NZES had five major components: A New General Sample, which involved a
proportionately random selection from the general parliamentary electorates;
the Election to Election Panels, which was conducted post-election and included
respondents from the 1996 and 1999 NZESes; the Campaign Pre-Election Sample and
Pre-Post Panel, which involved a random national sample and was conducted 36
days before the election; the Māori Election Study, which involved an
over-sample from the Māori electoral rolls; and The Candidate Study, which was
sent out to all candidates standing for parties in the House.
Variables include the
respondent’s interest in politics, internet usage, how many hours spent
watching television or listening to the radio, attitudes toward and trust in
the government in general, opinions of other candidates, campaign involvement,
attitudes to immigrants, group membership, voting preferences and confidence in
the public service.
Background variables include gender, date of
birth, country of birth, highest level of education, employment status,
religious affiliation, and parents’ political views.
Response rate: New General Sample: The postal response
rate was 44.6% (N = 1,338), with the telephone interviewing adding a further 8%
(N = 248), resulting in a combined response rate of 52.2% (N = 1,586).
Election to Election
Panels: The 1996 Panel had N =
533, and the 1999 Panel had N = 537. Of all the panel respondents, 1,040
completed the postal questionnaire and a further 120 were followed up by phone.
Respondents within each panel were subject to different levels of response rate
attrition, but no significant or obvious non-response bias was apparent.
The Campaign Pre-Election
Sample and Pre-Post Panel: The Pre-Election
campaign had N = 3,590, with a target of 100 interviews for the 36 days
immediately before the election. The response rate was 34%. Campaign
respondents were also asked to participate post-election and the 3,190 who
agreed to do so were mailed the post-election questionnaire. Of these, 2,008
responded again by post and 514 by phone, resulting in a response rate of 79%
of those who had agreed to participate.
Māori Election Study: This study had N = 500, with a corresponding
response rate of 33.3%. 27% resulted from the mail questionnaire; 6.3% was
achieved by telephone.
SamplingNew General Sample: This was randomly selected from the electoral rolls, proportionately from each of the 62 General parliamentary electorates and conducted immediately post-election as detailed above. Election to Election Panels: Administered post-election, these samples contain respondents from the 1996 and 1999 NZES (Vowles, Aimer, Banducci and Karp 1998; Vowles, Aimer, Karp, Banducci, Miller and Sullivan 2002). The Campaign Pre-Election Sample and Pre-Post Panel: This campaign was a random national sample from households with telephone interviews conducted for the NZES by ACNielsen (NZ) Ltd. Respondents were randomly selected from within households. Campaign respondents were also asked to participate post-election, and those who agreed to do so were mailed the post-election questionnaire. Merging the pre and post data by respondent thus constitutes the pre-post panel. Māori Election Study: The Māori Election Study is an over-sample from the Māori electoral rolls. The Candidate Study: Over the same period as the voter surveys, although excluding the telephone top-up, mail questionnaires were sent out to all candidates standing for parties with seats in the House, or likely to gain any. The candidate survey provides data on the respondents’ background, recruitment and selection, role as an MP (if relevant), and attitudes. Questions on issues and policies replicated those in the voter surveys, enabling comparison between the attitudes and behaviour of voters and candidates.
UniversePersons aged 18 and over listed on the New Zealand electoral rolls; persons aged 18 and over and listed on the Māori electoral rolls; respondents from the 1996 and 1999 New Zealand Election Studies; households with phones listed with Telecom New Zealand Ltd for the telephone survey component.
Data CollectorACNielsen collected the data for the telephone component.
Mode of CollectionTelephone interview (separate questionnaire not included here); Self-completion (mail out, mail back).
WeightingSeveral weighting variables are provided for more representative analysis.
Series InformationThrough the analysis of political behaviour over successive New Zealand elections, we have been monitoring the democratic process in New Zealand during a period of social and economic change and, most particularly, during the transition between electoral systems: the first past the post (FPP) or plurality electoral system in effect in New Zealand from the origins of the political system, and the new Mixed Member Proportional (MMP) system which is in effect from the 1996 election. The NZES began in its present form in 1990. The NZES’s main source of data are questionnaires which are posted to randomly selected registered electors across the country immediately following each election. Questions focus on voting choices, political opinions, and social and demographic characteristics.
Publisher (e.g. University of Auckland)The University of Auckland