Our Methodology

The Gold Standard in Latino Political Polling

Most frequently, our clients are interested in the voter behavior. Accordingly, our surveys employ rigorous social science standards and precise information about Latino demographics to make sure our respondents reflect the Latino electorate. Clients and the larger public can be confident in the accuracy of our survey results. Sound methodology and appropriate protocols are essential to a survey’s validity, here we highlight the most important aspects to our approach that make Latino Decisions “the gold standard in Latino American political polling”.

Latino Decisions conducts surveys of Latinos in the United States, many times focusing specifically on Latino registered voters. In our Latino registered voters surveys, we poll respondents who self-identify as Latino or Hispanic and are registered to vote in a given state or nationwide. Our national polls are always based on 50-state national sampling proportionate to the Latino population. Our samples are drawn randomly from the most recent publicly available list of registered voters in the given state or nationwide, and based on Hispanic households, as identified by different commercial vendors, and merged with third party data to secure telephone numbers; both landline and cellphone numbers are included.

One important starting point for identifying Hispanic households is to screen for Hispanic surnames using the Census Bureau list of 12,000 commonly occurring Spanish surnames. However we DO NOT rely on a Spanish-surname only sampling approach. Beyond the surname list, additional non-Spanish surname Hispanic households are identified by commercial market data and U.S. Census official population statistics at the census block level to more precisely identify Hispanic households in the sample. 

Voter registration status and Hispanic identification are verified upon contact with respondents, who confirm if they are registered to vote and of Hispanic/Latino descent. A wide variety of Census and academic research reports suggest 90% of all Latinos in the U.S. have a Spanish-surname, and using a registered voter list is far superior to a simple RDD of Spanish-surname households because a large percentage of Latinos are not registered to vote, yet many will say they are registered to vote in RDD samples, resulting in a high percentage of non-registrants in the sample. Latino Decisions (and most reputable pollsters) avoid this simple error by using the registered voter list as a starting point.

Latino Decisions samples with whatever method a particular client prefers, built on the premise of obtaining the most accurate and representative sample possible.  These samples havesometimes been simplistically identified as “surname” samples, but in fact, the samples we purchase do contain an appropriate percentage of respondents with non-Spanish surnames, since we also use commercially available markers of hispanicity.  Typically the number of Hispanics with non-Spanish surnames hovers around 10%.  Hispanic households are typically identified first through the use of Spanish-surname lists, identified by the U.S. Census, but this is not the only identifier of Hispanic households.  Additional market-based, geographic, and consumer data is routinely collected and merged into voter files to identify potential Hispanic households, as well as to include non-Spanish surname households in heavily Hispanic census tracts.  Thus, Hispanic households are identified by a wide range in techniques, of which the surname list is a starting point.

Surveying is conducted by fully bilingual interviewers. Respondents are greeted in both languages, and surveys are conducted in either English or Spanish, at the discretion of the respondent. Up to five callbacks are scheduled for each record. The survey instrument is created by Dr. Matt Barreto and Dr. Gary Segura, often in consultation with other Latino political scientists, and translated into Spanish. The survey is administered under the direction of Pacific Market Research, in Renton, Washington, and performed using a Computer-Assisted-Telephone-Interviewing (CATI) protocols. CATI programming is performed by Pacific Market Research. Our CATI software offers a superior ability to exercise tight control of sample. We can track call histories for every number dialed, ensure that the times when respondents are called are varied (different times of day and on different days) to maximize response rates, and thus achieve a high degree of customization to fit individual project requirements.