"Undertaking four separate statistical tests did not permit a general comparison between treatment groups across pregnancy. Therefore, it cannot be concluded that there was a significant difference between treatments in gestational weight gain across pregnancy (c is false)."
So if the authors had only performed one test at 40 weeks, we would have been allowed to conclude a significant difference, but because we have three additional such tests, even though the closest two were also statistically significant on their own, we cannot? That is, the additional tests actually reduced the confidence we can have in the conclusion?
I can understand that the independent samples t test was not the optimal choice, but this has me puzzled.
Competing interests:
No competing interests
25 January 2013
Lennert Veerman
Senior Research Fellow
The University of Queensland, School of Population Health
Rapid Response:
Re: Analysis of longitudinal studies
"Undertaking four separate statistical tests did not permit a general comparison between treatment groups across pregnancy. Therefore, it cannot be concluded that there was a significant difference between treatments in gestational weight gain across pregnancy (c is false)."
So if the authors had only performed one test at 40 weeks, we would have been allowed to conclude a significant difference, but because we have three additional such tests, even though the closest two were also statistically significant on their own, we cannot? That is, the additional tests actually reduced the confidence we can have in the conclusion?
I can understand that the independent samples t test was not the optimal choice, but this has me puzzled.
Competing interests: No competing interests