Increasing the number of replication from default(50) to 5000

1 reply [Last post]
Ryan's picture
Joined: 02/08/2014

Dear Mike,

When I call summary (random2a, R=5000), z-values and standard errors of some estimates are significantly changed. The estimates and goodness-of-fit indices remain the same.

I didn't try (R=10000), as "R=5000" already took 7 hours to finish;)

However, if the number of replications dramatically influences the z-values and std.errors, are there any criteria for choosing one result for reporting?



Mike Cheung's picture
Joined: 10/08/2009
Dear Ryan, In my previous

Dear Ryan,

In my previous replies, I have indicated that the likelihood-based CI (intervals.type="LB") is preferred. The parametric bootstrap SE is provided only for those who need the SE or the VCOV of the parameter estimates.