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
I am running a bootstrap analysis on my model, which runs fine without bootstrapping.
There are no NAs in my data.
But, when bootstrapping, I receive the following error with certain combination of input data:
Error in Path[k1, k2] <- path_lm$coef[-1, 1] :
number of items to replace is not a multiple of replacement length
Now I was thinking this might have to do with errors in the lm-function, from which there is no coefficient to be passed on to Path[k1, k2]. But when checking simply all combinations of linear model correlations "by hand", I can find no combinations of input data that result in any error.
Have you encountered this before? Is there a simple solution or workaround? If it makes stuff easier, I could share my data and code by email.
Thanks for your time! :-)
Kasper
The text was updated successfully, but these errors were encountered:
Dear Gaston et al.,
I am running a bootstrap analysis on my model, which runs fine without bootstrapping.
There are no NAs in my data.
But, when bootstrapping, I receive the following error with certain combination of input data:
Error in Path[k1, k2] <- path_lm$coef[-1, 1] :
number of items to replace is not a multiple of replacement length
Now I was thinking this might have to do with errors in the lm-function, from which there is no coefficient to be passed on to Path[k1, k2]. But when checking simply all combinations of linear model correlations "by hand", I can find no combinations of input data that result in any error.
Have you encountered this before? Is there a simple solution or workaround? If it makes stuff easier, I could share my data and code by email.
Thanks for your time! :-)
Kasper
The text was updated successfully, but these errors were encountered: