I am working on smartPLS, and got a bit confused, is it necessary to chekc the outliers and normality of data before using smartPLS, as smartpls uses bootstrapping...and what if the data is not normally distributed?
Is it must to check the the normality and outliers before using smartPLS ? -
Is it must to check the the normality and outliers before using smartPLS ?
Checking for normality is not needed in SmartPLS because SmartPLS is not considering the data distribution i.e. SmartPLS also can be used for data which is not normally distributed. However, there are many researchers also performing the normality test to determine whether their data is normally distributed or not.
If there are outliers in your data, common approach is to remove them from the data set, performing some transformations / adjustments on the outliers, using different models / methods which are insensitive to outliers etc. Alternatively, you can perform further analyses e.g. running additional analyses with & without the outliers & document down how the results changed in your report findings.
- Badges
- Science topic