2side SDA Test Data September 4, 2001 true CODEBOOK SDA Test Data 1,113 Cases Introduction The SDA test data file is extracted from the 1986 Race and Politics Survey, a random-digit telephone survey of residents of the San Francisco-Oakland metropolitan area. The Survey Research Center of the University of California, Berkeley, conducted the survey from August through October 1986, using the CASES system for computer-assisted telephone interviewing. Interviews were completed with 1,113 persons, and the response rate was 68.1 percent. Case Identification CASEID: Case ID (numeric) 1,113 cases (Range of valid codes: 1,003-5,855) Data type: numeric Record/columns: 1/5-10 charid: Character version of CASEID This version of the CASEID is a character variable, instead of a numeric variable. 1,113 cases Data type: character Record/columns: 1/5-10 Attitudes About Government Spending spend: Military spending This country faces many problems, none of which can be solved easily or inexpensively. I'm going to name some of these problems. For each one, please tell me whether you think we're spending too much money on them, too little money, or about the right amount. First, how about spending on the military, armaments, and defense? % N VALUE LABEL 59.7 653 1 Too much 34.9 382 3 About right 5.4 59 5 Too little 17 8 Don't know 2 9 Refused ----- ----- 100.0 1,113 cases Data type: numeric Missing-data codes: 8,9 Record/column: 1/40 spend2: Urban problems spending How about spending on solving the problems of the big cities? % N VALUE LABEL 6.6 71 1 Too much 27.2 291 3 About right 66.1 706 5 Too little 41 8 Don't know 4 9 Refused ----- ----- 100.0 1,113 cases Data type: numeric Missing-data codes: 8,9 Record/column: 1/44 spend3: Crime reduction spending How about spending on halting the rising crime rate? % N VALUE LABEL 3.7 40 1 Too much 26.0 281 3 About right 70.3 758 5 Too little 31 8 Don't know 3 9 Refused ----- ----- 100.0 1,113 cases Data type: numeric Missing-data codes: 8,9 Record/column: 1/48 spend4: Welfare spending How about spending on welfare or public assistance for poor people? % N VALUE LABEL 19.6 212 1 Too much 32.5 352 3 About right 47.9 518 5 Too little 29 8 Don't know 2 9 Refused ----- ----- 100.0 1,113 cases Data type: numeric Missing-data codes: 8,9 Record/column: 1/52 Experiment on Equal Opportunity There were two versions of the question 'eqopp'. The content of the random number variable 'eqrandom' indicates which version of 'eqopp' each respondent was asked. eqopp: Eq opp for Blks/Wmen not job of govt While equal opportunity for [black and minorities / women] to succeed is important, it's not really the government's job to guarantee it. Would you say that you basically agree or basically disagree with that statement? (The wording of this item depends on the random variable 'eqrandom'.) % N VALUE LABEL 48.3 525 1 Agree 51.7 562 5 Disagree 18 8 Don't know 8 9 Refused ----- ----- 100.0 1,113 cases Data type: numeric Missing-data codes: 8,9 Record/column: 1/56 eqrandom: Random number variable for eqopp The values of this variable were generated at random. If this variable equals 1, eqopp asks about 'blacks and minorities'. If this variable equals 2, eqopp asks about 'women'. % N VALUE LABEL 49.1 547 1 Blacks 50.9 566 2 Women ----- ----- 100.0 1,113 cases Data type: numeric Record/column: 1/60 Political Ideology and Party ideo: Political ideology in general In general, when it comes to politics, do you usually think of yourself as a liberal, a conservative, a moderate, or what? % N VALUE LABEL 35.3 360 1 Liberal 27.1 276 3 Conservative 37.6 383 5 Moderate 59 7 Never think of myself in those terms 20 8 Don't know 15 9 Refused ----- ----- 100.0 1,113 cases Data type: numeric Maximum code defined as valid: 5 Missing-data codes: 8,9 Record/column: 1/64 party: Party identification Generally speaking, do you usually think of yourself as a Republican, a Democrat, an Independent, or what? % N VALUE LABEL 26.0 265 1 Republican 45.1 460 3 Democrat 28.9 295 5 Independent 64 6 No preference 9 7 Other 3 8 Don't know 17 9 Refused ----- ----- 100.0 1,113 cases Data type: numeric Maximum code defined as valid: 5 Missing-data codes: 8,9 Record/column: 1/68 Demographic Variables age: Age of respondent in years How old were you on your last birthday? 1,113 cases (Range of valid codes: 18-97) Data type: numeric Missing-data code: 99 Record/columns: 1/3-4 educ: Education in years of schooling What is the highest grade of school or year of college you COMPLETED? % N VALUE LABEL 0.2 2 0 0.3 3 2 0.2 2 3 0.4 4 4 0.4 4 5 0.4 4 6 0.3 3 7 1.2 13 8 thru 8th 1.0 11 9 1.5 17 10 1.1 12 11 19.7 217 12 HS grad 8.4 92 13 16.8 185 14 7.7 85 15 21.0 231 16 Col grad 19.5 215 17 13 99 Refused ----- ----- 100.0 1,113 cases Data type: numeric Maximum code defined as valid: 17 Missing-data code: 99 Record/columns: 1/19-20 employed: Employment status We'd like to know if you are now employed full-time, employed part-time, on temporary layoff, unemployed and looking for work, retired, a student, (a housewife), or what? IF R ASKS: By full-time, we mean 35 or more hours per week. % N VALUE LABEL 59.8 658 10 Fulltime 9.0 99 15 Parttime 0.5 6 20 Laidoff 2.8 31 40 Unemployed 11.5 126 50 Retired 0.6 7 60 Permanently disabled 0.5 6 65 Temporarily disabled 6.4 70 70 Keep house 8.5 93 80 Student 0.4 4 90 Other 13 99 Refused ----- ----- 100.0 1,113 cases Data type: numeric Missing-data code: 99 Record/columns: 1/23-24 gender: Gender of respondent CODE OR ASK AS NEEDED: What sex are you? % N VALUE LABEL 46.5 517 1 Male 53.5 596 2 Female ----- ----- 100.0 1,113 cases Data type: numeric Record/column: 1/28 income: Income of household (This is the income summary variable, giving household income range, determined from a series of questions about whether income is above or below certain figures. The range '15-25' means, for example, that household income is above $15,000 but less than $25,000.) % N VALUE LABEL 13.3 137 1 < 15 2.1 22 2 15 13.1 135 3 15- 25 1.7 17 4 25 15.0 154 5 25- 35 4.0 41 6 35 7.8 80 7 35- 40 1.9 20 8 40 11.7 120 9 40- 50 2.0 21 10 50 27.5 283 11 50+ 5 81 1 82 5 83 7 88 Don't know 1 91 13 92 1 94 50 99 Refused ----- ----- 100.0 1,113 cases Data type: numeric Maximum code defined as valid: 11 Missing-data codes: 88,99 Record/columns: 1/31-32 marital: Marital status Are you now married, or are you living with someone in a marriage-like relationship, widowed, divorced, or have you never been married? % N VALUE LABEL 44.2 486 1 Married 7.1 78 2 Like married 6.6 73 3 Widowed 3.4 37 4 Separated 12.6 138 5 Divorced 26.1 287 6 Never married 1 8 Don't know 13 9 Refused ----- ----- 100.0 1,113 cases Data type: numeric Missing-data codes: 8,9 Record/column: 1/36 race: Race or ethnic group What race or ethnic group do you consider yourself? (If necessary: We mean white, black, Asian, Mexican-American Native American, or what?) % N VALUE LABEL 71.6 794 1 White 13.4 149 2 Black 5.5 61 3 Hispanic 0.4 4 4 Native American 6.6 73 5 Asian 1.4 16 6 Filipino 0.5 5 7 Volunteered: Jewish 0.6 7 8 Other 4 99 Refused ----- ----- 100.0 1,113 cases Data type: numeric Missing-data codes: 88,99 Record/columns: 1/71-72 Weight Variable casewt: Overall sampling weight (Overall sampling weight. This weight adjusts for sampling stratum, number of adults in the selected household, and the number of telephone lines into the selected household. The weight is scaled so that the total number of weighted cases equals the number of unweighted cases -- 1113.) % N VALUE LABEL 0.2 2 0.107 0.4 4 0.160 0.2 2 0.214 12.1 135 0.321 0.4 5 0.428 1.0 11 0.481 34.6 385 0.641 0.3 3 0.802 4.7 52 0.962 0.1 1 1.069 0.1 1 1.123 34.9 388 1.283 0.4 5 1.604 7.5 84 1.924 2.9 32 2.566 0.3 3 3.207 ----- ----- 100.0 1,113 cases Data type: numeric Decimals: 3 Record/columns: 1/11-16 Sample Design The Race and Politics survey was a random-digit telephone survey of English-speaking persons 18 years of age or older living in the five- county San Francisco-Oakland Bay Area. Operationally, the sampling frame include all telephone numbers within the 415 area code. In 1986 this area code included the counties of San Francisco, Alameda, Marin, Contra Costa, and San Mateo. Telephone numbers identified on the Bellcore tape as being from the cities of Oakland and Richmond were sampled at twice the rate as telephone numbers in the rest of the Bay Area. Those cities have a relatively high proportion of black residents, and the purpose of oversampling those cities was to increase the proportion of blacks in the sample. The sampling weight adjusts for this oversampling of those two cities. Within each selected household all adults over the age of 18 were enumerated. One of the enumerated adults was selected at random to be interviewed for this study. Many calls were made in order to interview the one selected person in each sampled household. No substitutions were allowed. Interviews were completed with 1,113 persons. The response rate was 68.1 percent. Calculation of Weights The data file includes a variable 'casewt', which adjusts for unequal probabilities of selection between respondents. There are three components to this weight variable: (1) Since residents of Oakland and Richmond were oversampled by a factor of two, the weight for respondents from those cities included a factor to adjust for that oversampling. If S is the stratum factor, S is .5 for respondents from Oakland and Richmond; otherwise, S is 1. (2) Since only one adult was selected from each household, the probability of selection of each adult is 1/P, where P is the number of adult persons in the household. The corresponding weight factor for each respondent, consequently, is P. (3) Those households with more than one telephone line have a greater chance of being selected. The probability is proportional to T, where T is the number of lines. The corresponding weight factor is 1/T. The sampling weight for each case on the data file (casewt) is k*S*P/T, where k is a constant to scale the weight so that the weighted number of cases equals the unweighted number of cases (1,113).