Psy 524
Ainsworth
Lab #3
Multiple Regression
Copy and paste any results onto this page to hand in.
1. Finding estimates of B using matrix command in SPSS
a. Open SPSS and go to File -> New -> Syntax
b. Type into the window (anything after the # doesn’t need to be typed):
COMMENT Estimating Bs using the Moore-Penrose Pseudo Inverse, assumes IID (does not
account for #dependencies in the Xs).
get file='C:\Temp\social2.sav'.
Comment set above to whatever folder you have the "social2.sav" saved in.
matrix.
get x /variables=ciccomp oocomp.
get y /variables= qdicomp.
compute invx=(inv(t(x)*(x))) * t(x)).
compute b=(invx * y).
print b.
end matrix.
c. Copy and paste the b values below and tell me what they mean (consider first 2
lines in syntax).
.2820362148
.1302770591
They are relationships between each x and y. For a 1 unit
increase in X1, y increases by .28 and as X2 increases by
1, y increases by .13. They are over estimated because the
Moore-Penrose approach is treating them as independent
(orthogonal) when there is a slight dependency. When they
are ran through SPSS the values are .187 and .077 (a little
smaller when controlled for their correlation).
2. Standard regression in ARC (in forclass data n=neuroticism, e=extroversion,
o=openness, a=agreeableness, c=conscientiousness, ego=egotism, sos=sexual
opinion scale and soitot=sexual openness and intimacy)
a. Simple regression
i. Using the forclass.lsp data, plot SOS (H) versus SOI (V), set OLS
= 1. Click on the arrow next to OLS and choose display regression
summary. Look back at the original ARC window and interpret
the results.
LS regression summary for [Plot2]Forclass:V:soitot H:sos
Response = soitot
Coefficient Estimates
Label
Estimate
Std. Error t-value p-value
Constant -1.86162
0.205515
-9.058 0.0000
sos^1 0.0250756
0.00269860
9.292 0.0000
Psy 524
Ainsworth
R Squared:
0.232515
Scale factor:
0.890436
Number of cases:
287
Degrees of freedom:
285
Summary Analysis of Variance Table
Source
df
SS
MS
F p-value
Regression
1 68.4591
68.4591
86.34 0.0000
Residual
285 225.97
0.792876
Lack of fit 77 66.2655
0.86059
1.12 0.2619
Pure Error 208 159.704
0.767808
ii. Click on display summaries in the “Forclass” menu to obtain
descriptives and the correlation between SOS and SOI
Data set = Forclass, Sample Correlations
sos 1.0000 0.4822
soitot 0.4822 1.0000
sos soitot
b. Muliple Regression
i. Using forclass.lsp still click on Graph and Fit -> Fit linear LS.
Move a, e and sos over to predictors and soitot over to response
and click on OK. Back to the original ARC window and interpret
results.
Data set = Forclass, Name of Fit = L1
Normal Regression
Kernel mean function = Identity
Response
= soitot
Terms
= (a e sos)
Coefficient Estimates
Label
Estimate
Std. Error t-value p-value
Constant -1.74676
0.543001
-3.217 0.0014
a
-0.0251484
0.00846596 -2.971 0.0032
e
0.0270824
0.00981833 2.758 0.0062
sos
0.0228383
0.00271460
8.413 0.0000
R Squared:
0.269142
Sigma hat:
0.871993
Number of cases:
287
Degrees of freedom:
283
Summary Analysis of Variance Table
Source
df
SS
MS
F p-value
Regression
3 79.2432
26.4144
34.74 0.0000
Residual
283 215.185
0.760372
Lack of fit 281 214.26
0.762491
1.65 0.4543
Pure Error 2 0.925528
0.462764
Psy 524
Ainsworth
ii. Click on display summaries in the “forclass” menu to obtain
correlations for a, e, sos and soitot. Do any of the correlations
indicate multicollinearity, why or why not?
Data set = Forclass, Sample Correlations
a
1.0000 0.1387 -0.1988 -0.2235
e
0.1387 1.0000 0.0843 0.1579
sos -0.1988 0.0843 1.0000 0.4822
soitot -0.2235 0.1579 0.4822 1.0000
a
e sos soitot
None of the correlations exceed even .5 so no multicollinearity
iii. Go to graph and fit -> Multipanel plot. Put a, e, and sos into
changing axis and residuals into fixed axis. Does there seem to be
a problem with heteroskedasticity on any of the variables?
Explain.
This is a repeat from before but sos predicting soitot does seem to be a little
heteroskedastic because the residuals appear to be truncated at low levels of sos. The
bottom left of the graph shows that you don’t have as many negative residuals at low
sos values.
3. Standard Regression in SPSS
a. Open up the forclass.sav data set in SPSS. Go to Analyze -> Regression > Linear. Give me a, e, and sos predicting soitot. Include estimates,
model fit, r squared change, descriptives, part and partial correlations,
collinearity diagnostics, a plot of zpred (x) and zresid (y), and save
mahalanobis distances. Interpret and annotate the output.
Psy 524
Ainsworth
output for lab 3 question 3
De scriptiv e Statis tics
Me an
Std . Deviatio n
-.0 155
1.0 1463
sexual o penn ess a nd in timacy
N
28 7
ag reeab lene ss
41 .878
6.2 948
28 7
ext raversion
40 .728
5.3 385
28 7
73 .6237
19 .5111 0
28 7
sexual o pinio n survey
Correla tions
sexual o penn ess
an d inti macy
ag reeab lene ss ext raversion
Pe arson Correlatio n sexual o penn ess a nd in timacy
1.0 00
-.2 24
.15 8
Sig . (1-t ailed )
ag reeab lene ss
-.2 24
1.0 00
.13 9
ext raversion
.15 8
.13 9
1.0 00
.08 4
sexual o pinio n survey
.48 2
-.1 99
.08 4
1.0 00
sexual o penn ess a nd in timacy
N
sexual o pinio n
survey
.48 2
-.1 99
.
.00 0
.00 4
.00 0
ag reeab lene ss
.00 0
.
.00 9
.00 0
ext raversion
.00 4
.00 9
.
.07 7
sexual o pinio n survey
.00 0
.00 0
.07 7
.
sexual o penn ess a nd in timacy
28 7
28 7
28 7
28 7
ag reeab lene ss
28 7
28 7
28 7
28 7
ext raversion
28 7
28 7
28 7
28 7
sexual o pinio n survey
28 7
28 7
28 7
28 7
Va riable s Entered/Rem ov ed b
Mo del
1
Va riable s Ent ered
sexual o pinio n
survey,
ext raversion, a
agreeab leness
Va riable s
Re move d
Me thod
. En ter
a. All requ ested varia bles entered.
b. De pend ent V ariab le: se xual openn ess a nd in tima cy
Model S ummaryb
Mo del
1
R
.51 9 a
R S quare Ad justed R S quare
.26 9
.26 1
Std . Erro r of
the Estim ate R S quare Ch ange
.87 199
.26 9
Ch ange Stati stics
F Chang e
34 .739
df1
df2
3
28 3
a. Pre dicto rs: (Consta nt), sexua l opin ion survey, extraversion, agree able ness
b. De pend ent V ariab le: se xual open ness and intim acy
ANOVA b
Mo del
1
Re gression
Su m of Squa res
79 .243
df
3
Me an S quare
26 .414
.76 0
Re sidua l
21 5.185
28 3
To tal
29 4.429
28 6
F
34 .739
a. Pre dicto rs: (Consta nt), sexua l opi nion surve y, ext raversion, agre eable ness
b. De pend ent V ariab le: se xual open ness and intim acy
Sig .
.00 0 a
Sig . F Chang e
.00 0
Psy 524
Ainsworth
Coefficients a
Un stand ardized Co efficients
Mo del
1
Sta ndardized
Co efficie nts
t
-3.2 17
Sig .
Zero-ord er
Pa rtial
Co llinea rity Statistics
Std . Erro r
.54 3
agreeab leness
-2.5 15E-02
.00 8
-.15 6
-2.9 71
.00 3
-.22 4
-.17 4
-.15 1
.93 6
1.0 68
extraversion
2.7 08E-02
.01 0
.14 2
2.7 58
.00 6
.15 8
.16 2
.14 0
.96 8
1.0 33
sexual o pinio n survey
2.2 84E-02
.00 3
.43 9
8.4 13
.00 0
.48 2
.44 7
.42 8
.94 8
1.0 55
(Co nstan t)
Be ta
Co rrelations
B
-1.7 47
Pa rt
To leran ce
VIF
.00 1
a. De pend ent Variab le: se xual open ness a nd in tima cy
Collinea rity Diagnostic sa
Va riance Pro portio ns
Mo del
1
Dim ensi on
1
Eig enva lue Co nditio n Ind ex
3.9 20
1.0 00
(Co nstan t)
.00
ext raversion
.00
sexual o pinio n
survey
.00
2
5.7 79E-02
8.2 36
.00
.08
.01
.77
3
1.5 40E-02
15 .956
.00
.57
.57
.11
4
6.4 59E-03
24 .637
.99
.35
.41
.12
a. De pend ent V ariab le: se xual open ness and i ntima cy
Ca sew i se Di agnostics a
Ca se Nu mber Std . Residual
127
3.8 89
199
ag reeab lene ss
.00
3.2 61
sexual o penn ess
and intim acy
3.6 9
2.2 3
a. De pend ent V ariab le: se xual openn ess a nd in tima cy
Psy 524
Ainsworth
Re sidua ls Statisti cs a
Min imum
-1.4 835
Ma ximu m
1.4 066
-2.7 89
2.7 02
.00 0
1.0 00
287
Sta ndard Erro r of
Pre dicte d Va lue
.05 199
.20 516
.09 891
.02 859
287
Ad justed Pred icted Valu e
-1.4 898
1.3 820
-.01 54
.52 693
287
Re sidua l
-1.9 911
3.3 916
.00 00
.86 741
287
-2.2 83
3.8 89
.00 0
.99 5
287
Pre dicte d Va lue
Std . Pre dicte d Val ue
Std . Residual
Stu d. Re sidua l
Me an
Std . Dev iatio n
-.01 55
.52 638
N
287
-2.3 02
3.9 05
.00 0
1.0 01
287
-2.0 235
3.4 188
.00 00
.87 888
287
-2.3 20
4.0 08
.00 2
1.0 07
287
Ma hal. Distan ce
.02 0
14. 835
2.9 90
2.4 01
287
Co ok's Distan ce
.00 0
.06 4
.00 3
.00 6
287
Ce ntere d Lev erage Val ue
.00 0
.05 2
.01 0
.00 8
287
De leted Resid ual
Stu d. De leted Residual
a. De pend ent V ariab le: se xual open ness a nd in tima cy
Charts
Scatterplot
Dependent Variable: sexual openness and intimacy
4
3
2
1
0
-1
-2
-3
-3
-2
-1
0
1
2
3
Regression Standardized Predicted Value
yes the output is the same as the ARC output.
b. Compare the output to the output from ARC. Expect there to be a little
difference because they use different estimation methods, but are the two
outputs similar?
4. Do a user defined sequential analysis using the block function, predicting soitot
by a, e and sos. The order should be a, e and sos, include r-square change and
interpret results.
Psy 524
Ainsworth
Va riable s Entered/Rem ov ed b
Va riable s
Re move d
Mo del
1
Va riable s Ent ered
agreeab lenessa
Me thod
. En ter
2
ego tism a
. En ter
3
sexual o pinio n
a
survey
. En ter
a. All requ ested varia bles entered.
b. De pend ent V ariab le: se xual openn ess a nd in tima cy
Model S umm ary
Ch ange Stat istics
Mo del
1
R S quare Ch ange
.05 0 a
F Chang e
14 .992
df1
1
df2
28 5
Sig . F Chang e
.00 0
2
.00 0 b
.00 0
1
28 4
.99 3
3
.20 0 c
75 .467
1
28 3
.00 0
a. Pre dicto rs: (Consta nt), a gree able ness
b. Pre dicto rs: (Consta nt), a gree able ness, egot ism
c. Pre dicto rs: (Consta nt), a gree able ness, egot ism, sexua l opin ion surve y
Coeffici ents a
Un stand ardiz ed Co effici ents
Mo del
1
B
(Co nstan t)
agreeab leness
1.4 94
Std . Erro r
.39 4
-3.6 03E -02
.00 9
Sta ndardized
Co efficie nts
Be ta
t
Sig .
3.7 90
.00 0
-.22 4
-3.8 72
.00 0
ego tism
sex ual o pinio n survey
2
(Co nstan t)
agreeab leness
ego tism
1.4 88
.70 2
2.1 20
.03 5
-3.6 05E -02
.01 0
-.22 4
-3.7 82
.00 0
3.6 69E-05
.00 4
.00 1
.00 9
.99 3
sex ual o pinio n survey
3
(Co nstan t)
-.64 7
.67 2
-.96 4
.33 6
agreeab leness
-2.0 64E -02
.00 9
-.12 8
-2.3 81
.01 8
ego tism
-1.5 53E -03
.00 4
-.02 3
-.42 8
.66 9
2.3 76E-02
.00 3
.45 7
8.6 87
.00 0
sex ual o pinio n survey
a. De pend ent V ariab le: se xual open ness a nd in tima cy
Ex clude d Va riable s c
Co llinea rity
Sta tistic s
Mo del
1
ego tism
sex ual o pinio n survey
2
Be ta In
.00 1 a
t
.00 9
Sig .
.99 3
Pa rtial Correl ation
.00 1
To leran ce
.95 7
.45 6 a
8.6 89
.00 0
.45 8
.96 0
.45 7 b
8.6 87
.00 0
.45 9
.95 8
ego tism
sex ual o pinio n survey
a. Pre dicto rs in the M odel : (Con stant ), agreeab leness
b. Pre dicto rs in the M odel : (Con stant ), agreeab leness, eg otism
c. De pend ent V ariab le: se xual open ness and i ntima cy
Psy 524
Ainsworth
5. Do a forward statistical regression and include a, e and sos (include r-squared
change) predicting soitot. Interpret results and compare them to the previous
result (#4).
Regression
Va riable s Entered/Rem ov ed a
Mo del
1
Va riable s Ent ered
Va riable s
Re move d
sexual o pinio n
survey
2
Me thod
Forward
(Criterio n:
. Pro babi lity-of
-F-t o-ent er <=
.05 0)
agreeab leness
Forward
(Criterio n:
. Pro babi lity-of
-F-t o-ent er <=
.05 0)
ext raversion
Forward
(Criterio n:
. Pro babi lity-of
-F-t o-ent er <=
.05 0)
3
a. De pend ent V ariab le: se xual openn ess a nd in tima cy
Model Summary
Mo del
1
R
.48 2 a
Std . Erro r of
R Square Ad justed R Square the Estim ate R Square Ch ange
.23 3
.23 0
.89 044
.23 3
Ch ange Stati stics
F Chang e
86 .343
df1
1
df2
28 5
Sig . F Chang e
.00 0
2
.49 9 b
.24 9
.24 4
.88 208
.01 7
6.4 25
1
28 4
.01 2
3
.51 9 c
.26 9
.26 1
.87 199
.02 0
7.6 09
1
28 3
.00 6
a. Pre dicto rs: (Consta nt), sexua l opin ion survey
b. Pre dicto rs: (Consta nt), sexua l opin ion survey, agreeab leness
c. Pre dicto rs: (Consta nt), sexua l opin ion survey, agreeab leness, extrave rsion
ANOVA d
Mo del
1
2
3
Re gression
Su m of Squa res
68 .459
df
1
Me an S quare
68 .459
.79 3
Re sidua l
22 5.970
28 5
To tal
29 4.429
28 6
73 .458
2
36 .729
Re sidua l
22 0.971
28 4
.77 8
To tal
29 4.429
28 6
79 .243
3
26 .414
Re sidua l
21 5.185
28 3
.76 0
To tal
29 4.429
28 6
Re gression
Re gression
F
86 .343
.00 0 a
47 .205
.00 0 b
34 .739
.00 0 c
a. Pre dicto rs: (Consta nt), sexua l opi nion surve y
b. Pre dicto rs: (Consta nt), sexua l opi nion surve y, ag reeab lene ss
c. Pre dicto rs: (Consta nt), sexua l opi nion surve y, ag reeab lene ss, ex trave rsion
d. De pend ent V ariab le: se xual open ness and intim acy
Sig .
Psy 524
Ainsworth
Coeffici ents a
Un stand ardiz ed Co effici ents
Mo del
1
(Co nstan t)
sex ual o pinio n survey
B
-1.8 62
Std . Erro r
.20 6
2.5 08E-02
.00 3
Sta ndardized
Co efficie nts
Be ta
.48 2
t
-9.0 58
Sig .
.00 0
9.2 92
.00 0
agreeab leness
ext raversion
2
(Co nstan t)
sex ual o pinio n survey
agreeab leness
-.86 3
.44 3
-1.9 46
.05 3
2.3 70E-02
.00 3
.45 6
8.6 89
.00 0
-2.1 43E -02
.00 8
-.13 3
-2.5 35
.01 2
ext raversion
3
(Co nstan t)
sex ual o pinio n survey
agreeab leness
ext raversion
-1.7 47
.54 3
-3.2 17
.00 1
2.2 84E-02
.00 3
.43 9
8.4 13
.00 0
-2.5 15E -02
.00 8
-.15 6
-2.9 71
.00 3
2.7 08E-02
.01 0
.14 2
2.7 58
.00 6
a. De pend ent V ariab le: se xual open ness a nd in tima cy
Ex clude d Va riabl es c
Co llinea rity
Sta tistic s
Mo del
1
ag reeab lene ss
Be ta In
-.1 33 a
t
-2. 535
.11 8 a
.14 2 b
ext raversion
2
Sig .
.01 2
Pa rtial Correl ation
-.1 49
To leran ce
.96 0
2.2 84
.02 3
.13 4
.99 3
2.7 58
.00 6
.16 2
.96 8
ag reeab lene ss
ext raversion
a. Pre dicto rs in the M odel : (Co nstan t), se xual o pini on su rvey
b. Pre dicto rs in the M odel : (Co nstan t), se xual o pini on su rvey, agree able ness
c. De pend ent V ariab le: se xual open ness and intim acy
6. Do a stepwise regression including sos, ego, n, e, o, a and c predicting soitot.
Include estimates, model fit, r squared change, descriptives, part and partial
correlations, collinearity diagnostics, a plot of zpred (x) and zresid (y), and save
mahalanobis distances. Interpret and annotate the output.
Regression
De scriptiv e Statis tics
sexual o penn ess a nd in timacy
sexual o pinio n survey
Me an
Std . Deviatio n
-.0 155
1.0 1463
N
28 7
73 .6237
19 .5111 0
28 7
16 3.186 4
14 .7521 8
28 7
ne roticism
36 .948
7.1 976
28 7
ext raversion
40 .728
5.3 385
28 7
op enne ss
40 .456
5.8 355
28 7
ag reeab lene ss
41 .878
6.2 948
28 7
con scien tiousness
41 .983
7.0 728
28 7
eg otism
Psy 524
Ainsworth
Correlations
sexual openness sexual opinion
and intimacy
survey
Pearson Correlation sexual openness and intimacy
1.000
.482
Sig. (1-tailed)
N
egotism
neroticism extraversion
-.046
-.123
.158
openness agreeableness conscientiousness
.089
-.224
-.128
sexual opinion survey
.482
1.000
.007
-.098
.084
.191
-.199
egotism
-.046
.007
1.000
.013
.010
.390
.208
.087
neroticism
-.123
-.098
.013
1.000
-.238
.017
-.038
-.262
extraversion
.158
.084
.010
-.238
1.000
.033
.139
.168
openness
.089
.191
.390
.017
.033
1.000
.055
-.019
agreeableness
-.224
-.199
.208
-.038
.139
.055
1.000
.217
conscientiousness
-.128
-.048
.087
-.262
.168
-.019
.217
1.000
sexual openness and intimacy
-.048
.
.000
.218
.019
.004
.067
.000
.015
sexual opinion survey
.000
.
.453
.049
.077
.001
.000
.210
egotism
.218
.453
.
.415
.431
.000
.000
.071
neroticism
.019
.049
.415
.
.000
.388
.258
.000
extraversion
.004
.077
.431
.000
.
.290
.009
.002
openness
.067
.001
.000
.388
.290
.
.177
.372
agreeableness
.000
.000
.000
.258
.009
.177
.
.000
conscientiousness
.015
.210
.071
.000
.002
.372
.000
.
sexual openness and intimacy
287
287
287
287
287
287
287
287
sexual opinion survey
287
287
287
287
287
287
287
287
egotism
287
287
287
287
287
287
287
287
neroticism
287
287
287
287
287
287
287
287
extraversion
287
287
287
287
287
287
287
287
openness
287
287
287
287
287
287
287
287
agreeableness
287
287
287
287
287
287
287
287
conscientiousness
287
287
287
287
287
287
287
287
Psy 524
Ainsworth
Va riable s Entered/Rem ov ed a
Mo del
1
Va riable s Ent ered
Va riable s
Re move d
sexual o pinio n
survey
2
Me thod
Ste pwise
(Criteria :
Pro babi lity-of
-F-t o-ent er <=
.
.05 0,
Pro babi lity-of
-F-t o-rem ove
>= .100).
agreeab leness
Ste pwise
(Criteria :
Pro babi lity-of
-F-t o-ent er <=
.
.05 0,
Pro babi lity-of
-F-t o-rem ove
>= .100).
ext raversion
Ste pwise
(Criteria :
Pro babi lity-of
-F-t o-ent er <=
.
.05 0,
Pro babi lity-of
-F-t o-rem ove
>= .100).
con scien tiousness
Ste pwise
(Criteria :
Pro babi lity-of
-F-t o-ent er <=
.
.05 0,
Pro babi lity-of
-F-t o-rem ove
>= .100).
3
4
a. De pend ent V ariab le: se xual openn ess a nd in tima cy
Model Summarye
Model
1
R
.482 a
Std. Error of
R Square Adjusted R Square the Estim ate R Square Change
.233
.230
.89044
.233
Change Stati stics
F Change
86.343
df1
1
df2
285
Sig. F Change
.000
2
.499 b
.249
.244
.88208
.017
6.425
1
284
.012
3
.519 c
.269
.261
.87199
.020
7.609
1
283
.006
4
.528 d
.279
.269
.86753
.010
3.917
1
282
.049
a. Predictors: (Constant), sexual opinion survey
b. Predictors: (Constant), sexual opinion survey, agreeableness
c. Predictors: (Constant), sexual opinion survey, agreeableness, extraversion
d. Predictors: (Constant), sexual opinion survey, agreeableness, extraversion, conscientiousness
e. Dependent Variable: sexual openness and intim acy
Psy 524
Ainsworth
ANOVA e
Mo del
1
2
Re gression
Su m of Squa res
68 .459
Me an S quare
68 .459
.79 3
22 5.970
28 5
To tal
29 4.429
28 6
73 .458
2
36 .729
Re sidua l
22 0.971
28 4
.77 8
To tal
29 4.429
28 6
79 .243
3
26 .414
Re sidua l
21 5.185
28 3
.76 0
To tal
29 4.429
28 6
82 .191
4
20 .548
Re sidua l
21 2.237
28 2
.75 3
To tal
29 4.429
28 6
Re gression
4
1
Re sidua l
Re gression
3
df
Re gression
F
86 .343
Sig .
.00 0 a
47 .205
.00 0 b
34 .739
.00 0 c
27 .302
.00 0 d
a. Pre dicto rs: (Consta nt), sexua l opi nion surve y
b. Pre dicto rs: (Consta nt), sexua l opi nion surve y, ag reeab lene ss
c. Pre dicto rs: (Consta nt), sexua l opi nion surve y, ag reeab lene ss, ex trave rsion
d. Pre dicto rs: (Consta nt), sexua l opi nion surve y, ag reeab lene ss, ex trave rsion ,
con scien tiou sness
e. De pend ent V ariab le: se xual open ness and intim acy
Coefficients a
Un stand ardized Co efficients
Mo del
1
(Co nstan t)
sexual o pinio n survey
B
-1.8 62
Std . Erro r
.20 6
2.5 08E-02
.00 3
Sta ndardized
Co efficie nts
Be ta
.48 2
Co rrelations
t
-9.0 58
Sig .
Zero-ord er
Pa rtial
Co llinea rity Statistics
Pa rt
To leran ce
VIF
.00 0
9.2 92
.00 0
.48 2
.48 2
.48 2
1.0 00
1.0 00
agreeab leness
extraversion
con scien tiousness
2
(Co nstan t)
-.86 3
.44 3
-1.9 46
.05 3
sexual o pinio n survey
2.3 70E-02
.00 3
.45 6
8.6 89
.00 0
.48 2
.45 8
.44 7
.96 0
1.0 41
agreeab leness
-2.1 43E-02
.00 8
-.13 3
-2.5 35
.01 2
-.22 4
-.14 9
-.13 0
.96 0
1.0 41
extraversion
con scien tiousness
3
(Co nstan t)
-1.7 47
.54 3
-3.2 17
.00 1
sexual o pinio n survey
2.2 84E-02
.00 3
.43 9
8.4 13
.00 0
.48 2
.44 7
.42 8
.94 8
1.0 55
agreeab leness
-2.5 15E-02
.00 8
-.15 6
-2.9 71
.00 3
-.22 4
-.17 4
-.15 1
.93 6
1.0 68
extraversion
2.7 08E-02
.01 0
.14 2
2.7 58
.00 6
.15 8
.16 2
.14 0
.96 8
1.0 33
con scien tiousness
4
(Co nstan t)
-1.3 64
.57 4
-2.3 78
.01 8
sexual o pinio n survey
2.2 72E-02
.00 3
.43 7
8.4 12
.00 0
.48 2
.44 8
.42 5
.94 7
1.0 56
agreeab leness
-2.1 92E-02
.00 9
-.13 6
-2.5 55
.01 1
-.22 4
-.15 0
-.12 9
.90 2
1.1 08
extraversion
2.9 91E-02
.01 0
.15 7
3.0 29
.00 3
.15 8
.17 8
.15 3
.94 8
1.0 55
con scien tiousness
-1.4 86E-02
.00 8
-.10 4
-1.9 79
.04 9
-.12 8
-.11 7
-.10 0
.93 3
1.0 72
a. De pend ent Variab le: se xual open ness a nd in tima cy
Psy 524
Ainsworth
Ex clude d Va riable s e
Co llinea rity S tatistics
Mo del
1
2
ego tism
Be ta In
-.04 9 a
t
Sig .
-.95 2
Pa rtial Correl ation
.34 2
-.05 6
To leran ce
1.0 00
VIF
1.0 00
Min imum
To leran ce
1.0 00
neroticism
-.07 6 a
-1.4 62
.14 5
-.08 6
.99 0
1.0 10
.99 0
extraversion
.11 8 a
2.2 84
.02 3
.13 4
.99 3
1.0 07
.99 3
ope nness
-.00 3 a
-.06 3
.95 0
-.00 4
.96 4
1.0 38
.96 4
agreeab leness
-.13 3 a
-2.5 35
.01 2
-.14 9
.96 0
1.0 41
.96 0
con scien tiousness
-.10 5
a
-2.0 27
.04 4
-.11 9
.99 8
1.0 02
.99 8
ego tism
-.02 3 b
-.42 8
.66 9
-.02 5
.95 4
1.0 48
.91 7
neroticism
-.08 4 b
-1.6 31
.10 4
-.09 6
.98 7
1.0 13
.94 9
extraversion
.14 2 b
2.7 58
.00 6
.16 2
.96 8
1.0 33
.93 6
ope nness
.01 0 b
.18 2
.85 6
.01 1
.95 5
1.0 47
.92 0
con scien tiousness
-.08 1 b
-1.5 36
.12 6
-.09 1
.95 3
1.0 50
.91 7
ego tism
-.01 9 c
-.36 4
.71 6
-.02 2
.95 4
1.0 49
.89 3
neroticism
-.05 5 c
-1.0 51
.29 4
-.06 2
.93 7
1.0 67
.91 9
.00 9 c
.17 9
.85 8
.01 1
.95 5
1.0 47
.90 8
con scien tiousness
-.10 4 c
-1.9 79
.04 9
-.11 7
.93 3
1.0 72
.90 2
ego tism
-.01 4 d
-.27 1
.78 7
-.01 6
.95 1
1.0 51
.86 5
neroticism
-.08 5 d
-1.5 78
.11 6
-.09 4
.88 4
1.1 32
.88 0
.00 6 d
.11 6
.90 8
.00 7
.95 4
1.0 49
.89 3
agreeab leness
3
extraversion
ope nness
agreeab leness
4
extraversion
ope nness
agreeab leness
con scien tiousness
a. Pre dicto rs in the M odel: (Con stant), sexual o pinio n survey
b. Pre dicto rs in the M odel: (Con stant), sexual o pinio n survey, a greea blen ess
c. Pre dicto rs in the M odel: (Con stant), sexual o pinio n survey, a greea blen ess, e xtraversion
d. Pre dicto rs in the M odel: (Con stant), sexual o pinio n survey, a greea blen ess, e xtraversion , con scien tiousness
e. De pend ent V ariab le: se xual open ness a nd in tima cy
Psy 524
Ainsworth
Collinea rity Diagnostic sa
Va riance Pro portio ns
Mo del
1
Dim ensi on
1
2
Eig enva lue Co nditio n Ind ex
1.9 67
1.0 00
sexual o pinio n
(Co nstan t)
survey
ag reeab lene ss extraversion con scien tiou sness
.02
.02
3.3 26E-02
7.6 90
.98
.98
1
2.9 36
1.0 00
.00
.01
.00
2
5.5 27E-02
7.2 89
.01
.72
.12
3
8.5 24E-03
18 .559
.99
.27
.88
1
3.9 20
1.0 00
.00
.00
.00
.00
2
5.7 79E-02
8.2 36
.00
.77
.08
.01
3
1.5 40E-02
15 .956
.00
.11
.57
.57
4
6.4 59E-03
24 .637
.99
.12
.35
.41
1
4.8 96
1.0 00
.00
.00
.00
.00
.00
2
6.2 20E-02
8.8 73
.00
.76
.04
.00
.03
3
2.0 11E-02
15 .605
.01
.00
.22
.05
.88
4
1.5 34E-02
17 .866
.00
.11
.47
.62
.01
5
6.1 56E-03
28 .203
.99
.13
.26
.33
.07
3
4
5
2
4
5
3
5
4
a. De pend ent V ariab le: se xual open ness and intim acy
Ca sew i se Di agnostics a
Ca se Nu mber Std . Residual
127
3.8 39
199
sexual o penn ess
and intim acy
3.6 9
3.3 62
2.2 3
a. De pend ent V ariab le: se xual openn ess a nd in tima cy
Re sidua ls Statisti cs a
Min imum
-1.6 846
Ma ximu m
1.4 339
-3.1 14
2.7 04
.00 0
1.0 00
287
Sta ndard Erro r of
Pre dicte d Va lue
.05 827
.20 872
.11 020
.03 115
287
Ad justed Pred icted Valu e
-1.7 043
1.3 557
-.01 54
.53 741
287
Re sidua l
-1.9 009
3.3 307
.00 00
.86 145
287
Std . Residual
-2.1 91
3.8 39
.00 0
.99 3
287
Stu d. Re sidua l
-2.2 12
3.8 57
.00 0
1.0 01
287
-1.9 373
3.3 617
.00 00
.87 624
287
-2.2 28
3.9 56
.00 2
1.0 07
287
Ma hal. Distan ce
.29 4
15. 558
3.9 86
2.9 05
287
Co ok's Distan ce
.00 0
.05 4
.00 3
.00 7
287
Ce ntere d Lev erage Val ue
.00 1
.05 4
.01 4
.01 0
287
Pre dicte d Va lue
Std . Pre dicte d Val ue
De leted Resid ual
Stu d. De leted Residual
a. De pend ent V ariab le: se xual open ness a nd in tima cy
Me an
Std . Dev iatio n
-.01 55
.53 608
N
287
Psy 524
Ainsworth
Charts
Scatterplot
Dependent Variable: sexual openness and intimacy
4
3
2
1
0
-1
-2
-3
-4
-3
-2
-1
0
1
2
3
Regression Standardized Predicted Value
7. Still using the forclass.sav data go to Data -> Select Cases -> Random Sample of
Cases -> Sample. Choose approximately 50%. Continue -> OK. Go to transform
-> Compute. Put in set=filter_$. Fit a simultaneous regression with a, e, and sos
predicting soitot. Go back to Data -> select cases -> If condition satisfied -> If.
Type in set = 0. Fit the exact same regression equation and compare the two
outputs. Are the two outputs the same? Can you generalize the equation?
Regression for the first half
Va riable s Entered/Rem ov ed b
Mo del
1
Va riable s Ent ered
sexual o pinio n
survey,
ext raversion, a
agreeab leness
Va riable s
Re move d
Me thod
. En ter
a. All requ ested varia bles entered.
b. De pend ent V ariab le: se xual openn ess a nd in tima cy
Model S umm ary
Mo del
1
R
.54 5 a
R S quare
Ad justed R S quare
.29 7
.28 2
Std . Erro r of
the Estim ate
.92 738
a. Pre dicto rs: (Consta nt), sexua l opin ion surve y, ext raversion,
ag reeab lene ss
Psy 524
Ainsworth
ANOVA b
Mo del
1
Re gression
Su m of Squa res
52 .969
df
3
Me an S quare
17 .656
.86 0
Re sidua l
12 5.564
14 6
To tal
17 8.533
14 9
F
20 .530
Sig .
.00 0 a
a. Pre dicto rs: (Consta nt), sexua l opi nion surve y, ext raversion, agre eable ness
b. De pend ent V ariab le: se xual open ness and intim acy
Coeffici ents a
Sta ndardized
Co efficie nts
Un stand ardized Co effici ents
Mo del
1
B
-2.2 86
Std . Erro r
.80 4
-2.5 88E -02
.01 2
-.15 5
-2.1 17
.03 6
ext raversion
3.7 74E-02
.01 5
.18 0
2.5 47
.01 2
sexual o pinio n survey
2.4 96E-02
.00 4
.43 9
6.0 08
.00 0
(Co nstan t)
agreeab leness
Be ta
t
-2.8 43
Sig .
.00 5
a. De pend ent V ariab le: se xual open ness a nd in tima cy
Regression for second half
Va riable s Entered/Rem ov ed b
Mo del
1
Va riable s Ent ered
sexual o pinio n
survey,
ext raversion, a
agreeab leness
Va riable s
Re move d
Me thod
. En ter
a. All requ ested varia bles entered.
b. De pend ent V ariab le: se xual openn ess a nd in tima cy
Model S umm ary
Mo del
1
R
.48 9 a
R S quare
Ad justed R S quare
.23 9
.22 1
Std . Erro r of
the Estim ate
.81 266
a. Pre dicto rs: (Consta nt), sexua l opin ion surve y, ext raversion,
ag reeab lene ss
ANOVA b
Mo del
1
Re gression
Re sidua l
To tal
Su m of Squa res
27 .531
df
3
Me an S quare
9.1 77
87 .835
13 3
.66 0
11 5.367
13 6
F
13 .896
a. Pre dicto rs: (Consta nt), sexua l opi nion surve y, ext raversion, agre eable ness
b. De pend ent V ariab le: se xual open ness and intim acy
Sig .
.00 0 a
Psy 524
Ainsworth
Coeffici ents a
Un stand ardized Co effici ents
Mo del
1
Sta ndardized
Co efficie nts
B
-1.2 67
Std . Erro r
.73 4
-2.2 17E -02
.01 2
-.14 4
-1.8 66
.06 4
ext raversion
1.6 04E-02
.01 3
.09 5
1.2 39
.21 8
sexual o pinio n survey
2.0 45E-02
.00 4
.44 1
5.7 72
.00 0
(Co nstan t)
agreeab leness
Be ta
t
-1.7 25
Sig .
.08 7
a. De pend ent V ariab le: se xual open ness a nd in tima cy
When I did it I got slightly different R-squared values which says the equation may not
generalize and the regression coefficients are different for the two models which also
says it may not generalize.
8. Centering and Interactions. Open social2.sav in SPSS.
a. Recode gender so that males = 0 and females = 1.
b. Center both ciccomp and oocomp separately (ciccent and oocent)
c. Predict oocent with gender and ciccent and interpret results (don’t forget
to interpret the intercept since it is meaningful).
Va riabl es Entere d/Rem ov e db
Mo del
1
Va riable s En tered
GE NDE R,
a
CICCENT
Va riable s
Re move d
Me thod
. En ter
a. All requ ested vari ables ente red.
b. De pend ent V ariab le: O OCE NT
Model S umm ary
Mo del
1
R
.44 3 a
R S quare
Ad justed R S quare
.19 7
.19 0
Std . Erro r of
the Estim ate
4.1 8239
a. Pre dicto rs: (Consta nt), G ENDER, CICCENT
ANOVA b
Mo del
1
Re gression
Su m of Squa res
10 79.19 5
df
2
Me an S quare
53 9.597
17 .492
Re sidua l
44 08.09 2
25 2
To tal
54 87.28 6
25 4
a. Pre dicto rs: (Consta nt), G ENDER, CICCENT
b. De pend ent V ariab le: O OCE NT
F
30 .847
Sig .
.00 0 a
Psy 524
Ainsworth
Coeffici ents a
Un stand ardized Co efficients
Mo del
1
B
Sta ndardized
Co effici ents
(Co nstan t)
-.5 82
Std . Erro r
.35 0
Be ta
t
-1. 664
Sig .
CICCENT
.20 3
.02 8
.40 6
7.1 69
.00 0
GE NDE R
1.4 59
.52 9
.15 6
2.7 60
.00 6
.09 7
a. De pend ent V ariab le: O OCENT
d. Cross multiply gender (0 and 1) and ciccent to make a new variable
gen_cic.
e. Predict oocent by gender (0 and 1), ciccent and gen_cic. Interpret the
results.
Regression
Va riabl es Entere d/Rem ov e db
Mo del
1
Va riable s
Re move d
Va riable s En tered
GE N_CIC,
GE NDE R,a
CICCENT
Me thod
. En ter
a. All requ ested vari ables ente red.
b. De pend ent V ariab le: O OCE NT
Model S umm ary
Mo del
1
R
.44 4 a
Std . Erro r of
the Estim ate
4.1 9049
R S quare
Ad justed R S quare
.19 7
.18 7
a. Pre dicto rs: (Consta nt), G EN_ CIC, GENDER, CICCENT
ANOVA b
Mo del
1
Re gression
Su m of Squa res
10 79.67 6
df
3
Me an S quare
35 9.892
17 .560
Re sidua l
44 07.61 1
25 1
To tal
54 87.28 6
25 4
F
20 .495
Sig .
.00 0 a
a. Pre dicto rs: (Consta nt), G EN_ CIC, GENDER, CICCENT
b. De pend ent V ariab le: O OCE NT
Coeffici ents a
Un stand ardized Co efficients
Mo del
1
B
Sta ndardized
Co effici ents
(Co nstan t)
-.5 81
Std . Erro r
.35 1
GE NDE R
1.4 63
.53 0
.15 6
2.7 59
.00 6
CICCENT
.20 7
.03 7
.41 3
5.5 73
.00 0
GE N_CI C
-9. 538E -03
.05 8
-.0 12
-.1 65
.86 9
a. De pend ent V ariab le: O OCENT
Be ta
t
-1. 657
Sig .
.09 9
Psy 524
Ainsworth
9. Mediation using regression. Open social2.sav in SPSS and perform a mediational
analysis using oocomp as the predictor, ciccomp as the mediator and qdicomp as
the outcome. Interpret the results. Refer to the four steps from the powerpoint
slides.
Regression
Va riabl es Entere d/Rem ov e db
Mo del
1
Va riable s En tered
OO COM Pa
Va riable s
Re move d
Me thod
. En ter
a. All requ ested vari ables ente red.
b. De pend ent V ariab le: Q DICO MP
Model S umm ary
Mo del
1
R
.31 5 a
Std . Erro r of
the Estim ate
3.4 8964
R S quare
Ad justed R S quare
.09 9
.09 6
a. Pre dicto rs: (Consta nt), O OCO MP
ANOVA b
Mo del
1
Re gression
Su m of Squa res
34 2.701
df
1
Me an S quare
34 2.701
12 .178
Re sidua l
31 17.46 4
25 6
To tal
34 60.16 4
25 7
F
28 .142
Sig .
.00 0 a
a. Pre dicto rs: (Consta nt), O OCO MP
b. De pend ent V ariab le: Q DICO MP
Coeffici ents a
Un stand ardized Co efficients
Mo del
1
(Co nstan t)
B
16 .768
Std . Erro r
1.0 30
OO COM P
.24 2
.04 6
Sta ndardized
Co effici ents
a. De pend ent V ariab le: Q DICO MP
Regression
Va riabl es Entere d/Rem ov e db
Mo del
1
Va riable s En tered
OO COM Pa
Va riable s
Re move d
a. All requ ested vari ables ente red.
b. De pend ent V ariab le: CICCO MP
Me thod
. En ter
Be ta
.31 5
t
16 .277
5.3 05
Sig .
.00 0
.00 0
Psy 524
Ainsworth
Model S umm ary
Mo del
1
R
Std . Erro r of
the Estim ate
8.4 9284
R S quare
Ad justed R S quare
.19 8
.19 4
.44 4 a
a. Pre dicto rs: (Consta nt), O OCO MP
ANOVA b
Mo del
1
Re gression
Su m of Squa res
45 45.72 3
df
1
Me an S quare
45 45.72 3
72 .128
Re sidua l
18 464.8 59
25 6
To tal
23 010.5 82
25 7
F
63 .023
Sig .
.00 0 a
a. Pre dicto rs: (Consta nt), O OCO MP
b. De pend ent V ariab le: CICCO MP
Coeffici ents a
Un stand ardized Co efficients
Mo del
1
(Co nstan t)
B
48 .257
Std . Erro r
2.5 07
OO COM P
.88 3
.11 1
Sta ndardized
Co effici ents
Be ta
t
19 .249
.44 4
7.9 39
Sig .
.00 0
.00 0
a. De pend ent V ariab le: CICCO MP
Regression
Va riabl es Entere d/Rem ov e db
Mo del
1
Va riable s En tered
CICCOM P,
a
OO COM P
Va riable s
Re move d
Me thod
. En ter
a. All requ ested vari ables ente red.
b. De pend ent V ariab le: Q DICO MP
Model S umm ary
Mo del
1
R
.53 5 a
R S quare
Ad justed R S quare
.28 6
.28 1
Std . Erro r of
the Estim ate
3.1 1191
a. Pre dicto rs: (Consta nt), CICCO MP, OOCOMP
ANOVA b
Mo del
1
Re gression
Su m of Squa res
99 0.756
df
2
Me an S quare
49 5.378
9.6 84
Re sidua l
24 69.40 8
25 5
To tal
34 60.16 4
25 7
a. Pre dicto rs: (Consta nt), CICCO MP , OOCOMP
b. De pend ent V ariab le: Q DICO MP
F
51 .155
Sig .
.00 0 a
Psy 524
Ainsworth
Coeffici ents a
Un stand ardiz ed Co effic ients
Mo del
1
(Co nstan t)
B
7.7 27
Std . Erro r
1.4 37
OO COM P
7.6 99E-02
.04 5
CICCOM P
.18 7
.02 3
Sta ndardized
Co efficie nts
Be ta
t
Sig .
5.3 77
.00 0
.10 0
1.6 93
.09 2
.48 3
8.1 80
.00 0
a. De pend ent V ariab le: Q DICO MP
10. In the social2 data set the variables are:
1 ciccomp
classroom interracial climate
2 qdicomp
discrimination index
3 srchcomp ethnic identity search
4 eicomp
ethinic identity strength
5 subcomp
subgroup identity
6 oocomp
outgroup orientation
7 supcomp
superordinate identity
a. Think of a possible hypothesis for how these variables might predict one
another (e.g. pick a DV and a few IVs and make up a reason why they might
be related) in a use defined sequential regression analysis.
b. Perform all appropriate tests on the variables (assumptions, transformations
when needed,etc).
c. Perform the sequential analysis using SPSS. Interpret the results
d. On a separate sheet of paper write the hypothesis in a couple of sentences max
and then write an APA style results section summarizing your results (refer to
the end of chapter 5 for a couple of samples). Make sure to write the results
so that anyone reading it can understand it (make it as clear as possible and in
very simple language, explaining all technical terms).
This answer is different for everyone so there is no real way to answer it here.