The telephone exchanges were selected with probabilities proportional to their size. The first eight digits of the sampled telephone numbers (area code, telephone exchange, bank number) were stratified by county and by telephone exchange within county. The number of telephone numbers randomly sampled from within a given county is proportional to that county’s share of telephone households in the state. Estimates of the number of telephone households within each county are derived from 1990 Census data on residential telephone incidence that have been updated with state- level information on new telephone installations and county-level projections of the number of households. Only working banks of telephone numbers are selected. A working bank is defined as 100 contiguous telephone numbers containing three or more residential listings.
The sample was released for interviewing in replicates. Using replicates to control the release of sample to the field ensures that the complete call procedures are followed for the entire sample.
At least four attempts were made to complete an interview at every sampled telephone number. The calls were staggered over times of day and days of the week to maximize the chances of making a contact with a potential respondent. All interview breakoffs and refusals were re-contacted at least once in order to attempt to convert them to completed interviews. In each contacted household, interviewers asked to speak with the “youngest male 18 or older who is at home”. If there is no eligible man at home, interviewers asked to speak with “the oldest woman 18 or older who lives in the household”. This systematic respondent selection technique has been shown empirically to produce samples that closely mirror the population in terms of age and gender. Respondents were screened to determine if they are registered to vote. Respondents who reported they are not registered were asked demographic questions, which were used in weighting the data, but they were not given the entire interview.
Non-response in telephone interview surveys produces some known biases in survey-derived estimates because participation tends to vary for different subgroups of the population, and these subgroups are likely to vary also on questions of substantive interest. In order to compensate for these known biases, the sample data are weighted in analysis.
All respondents, both registered voters and those not registered who were only asked demographic questions, were weighted to bring their demographic characteristics into alignment with the most recently available census data on the age, sex, education and region distribution of the adult population of the state of New Hampshire. The registered voters were then separated out for analysis.
The weights are derived using an iterative technique that simultaneously balances the distributions of all weighting parameters. After an optimum sample balancing solution is reached, the weights were constrained to fall within the range of 1 to 5. This constraint is useful to ensure that individual respondents do not exert an inordinate effect on the survey’s overall results.