Similarities and Differences in Tobacco Control Research Findings From Convenience and Probability Samples.

Similarities and Differences in Tobacco Control Research Findings From Convenience and Probability Samples.
复制标题

DOI:
10.1093/abm/kay059
复制
发表时间:
2019-03-28
期刊:
Annals of behavioral medicine : a publication of the Society of Behavioral Medicine
影响因子:
--
通讯作者:
Brewer NT
Brewer NT
中科院分区:
其他
文献类型:
--
作者:
Jeong M;Zhang D;Morgan JC;Ross JC;Osman A;Boynton MH;Mendel JR;Brewer NT

文献摘要

参考文献

被引文献

相似文献

在线方便样本是研究健康行为的一种快速且低成本的方法,但其与概率样本结果的可比性尚未得到很好的理解。在烟草控制研究的背景下,我们试图比较便利样本和概率样本在实验、相关因素和患病率方面的发现。参与者是2014年9月至2015年5月通过电话招募的5014名美国成年人(成本约62万美元)的概率样本,以及2014年12月通过亚马逊土耳其机器人(MTurk)招募的4137名美国成年人的在线便利样本(成本约1.7万美元)。参与者完成了一项调查,包括实验、烟草制品使用测量和人口统计学特征。在几乎所有的实验(24项分析中的21项没有差异)和观察性研究(25项关联中的19项没有差异)中,MTurk便利和概率样本显示了相同的统计显著性模式和方向。样本的人口统计学特征差异很大(17个估计中有1个没有差异),方便样本更年轻,受教育年限更长,包括更多的白人和亚洲人。烟草制品的使用也存在很大差异(22个患病率估计值中有1个没有差异),便利样本报告了更多的香烟和电子烟使用(中位数误差19%)。使用MTurk方便样本可以为实验和观察研究提供可推广的发现。来自MTurk便利样本的患病率估计可能过高或过低。
Online convenience samples are a quick and low-cost way to study health behavior, but the comparability to findings from probability samples is not yet well understood. We sought to compare convenience and probability samples’ findings for experiments, correlates, and prevalence in the context of tobacco control research. Participants were a probability sample of 5,014 US adults recruited by phone from September 2014 through May 2015 (cost ~ $620,000 US) and an online convenience sample of 4,137 US adults recruited through Amazon Mechanical Turk (MTurk) in December 2014 (cost ~ $17,000 US). Participants completed a survey with experiments, measures of tobacco product use, and demographic characteristics. MTurk convenience and probability samples showed the same pattern of statistical significance and direction in almost all experiments (21 of 24 analyses did not differ) and observational studies (19 of 25 associations did not differ). Demographic characteristics of the samples differed substantially (1 of 17 estimates did not differ), with the convenience sample being younger, having more years of education, and including more Whites and Asians. Tobacco product use also differed substantially (1 of 22 prevalence estimates did not differ), with the convenience sample reporting more cigarette and e-cigarette use (median error 19%). Using MTurk convenience samples can yield generalizable findings for experiments and observational studies. Prevalence estimates from MTurk convenience samples are likely to be over- or underestimates.
DOI: 10.1371/journal.pone.0051876
发表时间: 2012-12-18
期刊: PLOS ONE
影响因子: 3.7
作者:
Simons, Daniel J.;Chabris, Christopher F.
通讯作者: Chabris, Christopher F.
DOI: 10.1086/323732
发表时间: 2001-12-01
影响因子: 7.2
作者:
Peterson, RA
通讯作者: Peterson, RA
DOI: 10.1093/pan/mpr057
发表时间: 2012-06-01
期刊: POLITICAL ANALYSIS
影响因子: 5.4
作者:
Berinsky, Adam J.;Huber, Gregory A.;Lenz, Gabriel S.
通讯作者: Lenz, Gabriel S.
DOI: 10.1177/1745691610393980
发表时间: 2011-01-01
影响因子: 12.6
作者:
Buhrmester, Michael;Kwang, Tracy;Gosling, Samuel D.
通讯作者: Gosling, Samuel D.
DOI: 10.1136/tobaccocontrol-2015-052897
发表时间: 2016-09
期刊: Tobacco control
影响因子: 5.2
作者:
Brewer NT;Morgan JC;Baig SA;Mendel JR;Boynton MH;Pepper JK;Byron MJ;Noar SM;Agans RP;Ribisl KM
通讯作者: Ribisl KM