You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
the default code for the J-PAL_Power_by_simulation_clusters.R script yields 0 for power and ICC. I've tried modifying input parameters in attempt to increase the power (lowered effect size, increased cluster size, decreased number of clusters) and the code results also yielded 0.
Is there something I should adjust prior to running the script?
Thank you!
Results:
"""If the treatment effect and the assumption about the disribution of the error is true, the study with 200 of size 500 will detect the true treatment effect of 0.25 with probability, 0 in a two -sided test. Hence the power of the study is 0 .The calculated ICC is 0"""
The text was updated successfully, but these errors were encountered:
Hi there,
the default code for the
J-PAL_Power_by_simulation_clusters.R
script yields 0 for power and ICC. I've tried modifying input parameters in attempt to increase the power (lowered effect size, increased cluster size, decreased number of clusters) and the code results also yielded 0.Is there something I should adjust prior to running the script?
Thank you!
Results:
"""If the treatment effect and the assumption about the disribution of the error is true, the study with 200 of size 500 will detect the true treatment effect of 0.25 with probability, 0 in a two -sided test. Hence the power of the study is 0 .The calculated ICC is 0"""
The text was updated successfully, but these errors were encountered: