Selection Bias in Web Surveys

被引:740
作者
Bethlehem, Jelke [1 ]
机构
[1] Stat Netherlands, Dept Methodol, The Hague, Netherlands
关键词
Adjustment weighting; bias; online survey; reference survey; self-selection; under-coverage; web survey;
D O I
10.1111/j.1751-5823.2010.00112.x
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
P>At first sight, web surveys seem to be an interesting and attractive means of data collection. They provide simple, cheap, and fast access to a large group of potential respondents. However, web surveys are not without methodological problems. Specific groups in the populations are under-represented because they have less access to Internet. Furthermore, recruitment of respondents is often based on self-selection. Both under-coverage and self-selection may lead to biased estimates. This paper describes these methodological problems. It also explores the effect of various correction techniques (adjustment weighting and use of reference surveys). This all leads to the question whether properly design web surveys can be used for data collection. The paper attempts to answer this question. It concludes that under-coverage problems may solve itself in the future, but that self-selection leads to unreliable survey outcomes.Resume A premiere vue, les enquetes en ligne semble etre un moyen interessant et attrayant de collecte de donnees. Ils fournissent un acces simple, rapide et peu couteux a un grand groupe de repondants potentiels. Les enquetes en ligne ne sont toutefois pas sans problemes methodologiques. Certains groupes au sein des populations sont sous-representes parce qu'ils ont un acces restreint a Internet. En outre, le recrutement des personnes interrogees est souvent fonde sur l'auto-selection. Sous-couverture et auto-selection peuvent toutes deux etre la source d'estimations biaisees. Le present article decrit ces problemes methodologiques. Il explore egalement l'effet des differentes techniques de correction (ponderation corrective et utilisation d'enquetes de reference). Tout ceci amene a la question de savoir si des enquetes en ligne bien concues sont propres a etre utilisees pour la collecte de donnees. L'article tente de repondre a cette question. Il conclut que le probleme de la sous-couverture pourrait se resoudre dans l'avenir, mais que l'auto-selection aboutit a des resultats d'enquete non fiables.
引用
收藏
页码:161 / 188
页数:28
相关论文
共 45 条
[1]  
[Anonymous], JB ICT SAMENLEVING D
[2]  
[Anonymous], 2008, INTERNET MAIL MIXED
[3]  
[Anonymous], 2009, 09015 STAT NETH
[4]  
[Anonymous], 2002, SURVEY NONRESPONSE
[5]  
[Anonymous], 1953, SAMPLING TECHNIQUES
[6]  
Bethlehem J., 1988, J. Off. Stat., V4, P251
[7]  
Bethlehem J., 2009, APPL SURVEY METHODS
[8]  
Bethlehem J.G, 2007, 07001 STAT NETH
[9]  
BORSCHSUPAN A, 2004, CORRECTING PARTICIPA
[10]   Address to the Economic Science and Statistics Section of the British Association for the advancement of science, York, 1906. [J].
Bowley, AL .
JOURNAL OF THE ROYAL STATISTICAL SOCIETY, 1906, 69 :540-558