@MarionKoopmans As this is a large randomized cluster trial (600 randomized villages), the study disign should be robust against pre-test differences in villages (assuming proper randomization). https://t.co/jMTwuw0EDo
@aliettejonkers @MarionKoopmans Alleen als de randomisatie fout is gegaan, en daar zie ik geen aanleiding toe: https://t.co/jMTwuw0EDo
Alex Mitchell talked about baseline testing in cluster trials: https://t.co/41puOppAKn
@GuyProchilo Here's an example where selection bias may be present and therefore a test maybe useful https://t.co/9QNQ1mYjMD
"We think that it may be acceptable to present baseline statistical tests for cluster trials that recruit participants after randomisation to assess whether there is evidence of selection bias." https://t.co/oyoorgDyi5
Hey #statstwitter what do you think of this, titled: “Baseline testing in cluster randomised controlled trials: should this be done?”
He #statstwitter what do you think of this, titled: “Baseline testing in cluster randomised controlled trials: should this be done?”
I don't know where to start on this but let me hold back. Perhaps sometimes we just want to provoke debate or attention. https://t.co/vU1vhHKJP2