Associations between early predictors and early dissolution (before children were 8 years old) and late dissolutions (when children were between 8 and 19 years) were compared using
multinomial logistic regression analyses.
The association between parental alcohol consumption at age 4 years (using linear and binary exposures) and developmental trajectories of offspring conduct problems across all 6 timepoints (i.e., EOP, AO, CL, and Low as the reference group) were examined
using multinomial logistic regression.
To check for reverse causation, that depressive symptoms may affect subsequent sugar intake from sweet food / beverages, linear regression models of 5 - year change and
multinomial logistic regression for change groups were fitted for each cycle, from phases 3 to 5, 5 to 7 and 7 to 9, with CMD at phases 3, 5, 7 respectively, and for change from phase 7 to 9 with depression at phase 7.
Multivariate logistic regression analyses examined parity progression by birth order,
while multinomial logistic regression was used to identify associations between sex composition and use of permanent, temporary and traditional contraceptive methods.
Moreover,
multinomial logistic regressions revealed a profile of children at risk of developing high anxiety symptoms (i.e., high group), characterized by sociofamily adversity, inattention, and low prosociality in the classroom.
Multinomial logistic regression models suggested that families that experienced significant declines in income were more likely to persistently participate and initiate participation than to never participate.
To assess the impact of condition at intake on the outcome for the senior animals,
a multinomial logistic regression was performed.
Multinomial logistic regression analysis for associations between T1 variables and early versus late dissolutions
In
the multinomial logistic regressions the cognition, social competence, and temperament variables are statistical predictors of trajectory membership.
In the second part of the analyses,
multinomial logistic regression models were used to examine which variables2 would discriminate between trajectories of social anxiety (Duchesne et al. 2010).
Multinomial Logistic Regression Model Predicting Family Patterns of Support Given to Adult Offspring
Multinomial logistic regression was used to ascertain recurrence risks of the pure and comorbid conditions in the siblings as predicted by the status of the cases.