Danke für die schnelle Antwort
Zur Info:
- Längsschnittstudie über 10 Tage hinweg
- also "time" (von 0 bis 10)
- Prädiktor Nr.1 : Geschlecht ("Genfer") (1 = Frau, 0 = Mann)
- Prädiktor Nr.2 : Verzeihen ("SplitForgiveness") (1 = niedrig, 0 = hoch)
- Outcome/Target: tägliche Beleidigung ("TransDaily") (dichotom 0 = nein, 1 = ja)
Also es geht darum, ob "Geschlecht" bzw. "Verzeihen" einen Einfluss auf das Erleben von Beleidigungen hat (ja oder nein).
Hier die Syntax meiner drei Modelle:
*Generalized Linear Mixed Models. MODEL 2.1.
GENLINMIXED
/DATA_STRUCTURE SUBJECTS=id REPEATED_MEASURES=time COVARIANCE_TYPE=COMPOUND_SYMMETRY
/FIELDS TARGET=TransDaily TRIALS=NONE OFFSET=NONE
/TARGET_OPTIONS DISTRIBUTION=BINOMIAL LINK=LOGIT
/FIXED EFFECTS=Gender time USE_INTERCEPT=TRUE
/BUILD_OPTIONS TARGET_CATEGORY_ORDER=DESCENDING INPUTS_CATEGORY_ORDER=DESCENDING
MAX_ITERATIONS=100 CONFIDENCE_LEVEL=95 DF_METHOD=RESIDUAL COVB=ROBUST PCONVERGE=0.000001(ABSOLUTE)
SCORING=0 SINGULAR=0.000000000001
/EMMEANS_OPTIONS SCALE=ORIGINAL PADJUST=LSD.
*Generalized Linear Mixed Models. Model 2.2
GENLINMIXED
/DATA_STRUCTURE SUBJECTS=id REPEATED_MEASURES=time COVARIANCE_TYPE=AR1
/FIELDS TARGET=TransDaily TRIALS=NONE OFFSET=NONE
/TARGET_OPTIONS DISTRIBUTION=BINOMIAL LINK=LOGIT
/FIXED EFFECTS=time USE_INTERCEPT=TRUE
/RANDOM USE_INTERCEPT=TRUE SUBJECTS=id COVARIANCE_TYPE=VARIANCE_COMPONENTS
/BUILD_OPTIONS TARGET_CATEGORY_ORDER=DESCENDING INPUTS_CATEGORY_ORDER=DESCENDING
MAX_ITERATIONS=100 CONFIDENCE_LEVEL=95 DF_METHOD=RESIDUAL COVB=ROBUST PCONVERGE=0.000001(ABSOLUTE)
SCORING=0 SINGULAR=0.000000000001
/EMMEANS_OPTIONS SCALE=ORIGINAL PADJUST=LSD.
*Generalized Linear Mixed Models. Model 2.3.
GENLINMIXED
/DATA_STRUCTURE SUBJECTS=id REPEATED_MEASURES=time COVARIANCE_TYPE=AR1
/FIELDS TARGET=TransDaily TRIALS=NONE OFFSET=NONE
/TARGET_OPTIONS DISTRIBUTION=BINOMIAL LINK=LOGIT
/FIXED EFFECTS=time Gender SplitForgivingness Gender*time SplitForgivingness*time
USE_INTERCEPT=TRUE
/RANDOM USE_INTERCEPT=TRUE SUBJECTS=id COVARIANCE_TYPE=VARIANCE_COMPONENTS
/BUILD_OPTIONS TARGET_CATEGORY_ORDER=DESCENDING INPUTS_CATEGORY_ORDER=DESCENDING
MAX_ITERATIONS=100 CONFIDENCE_LEVEL=95 DF_METHOD=RESIDUAL COVB=ROBUST PCONVERGE=0.000001(ABSOLUTE)
SCORING=0 SINGULAR=0.000000000001
/EMMEANS_OPTIONS SCALE=ORIGINAL PADJUST=LSD.
Auf welche Werte sollte ich für die Interpretation eingehen?