Skip to main content

New answers tagged

1 vote

Why are 1/SE or 1/variance commonly used as weights in regressions?

To understand this precisely, we can't use SE and $\sigma^2$ interchangeably. One is the property of the analysis, the other is a property of the data and both involve assumptions about the data ...
AdamO's user avatar
  • 63.1k
5 votes
Accepted

Why are 1/SE or 1/variance commonly used as weights in regressions?

You are asking about what is called "weighted least squares". The idea is that if for some $X_i$ values (values of the independent variable) your observations show more variation in the ...
BenP's user avatar
  • 1,324
2 votes
Accepted

What is the R Equivalent of this Stata Survey Weighting Code?

You've got the regular expression for the weights wrong. The example "wt[1-9]+" in the help page already matches any name starting with wt then a digit ...
Thomas Lumley's user avatar

Top 50 recent answers are included