Mlr Tutorial Mr2 Spss
-
Upload
marusyasmokova -
Category
Documents
-
view
262 -
download
0
Transcript of Mlr Tutorial Mr2 Spss
-
7/21/2019 Mlr Tutorial Mr2 Spss
1/51
SPSS
- ( ) . -
:
, .. - ;
, .. ;
, .. , ;
- ( );
- ( );
, .
Philips 16 Metro
Cash-and-Carry. - , - , - .
:
, - -, , .
. - -, -.
, - .
- , , ,
-. 30 ./, -
. - , 2: -
1
-
7/21/2019 Mlr Tutorial Mr2 Spss
2/51
SPSS
- 120000 .
( - ),
Metro. , -
. - - .
, , - .
.
1.
PB
P
SF
S
PBPSFfS
= ),,(
bbbb
PBbPbSFbbS
+++=
3210
3210
,,,
, : AnalyzeRegressionLinear
1 , -
, , - -. Chart Builder SPSS (Graphs -> Chart Build-er(Scatter/DotSimple Scatter)).
. - , 2: -
2
-
7/21/2019 Mlr Tutorial Mr2 Spss
3/51
SPSS
Statistics : -, , - , - , , . . Sta-tistics :
Estimates , - , , t- - p-value.
Model Fit -: , - , ANOVA , .
Part and Partial Correlations (Ze-ro-order), (Part; Semipartial) / (Partial) - .
Collinearity d iagnostics , - .
( , , -- ).
. - , 2: -
3
-
7/21/2019 Mlr Tutorial Mr2 Spss
4/51
SPSS
Plots , , -
. - . - , , - .
Save : (1) - - ; (2) , -, , -; (3)
( , - ()); (4) , 2.
2 (3) (4) , .- (outliers) , ( -). - (. 1. . -). . , , -
2. ( leverage) , .
. - , 2: -
4
-
7/21/2019 Mlr Tutorial Mr2 Spss
5/51
SPSS
Enter ( , , -), SPSS 3.
. , - - . - 0 ( ) 1 ( ). , , (2k+2)/n, , n
( (2.3+2)/16 = 0,5). (influential) , - . - , -. - , - -. 4/n ( 4/16=0,25). -, , dfbeta (, - , .. )., dfbeta 2/sqrt(n), (
5,04/216/2 ==
).3 - , - . Syntax_outlier_case.sps.
. - , 2: -
5
-
7/21/2019 Mlr Tutorial Mr2 Spss
6/51
SPSS
-. , , :
- (R = 0,959)
.
- (R2 = 0,919). , 91,9 % , - . 9,1 % .
Model Summary(b)
Model R R SquareAdjustedR Square
Std. Error ofthe Estimate
1 .959(a) .919 .899 4546.245
a Predictors: (Constant), , -, b Dependent Variable:
. F-. - , ,
. , Sig.=0,000 < 0,05, , . , .
ANOVAb
2808359494.7 3 936119831.6 45.292 .000a
248020088.34 12 20668340.70
3056379583.0 15
Regression
ResidualTotal
Model
1
Sum of
Squares df Mean Square F Sig.
Predictors: (Constant), , ,
a.
Dependent Variable: b.
: ; - -. , , :
. - , 2: -
6
-
7/21/2019 Mlr Tutorial Mr2 Spss
7/51
SPSS
(b)4 , p-value t- - 0,05. , , .
(b) , ( , - ).
- (be-ta5,6 = -0,725), - (beta = 0,665) (beta = 0,242). , - .
-
(VIF) , - ( VIF -, ). , VIF>107.
Coefficientsa
210159.4 23729.909 8.856 .000
6723.478 840.997 .665 7.995 .000 .542 .918 .657 .976 1.024
-3832.503 444.013 -.725 -8.632 .000 -.668 -.928 -.710 .958 1.044
.069 .024 .242 2.903 .013 .303 .642 .239 .972 1.029
(Constant)
Model
1
B Std . Er ror
Unstandardized
Coefficients
Beta
Standardized
Coefficients
t Sig. Zero-order Partial Part
Correlations
Tolerance VIF
Collinearity Statistics
Dependent Variable: a.
. , (). -, -, . - , - ( , -, -, , ).
4 b , -.5 beta . - beta . .6 beta - - . - .
7 , VIF>2, VIF>3, VIF>4, VIF>5. - 10.
. - , 2: -
7
-
7/21/2019 Mlr Tutorial Mr2 Spss
8/51
SPSS
- .
, 8:1. .
(RES2) - (RES_1).
2. (SF2, P2, PB2).
8 , :http://www.spsstools.net/Syntax/RegressionRepeatedMeasure/WhiteTestStatisticsAndSignificance.txt.
. - , 2: -
8
http://www.spsstools.net/Syntax/RegressionRepeatedMeasure/WhiteTestStatisticsAndSignificance.txthttp://www.spsstools.net/Syntax/RegressionRepeatedMeasure/WhiteTestStatisticsAndSignificance.txthttp://www.spsstools.net/Syntax/RegressionRepeatedMeasure/WhiteTestStatisticsAndSignificance.txt -
7/21/2019 Mlr Tutorial Mr2 Spss
9/51
SPSS
3. () - . m -
:2
)1( =
mmcp
, , 3. SFxP, SFxPB, PxPB.
4. , , - (RES2), : (SalesForce, Price, PromoBudget);
. - , 2: -
9
-
7/21/2019 Mlr Tutorial Mr2 Spss
10/51
SPSS
(SF2, P2, PB2)9 - (SFxP, SFxPB, PxPB).
Model Summary
Model R R SquareAdjustedR Square
Std. Error of theEstimate
1 .846(a) .716 .290 12051207.228
a Predictors: (Constant), PxPB, , , SFxPB,
SF2, PB2, , SFxP, P2
, , .
WH
P
NRtestWhite
critical
Pd
RES
f
0
2
)9;05,0(2
)2(2
919,16
45842,118257161513741,0.16
=
, , .. . , , , . , , . - ,
. - , 2: -
11
-
7/21/2019 Mlr Tutorial Mr2 Spss
12/51
SPSS
10, (stem-and-leaf) .
, ,
. , (16 11
), -12. - - (0,191> 0,05),
10 450- .11 , -, , -. - -,
]4
)3([
6
22
)2(
+=
=
KurtosisSkewness
NtestBeraJarque df
.
, - -
2.12 Explore (Analyze -> Descriptive Statis-tics -> Explore ).
. - , 2: -
12
-
7/21/2019 Mlr Tutorial Mr2 Spss
13/51
SPSS
. -, .
Tests of Normality
.163 16 .200* .923 16 .191Unstandardized Res idual
Statistic df Sig. Statistic df Sig.
Kolmogorov-Smirnova
Shapiro-Wilk
This is a lower bound of the true s ignificance.*.
Lilliefors Significance Correctiona.
. - , 2: -
13
-
7/21/2019 Mlr Tutorial Mr2 Spss
14/51
SPSS
-
, : , . :
PBPSFS 660571.0,069193962487.3832,50331-5647.6723,477517074210159,443 ++=
- (-, ). - . -
(.. - ) -. .
6605710,06919396
12487-3832,5033
56476723,47751
3
2
1
==
==
==
bPB
S
bP
S
bSF
S
, - - ( !)13.
13 PS/ ,
SFS/ , PBS/ .
. - , 2: -
14
-
7/21/2019 Mlr Tutorial Mr2 Spss
15/51
SPSS
SPB
SPB
PBS
S
P
S
P
P
S
S
SF
S
SF
SF
S
PBS
PS
SFS
.b.
.b.
.b.
3/
2/
1/
=
=
=
=
=
=
SPSS, (SF_elasticity, P_elasticity, PB_elasticity).
, .
16;
1/
/
1/
/
1/
/
==
=
=
=
=
=
=
NN
N
N
N
N
iPBSi
PBS
N
iPSi
PS
N
iSFSi
SFS
. - , 2: -
15
-
7/21/2019 Mlr Tutorial Mr2 Spss
16/51
SPSS
Statistics
16 16 16
0 0 0
.4480 -2.2825 .2617
Valid
Missing
N
Mean
SF_elasticity P_elas ticity PB_elasticity
0,45, (-2,28), 0,26. ,
1 %, 2,28% ( !).
.
, , , - . , , -.
. - , 2: -
16
-
7/21/2019 Mlr Tutorial Mr2 Spss
17/51
SPSS
PBbPbSFbbS
PBPSFbS
PBPSFbS
PBPSFbS
bbb
bbb
bbb
lnlnlnlnln
lnlnlnlnln
)ln(ln
3210
0
0
0
321
321
321
+++=
+++=
=
=
, - .
1
30
1
20
1
10
321
321
321
=
=
=
bbb
bbb
bbb
PBPSFbb
PB
S
PBPSFbbP
S
PBPSFbbSF
S
, - , - ..., , .
3
0
1
30/
2
0
120/
1
0
1
10/
321
321
321
321
321
321
.
.
.
bPBPSFb
PBPBPSFbb
S
PB
PB
S
bPBPSFb
PPBPSFbbSP
PS
bPBPSFb
SFPBPSFbb
S
SF
SF
S
bbb
bbb
PBS
bbbbbb
PS
bbb
bbb
SFS
==
=
==
=
==
=
, - . , - (lnS, lnSF, lnP, lnPB).
. - , 2: -
17
-
7/21/2019 Mlr Tutorial Mr2 Spss
18/51
SPSS
SPSS .
.
Model Summary b
.963a .928 .909 .05198
Model
1
R R Square
Adjusted
R Square
Std. Error of
the Estimate
Predictors: (Constant), lnPB, lnSF, lnPa.
Dependent Variable: lnSb.
, , , : ,
(92,8 %) - .
, -( -!).
. - , 2: -
18
-
7/21/2019 Mlr Tutorial Mr2 Spss
19/51
SPSS
, F- - (=0,05).
ANOVAb
.415 3 .138 51.231 .000a
.032 12 .003
.448 15
Regression
Residual
Total
Model
1
Sum of
Squares df Mean Square F Sig.
Predictors: (Constant), lnPB, lnSF, lnPa.
Dependent Variable: lnSb.
, . , - :
( ), ( ) - ( ). - -.
Coefficientsa
16.981 1.493 11.372 .000
.400 .047 .674 8.565 .000 .547 .927 .665 .974 1.026
-2.339 .248 -.749 -9.440 .000 -.669 -.939 -.733 .959 1.042
.217 .082 .207 2.647 .021 .279 .607 .206 .983 1.017
(Constant)
lnSF
lnP
lnPB
Model
1
B Std . Err or
Unstandardized
Coefficients
Beta
Standardized
Coefficients
t Sig. Zero-order Partial Part
Correlations
Tolerance VIF
Collinearity Statistics
Dependent Variable: lnSa.
, , p-value - 0,05 , - .
Model Summary
. - , 2: -
19
-
7/21/2019 Mlr Tutorial Mr2 Spss
20/51
SPSS
Model R R SquareAdjustedR Square
Std. Error ofthe Estimate
1 .713(a) .508 .262 .00240
a Predictors: (Constant), lnPxlnPB, lnSF2, lnPB2, lnSFxlnPB, lnSFxlnP
valuep
NRtestWhite
dfWh
RES
0
)9;1293,8(
)2_2_(2
05,05212,0
5212,0
129349491,8318370,50808434.16
>
=
===
==
- 0,05 , - .
. - , 2: -
20
-
7/21/2019 Mlr Tutorial Mr2 Spss
21/51
SPSS
Tests of Normality
.137 16 .200* .968 16 .803Unstandardized Residual
Statistic df Sig. Statistic df Sig.
Kolmogorov-Smirnova
Shapiro-Wilk
This is a lower bound of the true s ignificance.*.
Lilliefors Significance Correctiona.
- , - . , - ( - ); ( , - ); ( -, , ).
. - , 2: -
21
-
7/21/2019 Mlr Tutorial Mr2 Spss
22/51
SPSS
. b014. :
o
A
o beAb ==ln
SPSS .
- :
548270,2168934961831-2,3394799227330,39951578PB.P.SF82352.23692308,1S =
, :
14 b0, -.
. - , 2: -
22
-
7/21/2019 Mlr Tutorial Mr2 Spss
23/51
SPSS
548270,21689349
61831-2,3394799
227330,39951578
/
/
/
=
=
=
PBS
PS
SFS
- , .
c
S
PBSFSKScKK
PSU
K
U
G
KUG
v
f
vf
+=
+=
=
=
..
.
max
- . - .
0..
0..
0..
max],),,,([),,(.
=
=
=
=
=
+=
=
PB
K
PB
S
S
K
PB
SP
PB
G
SF
K
SF
S
S
K
SF
SP
SF
G
P
S
S
K
P
SPS
P
G
PBSFPBPSFSKPBPSFSPG
PB
K
PB
S
S
KP
SF
K
SF
S
S
KP
P
S
S
K
P
S
PS
=
=
=
+
].[
].[
..
. - , 2: -
23
-
7/21/2019 Mlr Tutorial Mr2 Spss
24/51
SPSS
=
++=+=
+
=
=+
=+
=
+
=
+
v
vvf
PS
PS
G
PSPS
PSPS
cS
K
ScPBSFSScKK
LINSK
S
KP
S
KP
SKPP
S
P
P
S
S
K
S
P
P
SP
S
PS
S
P
P
S
S
K
P
SPS
opt
...
..,)(
1
..
.)1.(
..
.....
./.
/
/
//
//
, - ( - -!15).
2
2vG
b1
b.cP
MULTS
opt+
=
, . .
S
SF
SF
KcP
S
KP
S
SF
SF
K
S
SF
SF
S
S
KP
S
SF
SF
K
SF
S
S
KP
SFSvSFS .].[].[
..].[
./].[
//
==
=
=
15 , .. 1/
-
7/21/2019 Mlr Tutorial Mr2 Spss
25/51
SPSS
SPB
PBKcP
SKP
S
PB
PB
K
S
PB
PB
S
S
KP
S
PB
PB
K
PB
S
S
KP
PBSvPBS .].[].[
..].[
./].[
//
==
=
=
PB
PB.KSF
SF.K
S
PB.
PB
KS
SF.
SF
K
].cP[
].cP[
S
PB.
PB
K].cP[
S
SF.
SF
K].cP[
PB/S
SF/S
PB/Sv
SF/Sv
PB/Sv
SF/Sv
=
=
=
=
PB
SF.S
PB
PB.KSF
SF.K
1PB
K
SSF
K
S.cPBSF.SS.cKK
..,LIN)S(K
PB/S
SF/S
vvf
=
=
=
=
++=+=
- ( - -. - : - ).
. - , 2: -
25
-
7/21/2019 Mlr Tutorial Mr2 Spss
26/51
SPSS
3
1
b
b
omoBudgetPr
onBudgetDistributi
MULTS
=
, , 3 ( ) , Solver.
1.
)PB.P.SF82352.23692308,1.(30PBSF.120000
/.30c
/.120000S
PB.P.SF82352.23692308,1S
548270,2168934918312,33947996-227330,39951578
v
548270,2168934961831-2,3394799227330,39951578
++=
=
=
=
0..
0..
0..
max],),,,([),,(.
max
=
=
=
=
=
+=
=
=
PB
K
PB
S
S
K
PB
S
PPB
G
SF
K
SF
S
S
K
SF
SP
SF
G
P
S
S
K
P
SPS
P
G
PBSFPBPSFSKPBPSFSPG
KUG
01)PB.P.SF7.689349548282352.0,2123692308,1.(30
)PB.P.SF7.689349548282352.0,2123692308,1.(PPB
G
0120000)PB.P.SF3.951578227382352.0,3923692308,1.(30
)PB.P.SF3.951578227382352.0,3923692308,1.(PSF
G
0)PB.P.SF2.2308,1823561831.2369-2,3394799.(30
)PB.P.SF2.2308,1823561831.2369-2,3394799.(P
PB.P.SF82352.23692308,1P
G
1-548270,2168934918312,33947996-227330,39951578
1-548270,2168934918312,33947996-227330,39951578
548270,2168934918312,33947996-1-227330,39951578
548270,2168934918312,33947996-1-227330,39951578
548270,216893491-18312,33947996-227330,39951578
548270,216893491-18312,33947996-227330,39951578
548270,2168934918312,33947996-227330,39951578
=
=
=
=
=
+
+=
- - :
. - , 2: -
26
-
7/21/2019 Mlr Tutorial Mr2 Spss
27/51
SPSS
227330,39951578SF54827.0,21689349.120000PB
548270,21689349
227330,39951578
PB
SF.120000
/.39675162,5218311,33947996-
18312,33947996-.30
118312,33947996-
18312,33947996-.30P
max
max
G
G
=
=
==+
=
=
=
=
+
01)227330,39951578
SF54827.0,21689349.120000.(P
.SF954827..0,216893423692308,2.30)
227330,39951578
SF54827.0,21689349.120000(
.P.SF7.689349548282352.0,2123692308,1
01)PB.P.SF7.689349548282352.0,2123692308,1.(30
)PB.P.SF7.689349548282352.0,2123692308,1(P
227330,39951578
SF54827.0,21689349.120000PB
1-548270,2168934918312,33947996-
227330,399515781-548270,21689349
118312,33947996-227330,39951578
1-548270,2168934918312,33947996-227330,39951578
1-548270,2168934918312,33947996-227330,39951578
Gmax
=
01)
227330,39951578
SF54827.0,21689349.120000(
.39675162,52.SF7.689349548282352.0,2123692308,1.30
)227330,39951578
SF54827.0,21689349.120000(
.39675162,52.SF7.689349548282352.0,2123692308,1
451730,78310650-
18312,33947996-227330,39951578
451730,78310650-
61831-1,3394799227330,39951578
=
01
SF5996952,05135754
2326670003485377,0.2559291320000949996,0.SF.131711,154161226
SF5996952,05135754
2326670003485377,0.85823450049776717,0.SF77237.5138707,53
451730,78310650-227330,39951578
451730,78310650-227330,39951578
93410256022559,5850515383078894,0SF
850515383078894,0SF1SF.85378576729405,1
01
SF.SF.49784883156795,2SF.SF013515.4,34598862
22440,38359072-
22440,38359072-
22440,38359072-
045173-0,7831065227330,39951578045173-0,7831065227330,39951578
==
=
=
=
. - , 2: -
27
-
7/21/2019 Mlr Tutorial Mr2 Spss
28/51
SPSS
.467258476,327402227330,39951578
548270,21689349.270719209,603072PB
548270,21689349
227330,39951578
PB
270719209,603072
PB
SF.S
.270719209,60307293410256022559,5.120000SF.S
93410256022559,5850515383078894,0SF
850515383078894,0SF
1SF.85378576729405,1
01
SF.SF.49784883156795,2SF.SF013515.4,34598862
max
max
max
G
PB/S
SF/S
G
22440,38359072-G
22440,38359072-
22440,38359072-
045173-0,7831065227330,39951578045173-0,7831065227330,39951578
==
=
=
==
==
=
=
=
.
.27,579033.26515462,57903346039693,295243072555155,3531463G
.46,2952430
.46039693,29524305240806416,67398.30467258476,32740293410256022559,5.120000
.73,3531463.72555155,35314635240806416,67398.39675162,52S.PU
673995240806416,67398467258476,327402
.39675162,52.93410256022559,582352.23692308,1S
max
548270,21689349
61831-2,3394799227330,39951578
Gmax
==
=++=
===
=
=
2. Solver
Solver : - ( - -). !16
2.1. -
16 Solver .
. - , 2: -
28
-
7/21/2019 Mlr Tutorial Mr2 Spss
29/51
SPSS
. - , 2: -
29
-
7/21/2019 Mlr Tutorial Mr2 Spss
30/51
SPSS
2.2. - .
. - , 2: -
30
-
7/21/2019 Mlr Tutorial Mr2 Spss
31/51
SPSS
. - , 2: -
31
-
7/21/2019 Mlr Tutorial Mr2 Spss
32/51
SPSS
.
Metro. .
DM
PB
P
SF
S
DMPBPSFfS
= ),,,(
bbbbb
DMbPBbPbSFbbS
++++=
43210
43210
,,,,
....
( ) , Enter.
. - , 2: -
32
-
7/21/2019 Mlr Tutorial Mr2 Spss
33/51
SPSS
.
Model Summaryb
,965a ,931 ,906 4371,811
Model
1
R R Square
Adjust ed
R Square
Std. Error of
the Estimate
Predictors: (Constant), ,
, ,
a.
Dependent Variable: b.
-. , - ( 0,906, - - (0,899)) - ( !) (R2=0,909). , , (
F 0,000 < 0,05).
ANOV Ab
2846139532.978 4 711534883.2 37.228 .000a
210240050.022 11 19112731.82
3056379583.000 15
Regression
Residual
Total
Model
1
Sum of Squares df Mean Square F Sig.
Predictors: (Constant), , , ,
a.
Dependent Variable: b.
- , , -
. - , 2: -
33
-
7/21/2019 Mlr Tutorial Mr2 Spss
34/51
SPSS
. , , , , (-
!) ( - !), - . , - ( , ) . (. !), . - . - ( -
VIF 53, 10) ( (r= -0,99)).
, - , .. - ( , .. ) , . , . - . - , -
. - , 2: -
34
-
7/21/2019 Mlr Tutorial Mr2 Spss
35/51
SPSS
()(), () ( , , , ). . .
( , - - - , ) - . , - . SPSS - , SPSS (Ridge regression.sps). , - .
17:
1. Syntax_ridge_case.sps. (Case_ridge.sav)!18
2. . , () Ridge regression.sps.
INCLUDE 'C:\Program Files\SPSS Evaluation\Ridge regression.sps '.
17 , , . , - , SPSS. Edit -> Options Viewer 133 -. SPSS 16.
18 , , - SPSS, - -, Case_ridge.sav. Case_Multiple_regression.sav, , , -
, . , - (sales, sforce,price, pbudget, dmail).
. - , 2: -
35
-
7/21/2019 Mlr Tutorial Mr2 Spss
36/51
SPSS
3. .
RIDGEREG DEP=sales /ENTER = sforce price pbudget dmail/.
SPSS , - - . .. . - . -
, ( ), -1920. =0,05., , - , - =1/F, F F , . =1/37.228319318166086 = 0.02686127169625.
19 , NCSS, -, . , VIF.20 , ,
( -).
. - , 2: -
36
-
7/21/2019 Mlr Tutorial Mr2 Spss
37/51
SPSS
4. (Case_ridge.sav) , .
RIDGEREG DEP=sales /ENTER = sforce price pbudget dmail/k=.05.
SPSS .
. - , 2: -
37
-
7/21/2019 Mlr Tutorial Mr2 Spss
38/51
SPSS
V.
- , , . - n , n-1 - () . (), . - - , . .
(D1) (D2). D1 -, , 1. - ( ) 0. . - !
. - , 2: -
38
-
7/21/2019 Mlr Tutorial Mr2 Spss
39/51
SPSS
. , . - - (R2 change). .. (-) . -
. - , ( Enter) (Remove) . , - ( 1 , - , , ; 2 1, ( )) . , , ( ) -. Statistics, Plots, Save
. - , 2: -
39
-
7/21/2019 Mlr Tutorial Mr2 Spss
40/51
SPSS
, R squared change.
. - , 2: -
40
-
7/21/2019 Mlr Tutorial Mr2 Spss
41/51
SPSS
- .
Model Summaryc
,959a ,919 ,899 4546,245 ,919 45,292 3 12 ,000
,965b ,932 ,898 4565,206 ,013 ,950 2 10 ,419
Model1
2
R R Square
Adjust ed
R Square
Std. E rror of
the Estimate
R Square
Change F Change df1 df2 Si g. F Change
Change Statistics
Predictors: (Constant), , , a.
Predictors: (Constant), , , , dummy_medium firms, dummy_
little firms
b.
Dependent Variable: c.
ANOVAc
2846139532,978 4 711534883,2 37,228 ,000a
210240050,022 11 19112731,82
3056379583,000 15
2881830408,300 6 480305068,0 24,765 ,000b
174549174,700 9 19394352,74
3056379583,000 15
Regression
Residual
Total
Regression
Residual
Total
Model
1
2
Sum of Squares df Mean Square F Sig.
Predictors: (Constant), , , ,
a.
Predictors: (Constant), , , ,
, dummy_medium firms, dummy_little firms
b.
Dependent Variable: c.
Coefficients a
210159,4 23729,909 8,856 ,000
6723,478 840,997 ,665 7,995 ,000 ,542 ,918 ,657 ,976 1,024
-3832,503 444,013 -,725 -8,632 ,000 -,668 -,928 -,710 ,958 1,044
,069 ,024 ,242 2,903 ,013 ,303 ,642 ,239 ,972 1,029
218059,3 24819,085 8,786 ,000
6061,229 1036,479 ,600 5,848 ,000 ,542 ,880 ,483 ,648 1,543
-3924,542 509,403 -,743 -7,704 ,000 -,668 -,925 -,636 ,734 1,363
,070 ,026 ,245 2,663 ,024 ,303 ,644 ,220 ,808 1,238
-2939,397 3945,131 -,092 -,745 ,473 -,466 -,229 -,062 ,446 2,240
1700,677 3331,032 ,061 ,511 ,621 -,111 ,159 ,042 ,477 2,096
(Constant)
(Constant)
dummy_little firms
dummy_medium firms
Model
1
2
B Std . Er ror
UnstandardizedCoefficients
Beta
StandardizedCoefficients
t Sig. Zero-order Partial Part
Correlations
Tolerance VIF
Collinearity Statistics
Dependent Variable: a.
Excluded Variablesb
-,129a -1,326 ,212 -,371 ,674 1,483 ,663
,113a 1,184 ,261 ,336 ,721 1,388 ,721
dummy_little firms
dummy_medium firms
Model
1
Beta In t Sig.
Partial
Correlation Tolerance VIF
Minimum
Tolerance
Collinearity Statistics
Predictors in the Model: (Constant), , , a.
Dependent Variable: b.
-
t -, (-
. - , 2: -
41
-
7/21/2019 Mlr Tutorial Mr2 Spss
42/51
SPSS
) F , . p-value F (F = [(R22- R12)/(k2- k1)]/[(1-R22)/(n - k2-1)], 1 , 2 ; ). ,
( ) . p-value = 0,419 > 0,05, , .. - - . - -, ( 1,3 %). :
267693030817001396922512939
10420699054105054243470139242291677096061281895218059
.D,.D,-
.PB-,.P,.SF-,,S
+
++=
- . . , - ( !), -, . b4 = -2939,4 , 2939,4 - ( -!), b5 = 1700,7 1700,7 . , .
PBPSFS
PBPSFS
PBPSFS
051042.0,069905414701.3924,54243-7709.6061,22916895218059,2810)D20;(D1
051042.0,069905414701.3924,54243-7709.6061,22916825308219759,958
1)D20;(D1
051042.0,069905414701.3924,54243-7709.6061,22916977249215119,884
0)D21;(D1
++=
==
++=
==
++=
==
, - , , . - , . (.. -), . -
, - , .
. - , 2: -
42
-
7/21/2019 Mlr Tutorial Mr2 Spss
43/51
SPSS
..,-M
-K
-N
ANOVA!-SquaresofSumResidual
SquaresofSumResidual
SquaresofSumResidualSquaresofSumResidual
SquaresofSumResidual
M
SquaresofSumResidualSquaresofSumResidual
modelnedunconstrai
modelnedunconstraimodeldconstraine
modelnedunconstrai
modelnedunconstraimodeldconstraine
>
=
=
=
M
KNKN
FtestChow
.
:
:)(
0371772,02
516.
7004174549174,
7004174549174,-0221210240050,)(
0308.D21700,67693251.D12939,39692-
-051042.0,069905414701.3924,54243-7709.6061,22916895218059,281
model)ined(unconstra,
0,069.3832,503.-6723,478.210159,4
model)ed(constrain
=
=
+
++=
++=
FtestChow
PBPSFS
PBPSFS
0)bb:(H
05,09636,0)11;2;0371772,0(
540
021
==
>==== HdfdfChowvaluep
, ,
.
V.
- , , . - . - , - - , . - , ,
, ,. - . - . . , . : ( SPSS Forward), ( Backward) - ( Stepwise). . , - . , , F ( -
. - , 2: -
43
-
7/21/2019 Mlr Tutorial Mr2 Spss
44/51
SPSS
(FIN) (PIN)). F > FIN ( FIN=3,84, - Analyze -> Regression -> Linear -> Op-tions), PIN ( PIN=0,05).
, . , - , - . - R-squared change Statistics
. - .
Model Summary
,668a ,447 ,407 10991,826 ,447 11,297 1 14 ,005
,928b ,862 ,841 5698,479 ,415 39,089 1 13 ,000
,959c ,919 ,899 4546,245 ,057 8,425 1 12 ,013
Model1
2
3
R R Square
Adjusted
R Square
Std. Error of
the Estimate
R Square
Change F Change df1 df2 Sig. F Change
Change Statistics
Predictors: (Constant), a.
Predictors: (Constant), , b.
Predictors: (Constant), , , c.
, , (.. , ) - - ( ),
41,5 %. -
. - , 2: -
44
-
7/21/2019 Mlr Tutorial Mr2 Spss
45/51
SPSS
, p-value F - - 0,05. - , ( 2) 5,7 %.
ANOVAd
1364896388,053 1 1364896388 11,297 ,005a
1691483194,947 14 120820228,2
3056379583,000 15
2634234994,787 2 1317117497 40,561 ,000b
422144588,213 13 32472660,63
3056379583,000 15
2808359494,659 3 936119831,6 45,292 ,000c
248020088,341 12 20668340,70
3056379583,000 15
Regression
Residual
Total
Regression
Residual
Total
Regression
Residual
Total
Model
1
2
3
Sum of Squares df Mean Square F Sig.
Predictors: (Constant), a.
Predictors: (Constant), , b.
Predictors: (Constant), , , c.
Dependent Variable: d.
Coefficientsa
254548,8 50837,204 5,007 ,000
-3531,561 1050,719 -,668 -3,361 ,005 -,668 -,668 -,668 1,000 1,000
241732,4 26435,070 9,144 ,000
-4023,777 550,383 -,761 -7,311 ,000 -,668 -,897 -,754 ,980 1,021
6579,154 1052,302 ,651 6,252 ,000 ,542 ,866 ,644 ,980 1,021
210159,4 23729,909 8,856 ,000
-3832,503 444,013 -,725 -8,632 ,000 -,668 -,928 -,710 ,958 1,044
6723,478 840,997 ,665 7,995 ,000 ,542 ,918 ,657 ,976 1,024
,069 ,024 ,242 2,903 ,013 ,303 ,642 ,239 ,972 1,029
(Constant)
(Constant)
(Constant)
Model
1
2
3
B Std . Er ror
Unstandardized
Coefficients
Beta
Standardized
Coefficients
t Sig. Zero-order Partial Part
Correlations
Tolerance VIF
Collinearity Statistics
Dependent Variable: a.
- . .
Excluded Variablesd
,651a
6,252 ,000 ,866 ,980 1,021 ,980
,203a 1,007 ,332 ,269 ,975 1,026 ,975
,648a 6,224 ,000 ,865 ,986 1,015 ,986
,242b 2,903 ,013 ,642 ,972 1,029 ,958
,290b ,389 ,704 ,112 ,020 48,981 ,020
,809c 1,406 ,187 ,390 ,019 52,962 ,019
Model
1
2
3
Beta In t Sig.
Partial
Correlation Tolerance VIF
Minimum
Tolerance
Collinearity Statisti cs
Predictors in the Model: (Constant), a.
Predictors in the Model: (Constant), , b.
Predictors in the Model: (Constant), , , c.
Dependent Variable: d.
. - , 2: -
45
-
7/21/2019 Mlr Tutorial Mr2 Spss
46/51
SPSS
-. , . , - . -, , F
( FOUT=2,71, POUT=0,10, !).- - , - .
Model Summary
,965a ,931 ,906 4371,811 ,931 37,228 4 11 ,000
,965b ,931 ,914 4196,281 ,000 ,056 1 11 ,818
Model
1
2
R R Square
Adjusted
R Square
Std. Error of
the Estimate
R Square
Change F Change df1 df2 Sig. F Change
Change Statistics
Predictors: (Constant), , , , a.
Predictors: (Constant), , , b.
ANOVAc
2846139533,0 4 711534883,2 37,228 ,000a
210240050,022 11 19112731,82
3056379583,0 15
2845074244,3 3 948358081,4 53,857 ,000b
211305338,736 12 17608778,233056379583,0 15
Regression
Residual
Total
Regression
ResidualTotal
Model
1
2
Sum of
Squares df Mean Square F Sig.
Predictors: (Constant), , , ,
a.
Predictors: (Constant), , , b.
Dependent Variable: c.
Coefficientsa
203009,3 23379,266 8,683 ,000
-1372,882 5815,151 -,136 -,236 ,818
-3711,737 435,531 -,702 -8,522 ,000
,078 ,024 ,274 3,288 ,007
7,949 5,654 ,809 1,406 ,187
204126,4 21976,139 9,289 ,000
-3733,676 408,418 -,707 -9,142 ,000
,077 ,022 ,269 3,484 ,005
6,627 ,755 ,675 8,781 ,000
(Constant)
(Constant)
Model
1
2
B St d. E rror
Unstandardized
Coefficients
Beta
Standardized
Coefficients
t Sig.
Dependent Variable: a.
. - , 2: -
46
-
7/21/2019 Mlr Tutorial Mr2 Spss
47/51
SPSS
Ex cluded Variabl esb
-,136a
-,236 ,818 -,071 ,019
Model
2
Beta In t Sig.
Partial
Correlation Tolerance
Collinearity
Statistics
Predictors in the Model: (Constant), , , a.
Dependent Variable: b.
- . () () , . . . - -
.Model Summary
,668a ,447 ,407 10991,826 ,447 11,297 1 14 ,005
,928b ,862 ,841 5698,479 ,415 39,089 1 13 ,000
,959c ,919 ,899 4546,245 ,057 8,425 1 12 ,013
Model
1
2
3
R R Square
Adjusted
R Square
Std. Error o f
the Estimate
R Square
Change F Change df1 df2 Sig. F Change
Change Statistics
Predictors: (Constant), a.
Predictors: (Constant), , b.
Predictors: (Constant), , , c.
ANOVAd
1364896388,1 1 1364896388 11,297 ,005a
1691483194,9 14 120820228,2
3056379583,0 15
2634234994,8 2 1317117497 40,561 ,000b
422144588,21 13 32472660,63
3056379583,0 15
2808359494,7 3 936119831,6 45,292 ,000c
248020088,34 12 20668340,70
3056379583,0 15
Regression
Residual
Total
Regression
Residual
Total
Regression
Residual
Total
Model
1
2
3
Sum of
Squares df Mean Square F Sig.
Predictors: (Constant), a.
Predictors: (Constant), , b.
Predictors: (Constant), , ,
c.
Dependent Variable: d.
. - , 2: -
47
-
7/21/2019 Mlr Tutorial Mr2 Spss
48/51
SPSS
Coefficientsa
254548,8 50837,204 5,007 ,000
-3531,561 1050,719 -,668 -3,361 ,005241732,4 26435,070 9,144 ,000
-4023,777 550,383 -,761 -7,311 ,000
6579,154 1052,302 ,651 6,252 ,000
210159,4 23729,909 8,856 ,000
-3832,503 444,013 -,725 -8,632 ,000
6723,478 840,997 ,665 7,995 ,000
,069 ,024 ,242 2,903 ,013
(Constant)
(Constant)
(Constant)
Model
1
2
3
B Std. Error
Unstandardized
Coefficients
Beta
Standardized
Coefficients
t Sig.
Dependent Variable: a.
Ex cluded Variabl esd
,651a
6,252 ,000 ,866 ,980
,203a 1,007 ,332 ,269 ,975
,648a 6,224 ,000 ,865 ,986
,242b 2,903 ,013 ,642 ,972
,290b ,389 ,704 ,112 ,020
,809c 1,406 ,187 ,390 ,019
Model
1
2
3
Beta In t Sig.
Partial
Correlation Tolerance
Collinearity
Statistics
Predictors in the Model: (Constant), a.
Predictors in the Model: (Constant), , b.
Predictors in the Model: (Const ant), , ,
c.
Dependent Variable: d.
, . - . . - , , . - . SPSS - , , . ( Enter) ( Remove) . , - -.
. - , 2: -
48
-
7/21/2019 Mlr Tutorial Mr2 Spss
49/51
SPSS
. - , 2: -
49
-
7/21/2019 Mlr Tutorial Mr2 Spss
50/51
SPSS
Model Summary
,542a
,294 ,244 12414,764 ,294 5,830 1 14 ,030,928b ,862 ,841 5698,479 ,568 53,449 1 13 ,000
,959c ,919 ,899 4546,245 ,057 8,425 1 12 ,013
Model
12
3
R R Square
Adjusted
R Square
Std. Error of
the Estimate
R Square
Change F Change df1 df2 Sig. F Change
Change Statistics
Predictors: (Constant), a.
Predictors: (Constant), , b.
Predictors: (Constant), , , c.
. - , 2: -
50
-
7/21/2019 Mlr Tutorial Mr2 Spss
51/51
SPSS
ANOV Ad
898610450,157 1 898610450,2 5,830 ,030a
2157769132,8 14 154126366,6
3056379583,0 152634234994,8 2 1317117497 40,561 ,000b
422144588,213 13 32472660,63
3056379583,0 15
2808359494,7 3 936119831,6 45,292 ,000c
248020088,341 12 20668340,70
3056379583,0 15
Regression
Residual
TotalRegression
Residual
Total
Regression
Residual
Total
Model
1
2
3
Sum of
Squares df Mean Square F Sig.
Predictors: (Constant), a.
Predictors: (Constant), , b.
Predictors: (Constant), , ,
c.
Dependent Variable: d.
Coefficients a
53454,950 12997,217 4,113 ,001
5478,706 2268,980 ,542 2,415 ,030 ,542 ,542 ,542 1,000 1,000
241732,4 26435,070 9,144 ,000
6579,154 1052,302 ,651 6,252 ,000 ,542 ,866 ,644 ,980 1,021
-4023,777 550,383 -,761 -7,311 ,000 -,668 -,897 -,754 ,980 1,021
210159,4 23729,909 8,856 ,000
6723,478 840,997 ,665 7,995 ,000 ,542 ,918 ,657 ,976 1,024
-3832,503 444,013 -,725 -8,632 ,000 -,668 -,928 -,710 ,958 1,044
,069 ,024 ,242 2,903 ,013 ,303 ,642 ,239 ,972 1,029
(Constant)
(Constant)
(Constant)
Model
1
2
3
B Std . Er ror
Unstandardized
Coefficients
Beta
Standardized
Coefficients
t Sig. Zero-order Partial Part
Correlations
Tolerance VIF
Collinearity Statistics
Dependent Variable: a.