American National Election Study, 1990-1992: Full Panel Survey (ICPSR 6230)

Version Date: Dec 15, 2005 View help for published

Principal Investigator(s): View help for Principal Investigator(s)
Warren E. Miller, Unknown; Donald R. Kinder, Unknown; Steven J. Rosenstone, Unknown


Version V2

This study is part of a time-series collection of national surveys fielded continuously since 1952. The American National Election Studies are designed to present data on Americans' social backgrounds, enduring political predispositions, social and political values, perceptions and evaluations of groups and candidates, opinions on questions of public policy, and participation in political life. This collection includes respondents who were first interviewed following the November 1990 general election (see AMERICAN NATIONAL ELECTION STUDY, 1990: POST-ELECTION SURVEY [ICPSR VERSION] [ICPSR 9548]), and then reinterviewed in two subsequent surveys: AMERICAN NATIONAL ELECTION STUDY: 1990-1991 PANEL STUDY OF THE POLITICAL CONSEQUENCES OF WAR/1991 PILOT STUDY [ICPSR VERSION] (ICPSR 9673) and AMERICAN NATIONAL ELECTION STUDY, 1992: PRE- AND POST-ELECTION SURVEY [ENHANCED WITH 1990 AND 1991 DATA] (ICPSR 6067). The purpose of this panel study is to trace the fortunes of the Bush presidency, from post-Gulf War height to November election defeat, and to provide insight into the origins of the Bill Clinton and Ross Perot coalitions. It also allows the panel analyst to do a traditional assessment of panel attrition which is not possible with any of the collections mentioned above. In 1990, respondents answered questions on topics such as presidential performance, the Persian Gulf War, values and individualism, and foreign relations. Post-election vote validation and election administration survey data are also included. In 1991, respondents were reinterviewed several months after hostilities in the Persian Gulf ended. The survey content consisted of a repeat of a subset of questions from the 1990 Post-Election Survey, and additional items especially relevant to the Gulf War. A number of contextual variables also are provided, including summary variables that combine the respondent's recall of his or her senator's and representative's vote on the use of force with that congressperson's actual vote. New pilot questions were also asked in areas such as gender, ethnicity, medical care for the elderly, and social altruism. In 1992, respondents were asked their positions on social issues such as altruism, abortion, the death penalty, prayer in the schools, the rights of homosexuals, sexual harassment, women's rights, and feminist consciousness. Other substantive themes included racial and ethnic stereotypes, opinions on school integration and affirmative action, attitudes towards immigrants (particularly Hispanics and Asians), opinions on immigration policy and bilingual education, assessments of United States foreign policy goals, and United States involvement in the Persian Gulf War. Part 2 provides information on the total number of cases included in the 1990 Post-Election Survey sample (1,980 respondents who were valid interviews and 805 selected respondents who were not interviewed) in order to study survey nonresponse. Variables include reasons for noninterview, the number of calls, and characteristics of the noninterviewed household.

Miller, Warren E., Kinder, Donald R., and Rosenstone, Steven J. American National Election Study, 1990-1992: Full Panel Survey. Ann Arbor, MI: Inter-university Consortium for Political and Social Research [distributor], 2005-12-15.

Export Citation:

  • RIS (generic format for RefWorks, EndNote, etc.)
  • EndNote
National Science Foundation (SES-8808361, SOC77-08885, SOC77-8341310, andSES-8808361)
Inter-university Consortium for Political and Social Research
1990 -- 1993

The study staff attempted to reinterview every respondent among the 1,980 individuals who participated in the 1990 Post-Election Survey. A total of 1,383 of these respondents participated in the 1990/1991 Panel Study. For the 1992 Pre- and Post-Election Survey, the study staff again attempted to reinterview every 1990 respondent whether or not they had given an interview in 1991. Thus, while there were 1,383 panel respondents in 1991 and 1,359 respondents in 1992, only 1,060 respondents were interviewed in all three studies. If a respondent was not interviewed in 1991 or 1992, his/her record was padded with missing data for variables from that year.

Variables that first appeared in either ICPSR 9548, ICPSR 9673, or ICPSR 6067 are unchanged in Part 1 of this collection.

Part 2, Supplementary Data File, provides coversheet, sampling, and field information on all sample cases from the 1990 Post-Election survey, including noninterview and nonsample cases. The data file can be merged with the main data file (Part 1) by using V900004, the 1990 Case Identification variable.

A national multistage area probability sample was employed for the 1990 Post-Election Survey and the 1992 Pre- and Post-Election Survey. For the 1991 Panel Study of the Political Consequences of the Persian Gulf War, 615 respondents were not reinterviewed either due to panel mortality (e.g., they had moved or died), or were effectively nonsample for telephone reinterview because they were extremely hard of hearing, could not be reached by telephone, or needed to be interviewed in a language other than English.

All United States citizens of voting age on or before November 6, 1990, residing in housing units other than on military reservations in the 48 coterminous states.

survey data


2018-02-15 The citation of this study may have changed due to the new version control system that has been implemented. The previous citation was:
  • Miller, Warren E., Donald R. Kinder, and Steven J. Rosenstone. American National Election Study, 1990-1992: Full Panel Survey. ICPSR06230-v2. Ann Arbor, MI: Inter-university Consortium for Political and Social Research [distributor], 2005-12-15.

2005-12-15 On 2005-08-15 new files were added to one or more datasets. These files included additional setup files as well as one or more of the following: SAS program, SAS transport, SPSS portable, and Stata system files. The metadata record was revised 2005-12-15 to reflect these additions.

1999-10-07 The data for this study are now available in SAS transport and SPSS export formats in addition to the ASCII data files. Variables in the datasets have been renumbered to the following format: 2-digit (or 2-character) year prefix + 4 digits + [optional] 1-character suffix. Dataset ID and version variables have also been added. The SAS and SPSS data definition statements and codebook have been revised accordingly. Finally, the errata from April 1994 (formerly Part 5) have been incorporated into the codebook, and the SAS data definition statements parts (formerly Parts 2 and 4) have been removed from the template and linked with their respective data files.


  • Data in this collection are available only to users at ICPSR member institutions.

  • The citation of this study may have changed due to the new version control system that has been implemented. Please see version history for more details.
ICPSR logo

This study is provided by ICPSR. ICPSR provides leadership and training in data access, curation, and methods of analysis for a diverse and expanding social science research community.