Scroll

# π‘ FAQ Weighting

Follow

#### Definition

The process of weighting consists in changing the weight of the interviews to correct sampling errors.

#### How to create a weighting ?

You can have a look at the π¬  or the π‘

#### Can I use a numeric variable as weight ?

Yes, it's possible.

You have imported your dataset and you have already a weight variable you want to use in your tables

You just have to select the numeric questions and set it as initial weight (Apply a weighting). Or you want to apply multiple weights  So, it's possible the weighting has not been calculated with askia analyse .

The only requirement is the weights mean must be equal to 1.

#### Can I show weighted and unweighted base on my table?

Yes , you can fully customize the calculations (to know more about π showing weighted and unweighted base)

#### Where can I find the weighting's report?

The report is generated in the survey.dat directory

`Check the option in Analyse/Tools/Options/Weighting => Write a report after each weighting.`

#### How i can measure the weighting efficiency  ?

The weighting efficiency is an indication of the amount of skewing that had to be done to get the weights to converge; the closer this figure is to 100%, the less skewing needed to be done.

You'll find it into the Weighting's report.

To know more about your sample reliability , see  πweighting efficiency  article

#### My weighting does not converge...

A weighting convergence error can occur for a number of reasons:

•
• when your weighting scheme falls outside the minimum or maximum bounds set in the weighting options.
• In order to converge, the weighting algorithm needs to iterate more than is allowed by your settings.
• You are attempting to weight a grouping to a target which is impossible e.g. the grouping has zero counts and you are weighting it > 0
• Less common, the weighting never actually converges beyond a certain number of decimal places accuracy. For this, you can reduce the accuracy setting

1. Create a variable by weighting

Check the 'weight'  mean  (must be equal to 1)

The maximum value must be unser the maximum weight

2. In the weighting's report. Look if there is any incoherency in the targets settled.

3. π‘ Modify the options

4. if the above 3 steps  doesn't solve your problem

Try to remove 1 variable or to group responses, in order to set reachable targets