"Response to Smith's "Trends in Voluntary Group Membership
"Comments on Baumgartner and Walker": Measurement Validity and the Continuity of Results in Survey Research
Bibliographic Data
| ID | 11623967 |
|---|---|
| Authors | F R Baumgartner (0000-0003-4193-4152), Jack L Walker, Jack Walker (0000-0003-2078-3981) |
| Year | 1990 |
| Volume | 34 |
| Issue | 3 |
| Pages | 662-662 |
| Publication date | 1990-08-01 |
| Peer Reviewed | Yes |
| Open Access | No |
| Type | ARTICLE |
| Venue | American Journal of Political Science (JOURNAL) |
| Journal identifiers | ISSN: 0092-5853 • E-ISSN: 1540-5907 |
| Publisher | Wiley (PUBLISHER • GB) |
| DOI | 10.2307/2111393 |
| OpenAlex | W2331941858 |
| Language | EN |
| Citations received | 4 |
| References cited | 1 |
It is widely understood that alterations in question often change the outcome of surveys. A controversy involving dozens of scholars arose during the past decade, for example, over whether U.S. voters have become more ideological in their thinking about politics. Unfortunately, the survey evidence around which the debate revolved was not entirely comparable because of subtle changes in the administration of the National Election Study (NES). After a decade of controversy, it became clear that most of the apparent change in opinion structure was artificial, produced not by political metamorphosis but by mundane alterations in question wording (Kinder 1983, 395-96). Incidents of this kind produce quite justifiable caution among the administrators of large surveys. They avoid the temptation to make small improvements in questions because they wish to preserve the reliability of a growing time series or to ensure comparability among surveys of different populations. It is precisely this trade-off between validity and the continuity of results that is at the core of the difference of opinion between Tom Smith and ourselves. Where interest group membership is concerned, we believe that fundamental social changes have occurred that require a new approach to the measurement of citizens' affiliations with groups. By clinging to a question conceived of a generation ago, we believe that researchers are introducing serious measurement error into their surveys. The Standard Question on group membership was entirely appropriate to the social realities and punch-card computer technology of the 1960s, but the world has changed, and we believe that in this case the survey questions must change along with it
Comparability · Economics · Ideology · Political science · Politics · Positive economics · Respondent · Temptation · Electoral Systems and Political Participation · Law · Psychology · Social Psychology · Survey Methodology and Nonresponse
| Unique citing works | 4 |
|---|---|
| Citations per year | 0,13 |
| Citation span | 1994 - 2011 (18) |
| Citation velocity | historical |
| Highly cited | No |
| Citation types | Neutral: 4 |