To examine heterogeneity of results among studies, tests of interaction were performed using the Cox model.
Tests of interaction hypotheses use data from the Family Transitions Project, a longitudinal study of 7th graders followed for 5 years.
Despite guidelines recommending the use of formal tests of interaction in subgroup analyses in clinical trials, inappropriate subgroup-specific analyses continue.
The analysis is to be done only for the primary outcome, be complemented by statistical tests of interaction, and be corrected for multiple comparisons (Section 2.8.4 GMS TAPS 5).
Tests of interaction by age, black race, family history and current smoking were performed.
For logistic regression tests of interaction in case-control data on the best model from MDR analysis the type I error rate was 0.46 at an alpha rate of 0.05.
Tests of interaction were conducted by including main effects for each FTO polymorphism and gender or race in the logistic regression models, and introducing a multiplicative two-way interaction term for gene by gender or gene by race.
Most commonly, variations in treatment effects between the sexes were examined within a multitude of subgroup analyses and very few studies employed tests of interaction to determine pre-specified subgroup effects.
In these sensitivity analyses we repeated the fully adjusted multivariable associations within the two strata and compared whether they looked similar and computed likelihood ratio tests of interaction between parental BMI and the stratifying characteristic.
Tests of interaction were performed.
No formal tests of interaction were done.
