Deriving the persontality traits for Understanding Soc
I want to know the method for deriving the Big5 components you have calculated. The brief explanation provided talks about taking an average, but given all components are weighted equally, the numbers I see do not tally with an average. I want to use such derived variables in ther earlier BHPS panel.
Updated by Gundi Knies over 5 years ago
- Category set to Derived variables
- Status changed from New to In Progress
- Assignee set to Tim Hinks
- Target version set to BHPS
- % Done changed from 0 to 80
sorry for the delay in getting back to you.
Each of the 5 trait scores is derived from the responses to three questions. If the response to no more than one of the three component questions was missing, we computed the mean value of the other two items and used that as an impute. Then, we summed the three items and divided over three, and rounded to the nearest digit. Hence, the value represents the average value scored on this trait. The same strategy can be applied to the BHPS wave 15 data for a harmonised measure.