Testing the Waters: Behavior across Participant Pools
نویسندگان
چکیده
We leverage a large-scale incentivized survey eliciting behaviors from (almost) an entire undergraduate university student population, representative sample of the US and Amazon Mechanical Turk (MTurk) to address concerns about external validity experiments with participants. Behavior in population offers bounds on other populations, correlations between are similar across samples. Furthermore, non-student samples exhibit higher levels noise. Adding historical lab participation data, we find small set attributes over which participants differ non-lab An additional shows no evidence observer effects. (JEL C83, D90, D91)
منابع مشابه
Participant Behavior in PHONELAB
This abstract examines the behavior of the participants in PHONELAB, a public smartphone testbed being developed at SUNY Buffalo. Currently consisting of 191 participants using Nexus S 4G smartphones, PHONELAB aims to provide a combination of unique features desirable for smartphone experimentation. This abstract briefly introduces PHONELAB and presents some of the early results of a usage meas...
متن کاملChallenges in Participant Recruiting For Usability Testing
Effective participant recruiting is crucial to collecting reliable data during usability testing of high-tech products and services. Not only should test participants reflect the characteristics of the targeted users of the product or service, but they also must be likely to use it. Only then will their experiences and opinions yield reliable data for identifying meaningful improvements. This p...
متن کاملTesting the political waters of healthcare reform.
~| y electing Democrat Harris Wofford B to the Senate over former Attorney General Richard T h o r n b u r g h in November 1991, the voters of Pennsylvania proved that healthcare reform is a politically salient issue. Policy analysts, amazed that Wofford's healthcare reform message was a key factor in his election, have debated during the past few months whether this was a fluke or the precurso...
متن کاملGroup Testing with Pools of Fixed Size
In the classical combinatorial (adaptive) group testing problem, one is given two integers d and n, where 0 ≤ d ≤ n, and a population of n items, exactly d of which are known to be defective. The question is to devise an optimal sequential algorithm that, at each step, tests a subset of the population and determines whether such subset is contaminated (i.e. contains defective items) or otherwis...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: The American Economic Review
سال: 2021
ISSN: ['2640-205X', '2640-2068']
DOI: https://doi.org/10.1257/aer.20181065