![Sample our Humanities journals, sign in here to start your FREE access for 14 days]({"type":"image" , "src" : "/sda/5939/TOC-Subject-Sample-2021-Humanities.jpg"})
Field experimentation is a promising but seldom used method for studying the effects of media messages on political attitudes and behavior. The practical challenges of conducting media experiments in real-world settings often come down to securing cooperation from research partners, such as political campaigns. To do so, researchers must be prepared to adapt their experimental designs to satisfy the constraints imposed by research partners and the media environment in which they operate. This article provides an overview of some alternative field experimental designs that allow researchers to maintain the advantages of random assignment while addressing practical considerations. Examples are drawn from the growing field experimental literature examining the effects of television, radio, and online communication.
Notes
1. As sample sizes increase, the advantages of blocking diminish. Lin (2013) and Miratrix, Sekhon, and Yu (2013) show that, asymptotically, simple between-subjects designs achieve the same precision as block randomized designs when the data are analyzed using covariate adjustment or post-stratification.
2. Modeling spillovers in this way in effect relaxes the assumption that subjects are affected solely by their own treatment status and not the status of others.
3. It is possible to construct experiments explicitly designed to estimate spillover effects. One option is a hierarchical design; Sinclair, McConnell, and Green (2012) provide an example in political science, and Hudgens and Halloran (2008) provide technical details. Aronow and Samii (2013) describe estimation and inference for alternative designs.
4. For a step-by-step explanation of the inverse-probability-weighted (Horvitz & Thompson, 1952) estimation of average causal effects under a blocked design or restricted random assignment, see Gerber and Green (2012, chapters 3 and 4, with technical details in Aronow & Middleton, 2013).
5. Special constraints apply when providing resources to political campaigns. In the United States, tax laws and election regulations restrict the use of university resources.