Comparing Modes and Samples in Experiments: When Lab Subjects Meet Real People

35 Pages Posted: 20 Sep 2016

See all articles by Pablo Beramendi

Pablo Beramendi

Duke University - Department of Political Science

Raymond M. Duch

Nuffield College University of Oxford

Akitaka Matsuo

University of Oxford

Date Written: September 19, 2016

Abstract

In this essay we assess the internal and external validity of experiments with online subjects. The assessments are based on tax compliance experiments in which subjects earn real money, are subject to a tax, and can lie about their earnings. We identify the mode effects that affect internal validity by comparing treatment effects in lab and online versions of the experiments. Secondly, we compare the treatment effects across different online (MTurk and U.K. CESS Online) and lab subject pools to determine whether these might affect the external validity of the experimental results.

Suggested Citation

Beramendi, Pablo and Duch, Raymond M. and Matsuo, Akitaka, Comparing Modes and Samples in Experiments: When Lab Subjects Meet Real People (September 19, 2016). Available at SSRN: https://ssrn.com/abstract=2840403 or http://dx.doi.org/10.2139/ssrn.2840403

Pablo Beramendi

Duke University - Department of Political Science ( email )

140 Science Drive (Gross Hall), 2nd floor
Duke University Mailcode: 90204
Durham, NC 27708-0204
United States

Raymond M. Duch (Contact Author)

Nuffield College University of Oxford ( email )

New Road
Oxford, OX1 1NF
United Kingdom

Akitaka Matsuo

University of Oxford ( email )

Register to save articles to
your library

Register

Paper statistics

Downloads
37
Abstract Views
248
PlumX Metrics