Version 01 Codebook ------------------- CODEBOOK INTRODUCTION FILE 1987 PILOT STUDY (1987.PN) USER NOTE: This file has been converted to electronic format via OCR scanning. As as result, the user is advised that some errors in character recognition may have resulted within the text. AMERICAN NATIONAL ELECTION STUDIES 1987 PILOT STUDY ICPSR ARCHIVE NUMBER 8713 TABLE OF CONTENTS Note: >>sections in the codebook introduction and codebook appendix can be navigated in the machine-readable files by searching ">>". INTRODUCTORY MATERIALS (file intpil87.cbk) ---------------------- >> 1987 PILOT STUDY DESCRIPTION >> 1987 NES PILOT STUDY DESIGN MEMO >> 1987 PILOT GUIDE TO LOCATION OF VARIABLES >> CODEBOOK INFORMATION CODEBOOK -------- 1987 Pilot Variables 1986 Post Variables APPENDICES (file intpil87.cbk) ---------- >>OPEN-END RESPONSES FOR 1987 Pilot WAVES 1 AND 2 >>OPEN-END 1987 Pilot Direction of Comment >>OPEN-END 1987 Pilot Affective Intensity >>OPEN-END 1987 Pilot Direction of Mention Code >>OPEN-END 1987 Pilot Emotional Intensity and 1987 Pilot Elaboration of Thought Codes >> 1980 CENSUS DEFINITIONS >> NES 1986 PARTY CANDIDATE NOTE >> NES 1986 CANDIDATE MASTER CODE >> NES 1986 IMPORTANT PROBLEMS >> NES 1986 EDUCATION AND OCCUPATION RECODES >> 1980 CENSUS OCCUPATION CODES >> 1980 CENSUS INDUSTRY CODES >> NES 1986 NATIONALITY NOTE >> NES 1986 STATE AND COUNTRY NOTE >> NES 1986 CITIES NOTE >> 1987 PILOT STUDY DESCRIPTION The 1987 Pilot Study, like its predecessors, provides an opportunity for social scientists to refine existing NES measures and develop and test new instrumentation. This Pilot Study carries new measures of foreign policy attitudes, system support, and morality. A significant portion of the study is devoted to experiments in question wording and question order effects. Study Design The Pilot Study can be thought of as a three-wave panel. A subsample of 457 respondents to the 1986 National Election Study were interviewed between May 5 and May 30, 1987; 360 of these people were reinterviewed between June 2 and July 2, 1987. The ICPSR dataset includes variables from the 1986 NES for the 457 Pilot Study cases. To facilitate the testing of the new items, two forms were used in each of the two waves. Study Administration The Survey Research Center at the Institute for Social Research administered the pilot study by Computer Assisted Telephone Interviewing (CATI). Responses to open-ended questions, however, were recorded in pencil in separate booklets, and later coded by the SRC coding section. To facilitate your use of the dataset, we have prepared paper and pencil questionnaires so that the flow of the questioning can be more easily seen. Study Processing Interviewing on the study ended July 2nd, and coding continued for two additional weeks. After the various components of the dataset had been merged together, the study staff scanned the frequencies for each variable. Beyond these very minimal checks, the NES staff has not done any processing of these data. If you discover any problems in the data or encounter difficulty using the data file, please contact me or a member of the project staff so we can assist you and alert other users to the problem. How to Order the 1987 Pilot Study If you are at an institution that is a member of the ICPSR, you should contact your Consortium representative and order this Class IV dataset in the usual manner. If you are not affiliated with an ICPSR member institution, you can also secure the 1987 Pilot Study Data and accompanying documentation from the ICPSR. Contact for details. >> 1987 NES PILOT STUDY DESIGN MEMO TO: Santa Traugott, NES Study Staff SUBJECT: 1987 NES Pilot Study FROM: Steve Heeringa, Sampling Section DATE: 13 July l9B7 The 1987 NES Pilot Study is a reinterview of a probability sample of n=633 of the original 1086 Form A respondents to the 1986 NES post-election survey. (Sample selection was actually restricted to 955 of the 1986 NES Form A respondents who provided a telephone number for recontact). Using an experimental approach that followed ideas first brought to the NES staff in the form of a memo from John Zaller, the Pilot Study sample was disproportionately allocated across five strata of sample respondents. The five strata were defined using 1984 NES quintile ranges for a special voter knowledge and interest index. Based on the 1984 scoring system, an index value was assigned to each of the 1986 NES Form A respondents. Table 1 below describes the distribution, of the 1986 NES Form A respondents to the five voter knowledge strata. (Note: Since the strata are defined on the basis of 1884 quintile ranges, each of the five voter knowledge strata will not necessarily contain exactly 20% of the l986 sample cases). Underlying this stratified sampling approach is a reasoning which says that the Pi1ot Study respondents shou1d bear a characteristic resemb1ance to the 1986 NES respondents or prospectively to the cross-section of respondents who will participate in the l988 NES. If an equal probability sample of 19866 NES respondents is selected for the Pilot Study contact, nonresponse will distort this characteristic representation whenever the response (or observation) probability is correlated with the characterist in of interest. The vote, knowledge index is one such characteristic. Conventionally, adjustments for nonresponse are introduced through post-survey weighting. The procedure involves formation of nonresponse adjustment strata and assignment of case weights which reflect the nonresponse pattern within the strata. Drawing heavily on past experience with the NES Pilot Study series, the current design for the 1987 NES Pilot shifts the nonresponse adjustment born the post-survey period to the stage at which the sample is designed and selected. For the l987 Pilot Study, strata of NES respondents defined by the quintile ranges of the knowledge index for l984 respor,dents were disproportionately sampled. Sampling rates for the five knowledge strata were set inversely proportional to the 1985 Pi1ot study response rate experience. (See Table 1 ) . In theory, if the 19B7 response rate experience is identica1 to that for l985, the l987 Pilot Study data base will emerge from the process with a knowledge index distribution which parallels that of the original 1986 NES data set. No further nonresponse correction may be needed. The sampling plan does not guarantee the elimination of nonresponse bias from the data set. The extent to which this sampling strategy succeeds in attenuating Pilot Study nonresponse bias is a function of the correlation between such biases and the stratifying variable and the extent to which there is exchangability in characteritics among respondents and nonrespondents within the individual sample design strata. RECONSTRUCTING A "STANDARD" SAMPLE Some analysts of the 1987 NES Pilot Study data may feel uncomfortable with the sampling plan and its implicit nonresponse adjustment or they may wish to perform certain analyses in which the sample is standardized with that of prior Pilot Study datasets. To aid these researchers, Sampling Section has resampled the 1987 NES Pilot Study sample control file, effectively reconstructing a data subset (sma11er in case count) with the equa1 probability (EPSEM) sample design properties and nonresponse characteristics of past Pilot Studies. After resampling, the EPSEM data subset of n=515 cases should mimic the response outcome of a 1 in 2.10 sampling of the original n=1086 Form A respondents to the l986 NES. The EPSEM subset of cases is flagged in the 1987 NES Pilot Study data set by a value of '1' for variable 872317. Table 1 1987 NES Pilot Study Sample design plan and assumptions SAMPLE SIZE TOTAL SAMPLE STRATUM * 1 2 3 4 5 Completed interviews 450 104 95 84 82 85 Response rate .56 .72 .67 .82 .87 (Assumed from 1985 Pilot Study) Sample records 185 131 125 100 97 SAMPLE SELECTION PARAMETERS 1986 Form A Cases Total 1086 251 231 205 196 203 W/Telephone No. 955 193 303 181 184 194 Sample records 185 131 125 100 97 Selection Interval -- l.043 1.550 1.448 1.840 2.00 * Strata defined on the basis of l984 NES quintile ranges for a voter knowledge index. Achieved No. Interviews and Response Rate By Stratum Completed interviews 457 94 97 96 82 88 Response rate (actual) .74 .54 .76 .79 .84 .93 EPSEM FLAG BY STRATUM TABLES 1 THE DATA ARE NOT WEIGHTED ANALYSIS 1 VARIABLE EPSEM FLAG STRATA(ROW) STRATUM 0| 1| TOTALS |-------------|-------------| 1| 66| 119| 185 Row %| 35.7| 64.3| 100.0 Column %| 53.7| 23.1| 29.0 Grnd %| 10.3| 18.7| 29.0 |-------------|-------------| 2| 23| 108| 131 Row %| 17.6| 82.4| 100.0 Column %| 18.7| 21.0| 20.5 Grnd %| 3.6| 16.9| 20.5 |-------------|-------------| 3| 29| 96| 125 Row %| 23.2| 76.8| 100.0 Column %| 23.6| 18.6| 19.6 Grnd %| 4.5| 15.0| 19.6 |-------------|-------------| 4| 5| 95| 100 Row %| 5.0| 95.0| 100.0 Column %| 4.1| 18.4| 15.7 Grnd %| 0.8| 14.9| 15.7 |-------------|-------------| 5| 0| 97| 97 Row %| 0.0| 100.0| 100.0 Column %| 0.0| 18.8| 15.2 Grnd %| 0.0| 15.2| 15.2 |-------------|-------------| Totals 123 515 638 Row % 19.3 80.7 100.0 Col % 100.0 100.0 100.0 Grnd % 19.3 80.7 100.0 *** Normal termination of TABLES $ 0.16 0.17 secs >> 1987 PILOT GUIDE TO LOCATION OF VARIABLES Variable numbers Description of data 820001-820802 1986 National Election Study 872001-872317 1987 Pilot Study, Wave 1: fixed alternative survey variables and field administration variables (from CATI application) 873001-874061 1987 Pilot Study, Wave I: open-end coding of study variables (from DDE application) 875001-875330 1987 Pilot Study Wave 2: fixed-alternative variables (from CATI application) 876001-877067 1987 Pilot Study, Wave A: - open-end coding of study variables (from DDE application) PLEASE NOTE: THERE ARE MANY GAPS IN THESE SEQUENCES OF VARIABLE NUMBERS. The next section documents the order, by form, in which questions were asked in the interview. Since there were a number of order experiments, neither the question number nor the variable number is a valid indicator of the order in which the questions were actually asked of respondents. Four questionnaires (Wave 1 -Form A, Wave 1 - Form B. Wave 2 - Form A, and Wave 2 - Form B) follow the Question Order section, and document question order in detail. Note: the variable numbers below are presented without the prefix ("V87"). QUESTION ORDER WAVE 1: FORM A Question No. Var. No. Variable description Al-Ala 2151-2152 Reagan approval -- job as President A2-A2a 2154-2155 Reagan approval -- managing economy A3-A3e 2157-2162 Thermometer -- people A4-A4j 2166-2171 Thermometer -- groups A5-A5d 2172-2175 Nationalism items A6a-A6d 2176-2179 Equality items A7 2180-2183 Forced Choice Party ID A9-A9h 2184-2191 Reagan traits A10-AlOf 2192-2197 Moral traditionalism A11-Alle 2198-2202 Roles of representatives A12-A17 2203-2209 Welfare items poverty frame A18 2210 Party handle problems of economy A19-A19d 2211-2214 Reagan affects A20-A2Ob 2215-2217 Filtered lib-cons, A21 2218 Spending and services -- response Open-ends: structure experiment 3102-3147, 3201-3251 A22a-A22h 2220-2227 Moral evaluation and objectivism A35-A36d 2245-2249, Foreign policy items A42,A43 267,268 A44 2269 Jobs and good standard of living - Open-ends: response structure experiment 3302-3347, 3401-3451 A45-A45c 2270-2274 Traditional party ID (See also 2315) A46-A46d 2275-2278 Anti-Reagan primes A47 2279 Aid to blacks -- response structure Open-ends: 3502-3547, 3601-3651 A48-A48b 2281-2282 Reagan approval (See also 2316) Open-ends: 3701-3729 A49-A49e 2283-2287 Roles of U.S. Senators WAVE 1 FORM B Question No. Var. No. variable description Al-Ala 2151-2152 Reagan approval -- job as President A2-A2a 2154-2155 Reagan approval -- managing economy A5-A5d 2172-2175 Nationalism items A6a-A6d 2176-2179 Equality items A53-53c 2294-2298 Traditional party ID -- filtered A50,A8 2288-2289 vote experiment A9-A9h 2184-2191 Reagan traits A10-AlOf 2192-2197 Moral traditionalism A11-Alle 2198-2202 Roles of representatives A56,A57, 2309-2310, Welfare items -- welfare frame A14-A16, 2205-2207 A59,A60 2311-2312 A18 2210 Party handle problems of economy A19-A19d 2211-2214 Reagan affects A20-A20b 2215-2217 Filtered lib-cons, A51c 2290 Spending and services -- stop Open-ends: and think experiment 3801-3845 A22a-A22h 2220-2227 Moral evaluation and objectivism A35-A36d, 2245-2249, Foreign policy items A42,A43 267,268 A3-A3e 2157-2162 Thermometer -- people A4-A4j 2163-2171 Thermometer -- groups A52 2292 Jobs and good standard of living - Open-ends: stop and think experiment 3901-3945 A45-A45c 2270-2274 Traditional party ID (See also 2315) A54-A54c 2299-2~01 Pro-Reagan primes A55d 2301 Aid to blacks -- stop and think Open-ends: experiment 4001-4061 A48-A48b 2281-2282 Reagan approval and follow-one (See also 2316) Open-ends: 3701-3729 WAVE 2: FORM A Question No. Var. No. Variable Description Ala-Alh 5151-5158 Patriotism A2a-A2j 5159-5168 Thermometer -- groups A3a-A5h 5169-5175 Regime based trust and efficacy (using NES efficacy) A4a-A4b 5176-5179 Traditional party identification, filtered A5a-A5d 5180-5183 Moral autonomy A6a-A6e 5184-5188 Roles of Representatives A7a-A7e 5189-5193 Senate Roles A8a-AlOd 5194-5205 Candidate evaluations A12 5210-5213 Unfiltered lib-con A13 5215 Policy -- abortion A14 5214,5326 Policy -- homosexuals A14a-A15f 5216-5223 Incumbent based trust and efficacy A17 5224 (Open:Aid to blacks, response structure 6501-6653) experiment A18 5266 (Open:Jobs and good standard of living - 6101-6253) response structure experiment A20-A36a 5229-5265 Foreign policy A37 522S (Open:Spending and services -- response 6301-6453) structure experiment A38a-A39f 5267-5279 Internal efficacy and NES trust in government items A41 5282-5284 Blacks' economic position A42 5285 Women's role A43-A44b 5286-5295 National and state party ID A45a-A45b 5294-5295 Pro-Reagan primes A19a-A19c 5226-5228 Moral evaluation, repeated items (Evaluations of homosexuality, divorce, abortion) A46 5296-5297 Reagan approval and follow-one (Open: 6701-6731) WAVE 2: FORM B Question No. Var.No. variable Description Ala-Alh 5151-5158 Patriotism A3a-A3h 5169-5175 Regime based trust and efficacy (using NES efficacy) A47 5300,5327 party identification' forced choice 5301 A5a-A5d 5180-5183 Moral autonomy A7a-A7e 5189-5193 Senate Roles A8a-AlOd 5194-5205 Candidate evaluations A48 5303-5306 Filtered lib-con A13 5215 Policy -- abortion A14 5214,5326 Policy -- homosexuals A14a-A15f 5216-5223 Incumbent based trust and efficacy A49 57.07 (Open: Aid to blacks, response structure 7001-7063) experiment A50 5308 (Open: Jobs and good standard of living - 6841-6847) response structure experiment A20-A36a 5229-5265 Foreign policy A2a-A2j 5159-5168 Thermometer -- groups A51 5309 (Open: Spending and services -- response 6901-6947) structure experiment A38a-A39f 5267-5279 Internal efficacy and NES trust in government items A41 5282-5284 Blacks' economic position A42 5285 Women's role A43-A44b 5286-5293 National and state party ID A52-A452d 5310-5313 Pro-Reagan primes A19a-A19c 5226-5228 Moral evaluation, repeated items (Evaluations of homosexuality, divorce, abortion) A46 5296-5297 Reagan approval and follow-one (Open: 6701-6731) >> CODEBOOK INFORMATION The following example from the 1948 NES study provides the standard format for codebook variable documentation. Note that NES studies which are not part of the Time-Series usually omit marginals and the descriptive content in lines 2-5 (except for variable name). Line 1 ============================== 2 VAR 480026 NAME-R NOT VT-WAS R REG TO VT 3 COLUMNS 61 - 61 4 NUMERIC 5 MD=0 OR GE 8 6 7 Q. 17. (IF R DID NOT VOTE) WERE YOU REGISTERED (ELIGIBLE) 8 TO VOTE. 9 ........................................................... 10 11 82 1. YES 12 149 2. NO 13 14 0 8. DK 15 9 9. NA 16 422 0. INAP., R VOTED Line 2 - VARIABLE NAME. Note that in the codebook the variable name (usually a 'number') does not include the "V" prefix which is used in the release SAS and SPSS data definition files (.sas and .sps files) for all variables including those which do not have 'number' names. For example the variable "VERSION" in the codebook is "VVERSION" in the data definition files. Line 2 - "NAME". This is the variable label used in the SAS and SPSS data definition files (.sas and .sps files). Some codebooks exclude this. Line 3 - COLUMNS. Columns in the ASCII data file (.dat file). Line 4 - CHARACTER OR NUMERIC. If numeric and the variable is a decimal rather than integer variable, the numer of decimal places is also indicated (e.g. "NUMERIC DEC 4") Line 5 - Values which are assigned to missing by default in the Study's SAS and and SPSS data definition files (.sas and .sps files). Line 7 - Actual question text for survey variables or a description of non-survey variables (for example, congressional district). Survey items usually include the question number (for example "B1a.") from the Study questionnaire; beginning in 1996 non-survey items also have unique item numbers (for example "CSheet.1"). Line 9 - A dashed or dotted line usually separates question text from any other documentation which follows. Line 10- When present, annotation provided by Study staff is presented below the question text/description and preceding code values. Lines 11-16 Code values are listed with descriptive labels. Valid codes (those not having 'missing' status in line 5) are presented first, followed by the values described in line 5. For continuous variables, one line may appear providing the range of possible values. A blank line usually separates the 'valid' and 'missing' values. Lines 11-16 Marginals are usually provided for discrete variables. The counts may be unweighted or weighted; check the Study codebook introductory text to determine weight usage.