minimum and maximum appropriate number for the samples in estimation of bootstrapping
minimum and maximum appropriate number for the samples in estimation of bootstrapping
What is the minimum and maximum appropriate number for the samples in estimation of bootstrapping when we want to conduct confirmatory factor analysis using smart PLS2?
-
- SmartPLS Developer
- Posts: 1284
- Joined: Tue Mar 28, 2006 11:09 am
- Real name and title: Dr. Jan-Michael Becker
Re: minimum and maximum appropriate number for the samples in estimation of bootstrapping
For the bootstrap samples the usual recommendation is the use at least 500 (for an initial screening, because it usually gives already quite good results) and 5,000 for the final model. Generally, the more the better (i.e., the more precise are your estimates of the standard error and the confidence intervals).
Personally, I would say that beyond 5,000 there is not much to gain, but you could also use 10,000 if your system memory allows that.
Personally, I would say that beyond 5,000 there is not much to gain, but you could also use 10,000 if your system memory allows that.
Dr. Jan-Michael Becker, BI Norwegian Business School, SmartPLS Developer
Researchgate: https://www.researchgate.net/profile/Jan_Michael_Becker
GoogleScholar: http://scholar.google.de/citations?user ... AAAJ&hl=de
Researchgate: https://www.researchgate.net/profile/Jan_Michael_Becker
GoogleScholar: http://scholar.google.de/citations?user ... AAAJ&hl=de
Re: minimum and maximum appropriate number for the samples in estimation of bootstrapping
thanks for your reply
I used SmartPls2 and its default value was 200 samples. I did not change it. Is my confirmatory factor analysis wrong?
I used SmartPls2 and its default value was 200 samples. I did not change it. Is my confirmatory factor analysis wrong?
-
- SmartPLS Developer
- Posts: 1284
- Joined: Tue Mar 28, 2006 11:09 am
- Real name and title: Dr. Jan-Michael Becker
Re: minimum and maximum appropriate number for the samples in estimation of bootstrapping
It is not wrong, but it might not be very precise. It is especially a problem for effects that are on the edge of being significant or not. If you are able to re-run it, I would go with a larger number.
Dr. Jan-Michael Becker, BI Norwegian Business School, SmartPLS Developer
Researchgate: https://www.researchgate.net/profile/Jan_Michael_Becker
GoogleScholar: http://scholar.google.de/citations?user ... AAAJ&hl=de
Researchgate: https://www.researchgate.net/profile/Jan_Michael_Becker
GoogleScholar: http://scholar.google.de/citations?user ... AAAJ&hl=de