CODEBOOK: socsurvey
==============================================================

All values are SIMULATED. No figure describes any real
person, household, city, or country.
Appendix B explains how each dataset was built and what it is
for.

Categorical variables are stored as integer codes; the
mapping is given below. Sentinel missing codes (97, 98,
99) are left in place, NOT converted to NA -- recoding
them is an exercise in several chapters.

Rows: 477    Columns: 17
--------------------------------------------------------------

rid              Respondent identifier  [Integer]

age              Age in years  [Numeric]

gender           Gender  [Coded]
                   1 = Woman; 2 = Man; 3 = Another gender

educ             Highest level completed  [Coded]
                   1 = Less than secondary; 2 = Secondary; 3 = College; 4 = Bachelor's; 5 = Graduate

income           Annual income, simulated dollars  [Integer]
                   ; top-coded

region           Region of residence  [Coded]
                   1 = North; 2 = South; 3 = East; 4 = West; 5 = Central

occupation       Occupational group  [Coded]
                   1 = Sales and service; 2 = Business, finance and administration; 3 = Natural and applied sciences; 4 = Management

ideology         Left--right self-placement  [Coded]
                   0 = Left ... 10 = Right; 98 = Don't know; 99 = Refused

trust_gov        Trust in government  [Coded]
                   0 = None ... 10 = Complete; 98 = Don't know; 99 = Refused

civic1           Civic duty item 1  [Coded]
                   1 = Strongly disagree; 2 = Disagree; 3 = Neither; 4 = Agree; 5 = Strongly agree

civic2           Civic duty item 2  [Coded]
                   1 = Strongly disagree; 2 = Disagree; 3 = Neither; 4 = Agree; 5 = Strongly agree

civic3           Civic duty item 3 \textbf{(reverse-worded)}  [Coded]
                   1 = Strongly disagree; 2 = Disagree; 3 = Neither; 4 = Agree; 5 = Strongly agree

frame            Experimental condition  [Coded]
                   1, 2, 3; randomly assigned. See the section noted in Appendix B

policy_support   Support for the policy  [Numeric]
                   ; 0 = strongly oppose, 10 = strongly support

voted            Voted in the last election  [Coded]
                   0 = No; 1 = Yes

weight           Survey weight  [Numeric]

income_rep       Income as actually reported  [Integer]
                   ; NA where refused. Download only

