Election Polling
Pre-election polling is a rare chance for pollsters to "check their work" by measuring how well their polls matched election outcomes.

• Identifying likely voters
• Determining voter preference
• Gauging the accuracy of election polls
• Additional topics on election polling

Sampling
Most of our national surveys of the general public are conducted by telephone using a random digit sample of listed and unlisted telephone numbers in the continental United States.

• Random digit dialing - our standard method
• Cell phones
• Oversamples
• Regional surveys
• International surveys
• Elites and other special populations
• Why probability sampling

Collecting Survey Data
Survey researchers employ a variety of techniques in the collection of survey data. In this section, we have chosen the reports and commentaries that best highlight these methods.

• Cell phone surveys
• Internet surveys
• The problem of declining response rates
• Mixed-mode surveys
• Reinterviews

Questionnaire Design
Question design is often thought to represent the art of survey research but there is also plenty of science involved. What are the pitfalls and best practices of survey design?

• Questionnaire development
• Measuring change over time
• Open and closed-ended questions
• Question wording
• Question order
• Pilot tests and focus groups
• Pretests

July 9, 2009
Accurately Locating Where Wireless Respondents Live Requires More Than A Phone Number

The mobile nature of wireless phones creates a significant problem for geographic sampling and analysis. This problem is exacerbated by the fact that the wireless-only are more geographically mobile than those with landline phones.

More Methodology Reports

June 25, 2009
Perils of Polling in Election '08

Despite such challenges as a growing wireless-only population, possible racially-related response bias and greater-than-usual difficulties in forecasting turnout, polllsters' methods were evidently adequate to the task.