Diff for "FAQ/VarMSE" - CBU statistics Wiki
location: Diff for "FAQ/VarMSE"
Differences between revisions 4 and 6 (spanning 2 versions)
Revision 4 as of 2009-03-03 16:14:26
Size: 835
Editor: PeterWatson
Comment:
Revision 6 as of 2015-08-07 10:52:55
Size: 816
Editor: PeterWatson
Comment:
Deletions are marked like this. Additions are marked like this.
Line 5: Line 5:
For example let us suppose the data is divided by 1000 and a mean square error for this transformed data is found to be equal to 0.0125. The mean square error of the original data is, therefore, equal to $$\mbox{1000}^text{2}$$ times the mean square error of the transformed data = $$\mbox{10}^text{6}$$ x 0.0125 = 12500. For example let us suppose the data is divided by 1000 and a mean square error for this transformed data is found to be equal to 0.0125. The mean square error of the original data is, therefore, equal to $$1000}^2 ^$$ times the mean square error of the transformed data
= $$10^6 ^$$ x 0.0125 = 12500.

What is the value of the error variance for raw data using that of its scalar transformed data?

It is sometimes necessary to quote the error variance, or mean square error of scalar transformed responses, such as reaction times, that have very large or small values. In this case the mean square error for the raw data may be obtained from the mean square error for the transformed data by simply multiplying the transformed data's mean square error by the square of the inverse transform.

For example let us suppose the data is divided by 1000 and a mean square error for this transformed data is found to be equal to 0.0125. The mean square error of the original data is, therefore, equal to $$1000}2 $$ times the mean square error of the transformed data = $$106 $$ x 0.0125 = 12500.

None: FAQ/VarMSE (last edited 2015-08-07 10:53:18 by PeterWatson)