Urban/Rural Indicator in GSS Cycle 18

Question

I have a Professor here, who is using the GSS Cycle 18 – Victimization (2004), in a course with second year students. The students are performing various cross-tabulations and one of the independent variables they are being asked to include is the “Urban/Rural Indicator” (urind). Curiously, apart from “Urban” and “Rural”, another response option is for “Prince Edward Island”.

I believe this has to do with the sample, but the Professor was looking for an explanation as to why the PEI respondents were not included in one of the Urban or Rural responses. I have searched through the User’s Guide and other documentation for a rationale for this, but wasn’t able to locate anything.

Would there be some other documentation or explanation that could help clear this up?

Answer

"Here are some details for the inquiry about the specific variable in the PUMF for Rural/Urban. There are no CMAs in PEI and CMA is what is used to determine the urban-rural indicators.

Previous GSS PUMFs have sometimes included a rural/urban indicator called URIND (1=Urban, 2=Rural, 3=PEI). This derived variable is based on the UA_RA_TYPE geocodes (e.g. Cycle14).

For cycle 17 onwards , instead of URIND, a new rural/urban indicator (LUC_RST) was included as follows: The new variable is based on GEO_SAC_TYPE. The categories "CMA, CA tracted, CA untracted" are grouped into a new category “Larger Urban Centres”, and "Strong MIZ, Moderate MIZ, Weak MIZ and No MIZ" are grouped into a new category called “Rural and Small Town”. PEI is kept as a separate category.

LUC_RST
1 Larger Urban Centres (CMA/CA)
2 Rural and Small Town (non-CMA/CA)
3 PEI "