Time-sharing Experiments for the Social Sciences, TESS2042 Creighton, Perceptions of Islam, Migration, and Citizenship in the United States

Data Archive > Other Data > Summary


TESS conducts general population experiments on behalf of investigators throughout the social sciences. General population experiments allow investigators to assign representative subject populations to experimental conditions of their choosing. Faculty and graduate students from the social sciences and related fields (such as law and public health) propose experiments. A comprehensive, on-line submission and peer review process screens proposals for the importance of their contribution to science and society.

This list experiment tests whether views toward immigrants depend on whether the immigrant group shares the same religion as the respondent. Since traditional survey methods may be more prone to social desirability bias, an experimental design is necessary. In this study, respondents are divided between a control group and, in this case, two treatment groups. The control group is just asked three questions unrelated to immigration. The first treatment group is asked the original three questions, but with an additional question pertaining to Muslim immigrants. The second treatment group is asked the original three questions, but with an additional question pertaining to Christian immigrants. In its most basic incarnation, the comparison of the mean of the responses to the control list with the mean of the responses to each of the treatments offers an estimate of the proportion opposed to the additional list item.

Data File
Cases: 3,290
Variables: 59
Weight Variable: WEIGHT
Data Collection
Date Collected: 4/20/2010-7/8/2010
Original Survey (Instrument)
TESS2042 Original Survey
Funded By
National Science Foundation
Collection Procedures
In order to account for social desirability bias, this study uses a list experiment design (Internet-based), which allows respondents to permanently and unconditionally conceal their individual responses from researchers. The greatest advantage of this approach is that individual-level responses are not only concealed from the interviewer, but they cannot be known. Respondents are divided between a control group and, in this case, two treatment groups. The control group is asked a single question about the following list of items. The question reads:

Below you will read three things that sometimes people oppose or are against. After you read all three, just tell us HOW MANY of them you OPPOSE. We donít want to know which ones, just HOW MANY.

(1) the federal government increasing assistance to the poor
(2) professional athletes making millions of dollars per year
(3) large corporations polluting the environment

Two independently sampled treatment groups are asked an identical question, but of a list that includes the original three items above and a fourth item that queries opposition to Muslim and Christian immigrants respectively.

(4) granting citizenship to a legal immigrant who is Muslim
(4) granting citizenship to a legal immigrant who is Christian
Sampling Procedures
TESS provides investigators an opportunity to run Internet-based experiments on a random, probability-based sample of the population. To achieve a representative sample, we contract with GfK (formerly Knowledge Networks), which conducts surveys using its KnowledgePanel. KnowledgePanel is a nationally representative, probability-based web panel based on dual-frame sampling that combines traditional random-digit-dialing telephone surveying techniques with an address-based technique that allows the sample to be representative of cell-phone-only households as well as those with land-lines. A summary of the KnowledgePanel survey design used for the TESS projects can be accessed here. Additional data and study materials can be downloaded here.
Principal Investigators
Mathew Creighton, Universitat Pompeu Fabra
Notes
For any additional information regarding TESS data, please visit the original website here

Bookmark and Share