Registration Based Sampling (RBS)

For voter surveys, WRS uses Registration Based Sampling (RBS) methodology.  First proposed by renowned Yale professors Green and Gerber in 2001, Registration Based Sampling has now become recognized as the most accurate and leading sampling methodology for pre-election polling.  RBS utilizes information available from electronic voter registration files to create a sample of registered likely voters.

In comparisons in the 2002 General election the forecasts from this sampling methodology proved far more accurate than traditional RDD polls.

When WRS samples of registered voters are implemented using a registration-based sampling methodology, lists of registered voters statewide are purchased from the most up to date sources. The lists are updated regularly and include the names along with a wealth of other information about the voter, including a voter's address, city and county of residence, gender, date of birth (age), party registration, whether or not the voter is a permanent absentee voter, and extent to which the voter participated in past elections.

Most lists provide a telephone number for between 90- 95% of the voters listed. These telephone numbers come from a variety of sources, including telephone numbers entered on the voter's registration form, as well as by cross referencing voter names and addresses against recent telephone directories and other telephone matching services.

While these telephone numbers are primarily landline telephone numbers, the listings also include cell phones, whenever a cell phone number is provided by the voter when registering to vote or in other settings accessible to telephone matching services. Thus, cell phones are not systematically excluded from the sample frame. Special procedures are employed when contacting voters on their cell phones to include them into each WRS voter survey.

Since the RBS sample frame is drawn from a list of individuals (i.e., voters), this sampling approach eliminates the need to implement any respondent selection procedures once a contact is made, because the full name of the voter to be sampled is known and this voter can be asked for directly.

In addition, RBS sampling does not rely on respondent testimony as to whether the respondent being sampled is a registered voter, and if so, what party the voter is affiliated with, since all persons contacted are known to be registered and their actual party registration is identified again making the sampling far more accurate.

Also, since the voter's gender, county of residence, age and party registration are known in advance, additional samples of voters meeting specified sampling requirements can easily be augmented or the statewide sample stratified along any of these dimensions.

To learn more about Registration Based Sampling, read Green and Gerber’s most recent paper here or Professor Christopher Mann's paper on Improving Pre-election Forecasts through RBS. Please contact us today to design or consult on your upcoming voter survey.