Electronic Letters to:
|
|
eLetters: Electronic letters published:
-
![[Read eLetter]](/icons/misc/sectionDOWN.gif)
Re: Can social factors explain sex differences in insomnia? Finding from a national survey in Taiwan
- Wenbin Liang (7 June 2005)
|
|
|||
|
Wenbin Liang, taking master of public health
Send letter to journal:
wenbin.liang{at}student.curtin.edu.au Wenbin Liang
|
Dear Editor, In the article, it is presented that all the people who are over age 15 in the sampled households, are taking as subjects. It means that in married families both the husband and the wife or even their children who share similar sleep environments, are included in the study, as to say, subjects are correlated, 'random sampling' need to be reconsidered. While regression, t-test, one-way ANOVA all require random sampling. Moreover if the same family is reviewed by the same interviewer (who is whether blinded from the study unknown), obviously there would create certain bias. Furthermore, no adjust R-square for the regression models is given, it's impossible for a reader to evaluate the 'fitness'/goodness of the regression models (the proportion of the variance of the dependent variable explained by the regression models), not to speak the effect of one of the independent variable. In addition, there is no information about the regression coefficients for the independent variables are standardized or not standardized, little comparison can be done between the independent variables. |
|||
