massa tubuh
b. Dependent Variable: trigliserida
Coefficientsa
Model
Unstandardized Coefficients
Standardized Coefficients
t
Sig.
B
Std. Error
Beta
1
(Constant)
168.623
48.827
3.453
.002
indeks massa tubuh
-.841
1.505
-.117
-.559
.581
umur kuadrat
.000
.003
.014
.069
.946
a. Dependent Variable: trigliserida
ESTIMASI MODEL 6 : 214.510 - 0.107 IMT - 1.886 UMUR + 0.010 UMUR KUADRAT
ANOVAb
Model
Sum of Squares
df
Mean Square
F
Sig.
1
Regression
1002.559
3
334.186
.194
.900a
Residual
48296.409
28
1724.872
Total
49298.969
31
a. Predictors: (Constant), umur kuadrat, indeks massa tubuh, umur
b. Dependent Variable: trigliserida
Coefficientsa
Model
Unstandardized Coefficients
Standardized Coefficients
t
Sig.
B
Std. Error
Beta
1
(Constant)
214.510
108.129
1.984
.057
indeks massa tubuh
-.107
2.166
-.015
-.050
.961
Umur
-1.886
3.951
-.699
-.477
.637
umur kuadrat
.010
.022
.653
.482
.634
a. Dependent Variable: trigliserida
Kita lakukan uji parsial F seperti berikut (berdasarkan hasil-hasil yang sudah kita lakukan diatas)
ANOVA Tabel untuk TRIG dengan IMT dan UM , UMSQ
Sumber
Df
SS
MS
F
r2
X1
1
601.667
601.667
0.34881
0.900
Regresi X2│X1
1
1.00018
1.00018
0.00058
X3│X1, X2
1
1.66600
1.66600
0.00966
Residual
28
48296.409
1724.872

Total
31
49298.969


Nilai F untuk penambahan independent variabel X3 = 0.00966 <  F 4.02  ini berarti hipotesa H0 : β3 = 0 diterima atau gagal ditolak artinya penambahan third order ( X 3) tidak secara bermakna dapat memprediksi Y.
Kita bersimpulan bahwa :
a.       Penambahan “ second order” sesuai (fit)  dengan nilai r2 = 0.021
b.      Penambahan nilai rmenjadi 0.900 pada “ thind order” hanya sebesar 0879 adalah kecil
c.       Kurva yang ada cukup diterangkan dengan “second order”