All are true about randomised controlled trial except? (AIPG 09)
|A|| Sample size depends upon hypothesis|
|B||Dropouts are excluded from analysis|
|C|| Interviewers bias can be eliminated by double blinding|
|D|| Groups are comparable on baseline characterstics.|
Sample size in a RCT depends upon :
- The difference in the response rates to be detected (Effect size).
- An estimate of the response rate in one of the groups
- Level of statistical significance (alpha)
- The value of the power desired (1-beta)
- Whether the hypothesis is one sided or two sided
- Attrition rate
Please remember, in RCT the sample size depends upon hypothesis whether it is one tailed or two tailed. Drop outs are never excluded from the analysis, in fact Intention to treat analysis is done whereby the drop outs are included in the analysis.
Groups are comparable on baseline characteristics – this may be a secondary function of randomization however this is not ensured by randomization.
Double blinding is done wherein both the participant as well as the researcher is unaware of the treatment group assigned – this eliminates interviewers bias.
Drop outs are not excluded from the analysis but instead intention to treat analysis is done.