risk items innovation sample waves 6 and 7
I am computing test-retest correlations to assess the temporal stability of risk preference using several measures of risk attitude/risky choice using USoc data (and other panels) and I think I may have detected an issue with the risk data from wave 7.
First, I find that the test-retest correlation of items "f_trriska","f_trhlrisk","f_trflrisk" and the equivalent ones in "g_trriska","g_trhlrisk","g_trflrisk" are negative and substantial (~.45). This is not to be expected after a 1 year interval (i'm conducting a meta-analysis using several household panels with similar data and this would be a first). Second, while, as expected, the items in wave 6 are negatively correlated with age and sex (as is known from the literature and other datasets), the items in wave 7 are positively correlated with age and sex. I've checked an this is true for the spss, state, and tab versions of the data.
Second, I am looking for data referring to Domain-Specific Risk-Taking Scale (DOSPERT) Questions that were supposedly collected in waves 6 and 7 (see Table 60 of Galizzi et al; http://eprints.lse.ac.uk/67554/1/Galizzi_temporal_stability.pdf) but was not able to locate this items. Could you perhaps help with this as well?
Any help would be much appreciated!
Updated by Stephanie Auty about 2 years ago
- Status changed from New to In Progress
- % Done changed from 0 to 10
- Private changed from Yes to No
Many thanks for your enquiry. The Understanding Society team is looking into it and we will get back to you as soon as we can.
Stephanie Auty - Understanding Society User Support Officer
Updated by Stephanie Auty almost 2 years ago
- Category set to Data inconsistency
- Status changed from In Progress to Feedback
- Assignee set to Rui Mata
- Target version set to X IP
- % Done changed from 10 to 80
The fieldwork agency changed between IP6 and IP7 and as a result in IP6 respondents entered a number from 0-10 and in IP7 they clicked on a radio button, but we are not sure if that contributed to the problem. You could contact Matteo Galizzi (at LSE) who is the author of this experiment and might be willing to share more insights based on his own analyses.