Statwing allows users to apply weights, so that if certain types of survey respondents are under- or over-represented, Statwing can be told that one row of data counts for more or less than one case. To enable weights, your data must have a column of weights (see "Additional Notes" below for more details).
Unless you uncheck that box, all future analyses will be weighted (though if you have a specific analysis that you’d like to not include weights, you can remove the weighting from that individual card):
Weighting can also be used if each row of your data represents several cases. For example, if you have a table that looks like this:
In that case you could upload the data, indicate that “Count” is the column to weight by, and Statwing will produce the same results as if you had loaded a larger table with 45 rows of grey cats, 5 rows of black cats, etc.
- Weighting is presently not available for regression analysis. Let us know if this is an issue and we'll prioritize the implementation of regression weighting.
- Statwing uses the same type of weighting as SPSS. Like SPSS, if you're using weights for a survey you should normalize your weights such that they have a mean of one (see below for more details).
- In order to use weights there must be a column of data where the weights have been calculated. Learn how to calculate weights here. Once you've calculated the appropriate weights per group, you can apply them to your data in Statwing by clicking "Create" to make a new variable, then using the "Variable by Filters" interface (or you can precalculate the weights in Excel or other software before uploading).