Too few observations

This forum is closed, and read-only.
Locked
hanjia
PLS Junior User
Posts: 1
Joined: Tue Oct 23, 2012 3:40 pm
Real name and title:

Too few observations

Post by hanjia »

Hi all,

I received an error message when running the bootstrapping. It says "An error occurred during the outside estimation. Maybe there are too few observations". The data has been validated. It's ok.
My dataset contains 1688 records, so I set the number of cases to 1688, and samples to 2000.

Any suggestions about possible causes for the issue? Thanks in advance!

Best,
Han
Han Jia
User avatar
Hengkov
PLS Super-Expert
Posts: 1599
Joined: Sun Apr 24, 2011 10:13 am
Real name and title: Hengky Latan
Location: AMQ, Indonesia
Contact:

Post by Hengkov »

Hi,
This problem show because you have many latent variable with single. Indicator. According to Wold state PLS need many indicator for consistent at large ( > 3). Diamantopoulos et al. (2012) provide rule of thumb for used single or multi-items (check it).

Regards,
Hengky
User avatar
Hengkov
PLS Super-Expert
Posts: 1599
Joined: Sun Apr 24, 2011 10:13 am
Real name and title: Hengky Latan
Location: AMQ, Indonesia
Contact:

Post by Hengkov »

Hi,
This problem show because you have many latent variable with single indicator. According to Wold state PLS need many indicator for consistent at large ( > 3). Diamantopoulos et al. (2012) provide rule of thumb for used single or multi-items (check it).

Regards,
Hengky
Locked