1958 Time Series Study

About the Dataset

  • Number of Cases: 1450
  • Number of Variables: 315
  • Weight Required: V580003

Study Content Highlights

The questionnaires contained both closed and open-ended questions covering a wide range of information. The study deals with political attitudes in general and more specific attitudes and behaviors pertinent to the 1958 Congressional Election. The survey obtained data on the respondent’s actual vote and reasons for the vote, attitudes toward political parties and candidates, and the respondent’s political history. It also obtained data on specific domestic and foreign policy issues such as government involvement in housing and public utilities, and United States aid to anti-Communist nations. The study also ascertained the financial situation of the family unit and other demographic information.

Study Design Highlights

The 1958 American National Election Study, conducted in December of 1958, represents the second wave of a 3-wave panel study; the other two waves consist of the 1956 and 1960 American National Election Studies. The 1958 study is itself a national cross-section sample of American citizens of voting age. Each respondent was interviewed only once after the election. Respondents who had not been interviewed in 1956 were selected from dwelling units vacated by 1956 respondents (movers). The individuals interviewed in 1958 were a representative cross-section of persons of voting age living in private households in the united states, but additional complications were introduced by the fact that the 1958 study was the second wave of a panel study which had begun in 1956. By 1958 many of the 1956 respondents had moved and could not be re-interviewed at their original addresses. Many of these respondents were included only in the panel study, not in the cross-section, because the cross-section sample is a sample of a specific set of households. To attempt to compensate for the loss of this group of respondents, a new group was selected from the current dwellers in the households from which the former respondents had moved. To reduce field costs only half as many such additional respondents were added as would have been selected if their probability of selection had been identical to that of the re-interviewed respondents. To adjust for this difference in sampling fractions, these additional respondents were given double weight; hence the weighted N of the 1958 election study is 1822, although the un-weighted N is only 1450.