Hallo, ich habe folgende Frage:
Wenn ich mit dem Process Plugin (Modell 1) keine Signifikanz für mein Modell habe aber nicht für die Interaktion von Prädiktor und Moderator, was bedeutet das? Kann ich eine Interaktion als signifikant berichten, auch wenn das Modell keine Signifikanz zeigt oder ist das eine Vorraussetzung um die Interaktion berichten zu können?
(bin über jede Hilfe sehr dankbar, in meiner Arbeitsgruppe kann mir wohl niemand helfen...)
Unten ein Beispiel aus meiner Auswertung (Variablennamen sind verändert).
Vielen Dank!
Run MATRIX procedure:
***************** PROCESS Procedure for SPSS Version 4.0 *****************
Written by Andrew F. Hayes, Ph.D. http://www.afhayes.com
Documentation available in Hayes (2022). http://www.guilford.com/p/hayes3
**************************************************************************
Model : 1
Y : Note
X : Bücher
W : Anwesenheit
Sample
Size: 37
**************************************************************************
OUTCOME VARIABLE:
Note
Model Summary
R R-sq MSE F(HC3) df1 df2 p
,3869 ,1497 ,0352 1,5844 3,0000 33,0000 ,2117
Model
coeff se(HC3) t p LLCI ULCI
constant ,3236 ,0332 9,7610 ,0000 ,2562 ,3911
Bücher -,0002 ,0003 -,5851 ,5624 -,0007 ,0004
Anwesenheit ,0014 ,0058 ,2503 ,8039 -,0103 ,0132
Int_1 ,0001 ,0001 2,1008 ,0434 ,0000 ,0002
Product terms key:
Int_1 : Anwesenheit x Bücher
Test(s) of highest order unconditional interaction(s):
R2-chng F(HC3) df1 df2 p
X*W ,1465 4,4132 1,0000 33,0000 ,0434
----------
Focal predict: Bücher (X)
Mod var: Anwesenheit (W)
Conditional effects of the focal predictor at values of the moderator(s):
Anwesenheit Effect se(HC3) t p LLCI ULCI
-7,7620 -,0010 ,0005 -1,9469 ,0601 -,0020 ,0000
,0000 -,0002 ,0003 -,5851 ,5624 -,0007 ,0004
7,7620 ,0007 ,0004 1,5616 ,1279 -,0002 ,0016
Moderator value(s) defining Johnson-Neyman significance region(s):
Value % below % above
-10,8810 10,8108 89,1892
Conditional effect of focal predictor at values of the moderator:
Anwesenheit Effect se(HC3) t p LLCI ULCI
-23,0270 -,0026 ,0013 -2,1094 ,0426 -,0052 -,0001
-21,1770 -,0024 ,0012 -2,1062 ,0429 -,0048 -,0001
-19,3270 -,0022 ,0011 -2,1016 ,0433 -,0044 -,0001
-17,4770 -,0020 ,0010 -2,0952 ,0439 -,0040 -,0001
-15,6270 -,0018 ,0009 -2,0858 ,0448 -,0036 ,0000
-13,7770 -,0016 ,0008 -2,0720 ,0462 -,0033 ,0000
-11,9270 -,0014 ,0007 -2,0511 ,0483 -,0029 ,0000
-10,8810 -,0013 ,0007 -2,0346 ,0500 -,0027 ,0000
-10,0770 -,0012 ,0006 -2,0185 ,0517 -,0025 ,0000
-8,2270 -,0010 ,0005 -1,9652 ,0578 -,0021 ,0000
-6,3770 -,0008 ,0004 -1,8745 ,0697 -,0018 ,0001
-4,5270 -,0006 ,0004 -1,7123 ,0962 -,0014 ,0001
-2,6770 -,0004 ,0003 -1,4150 ,1664 -,0011 ,0002
-,8270 -,0002 ,0003 -,8963 ,3766 -,0008 ,0003
1,0230 ,0000 ,0003 -,1592 ,8745 -,0006 ,0005
2,8730 ,0002 ,0003 ,5752 ,5691 -,0004 ,0007
4,7230 ,0004 ,0003 1,1025 ,2782 -,0003 ,0010
6,5730 ,0006 ,0004 1,4260 ,1633 -,0002 ,0014
8,4230 ,0008 ,0005 1,6204 ,1147 -,0002 ,0017
10,2730 ,0010 ,0006 1,7414 ,0909 -,0002 ,0021
12,1230 ,0012 ,0006 1,8206 ,0777 -,0001 ,0025
13,9730 ,0014 ,0007 1,8750 ,0697 -,0001 ,0028
Data for visualizing the conditional effect of the focal predictor:
Paste text below into a SPSS syntax window and execute to produce plot.
DATA LIST FREE/
Bücher Anwesenheit Note .
BEGIN DATA.
-130,4001 -7,7620 ,4415
,0000 -7,7620 ,3124
130,4001 -7,7620 ,1834
-130,4001 ,0000 ,3433
,0000 ,0000 ,3236
130,4001 ,0000 ,3039
-130,4001 7,7620 ,2452
,0000 7,7620 ,3348
130,4001 7,7620 ,4245
END DATA.
GRAPH/SCATTERPLOT=
Bücher WITH Note BY Anwesenheit .
*********** BOOTSTRAP RESULTS FOR REGRESSION MODEL PARAMETERS ************
OUTCOME VARIABLE:
Note
Coeff BootMean BootSE BootLLCI BootULCI
constant ,3236 ,3241 ,0313 ,2633 ,3836
Bücher -,0002 -,0002 ,0003 -,0008 ,0003
Anwesenheit ,0014 ,0007 ,0052 -,0107 ,0092
Int_1 ,0001 ,0001 ,0001 ,0000 ,0002
*********************** ANALYSIS NOTES AND ERRORS ************************
Level of confidence for all confidence intervals in output:
95,0000
Number of bootstrap samples for percentile bootstrap confidence intervals:
5000
W values in conditional tables are the mean and +/- SD from the mean.
NOTE: A heteroscedasticity consistent standard error and covariance matrix estimator was used.
NOTE: The following variables were mean centered prior to analysis:
Anwesenheit Bücher
------ END MATRIX -----