RESPONSE PATTERN ANALYSIS: ASSURING DATA INTEGRITY IN EXTREME RESEARCH SETTINGS

• 成果类型: Article
• 署名作者: Christensen, Lisa Jones; Siemsen, Enno; Branzei, Oana; Viswanathan, Madhu
• 署名单位: Brigham Young University; University of Wisconsin System; University of Wisconsin Madison; Western University (University of Western Ontario); University of Illinois System; University of Illinois Urbana-Champaign
• 刊物名称: STRATEGIC MANAGEMENT JOURNAL
• ISSN/ISSBN: 0143-2095
• DOI: 10.1002/smj.2497
• 发表日期: 2017
• 页码: 471-482
• 关键词: survey research; Survey design; survey administration; research methods; nontraditional contexts

摘要

Research summary: Strategy scholars increasingly conduct research in nontraditional contexts. Such efforts often require the assistance of third-party intermediaries who understand local culture, norms, and language. This reliance on intermediation in primary or secondary data collection can elicit agency breakdowns that call into question the reliability, analyzability, and interpretability of responses. Herein, we investigate the causes and consequences of intermediary bias in the form of faked data and we offer Response Pattern Analysis as a statistical solution for identifying and removing such problematic data. By explicating the effect, illustrating how we detected it, and performing a controlled field experiment in a developing country to test the effectiveness of our methodological solution, we encourage researchers to continue to seek data and build theory from unique and understudied settings. Managerial summary: Any form of survey research contains the risk of interviewers faking data. This risk is particularly difficult to mitigate in Base-of-Pyramid or developing country contexts where researchers have to rely on intermediaries and forms of control are limited. We provide a statistical technique to identify a faking interviewer's ex post data collection, and remove the associated data prior to analysis. Using a field experiment where we instruct interviewers to fake the data, we demonstrate that the algorithm we employ achieves a 90 percent accuracy in terms of differentiating faking from nonfaking interviewers. Copyright (C) 2016 John Wiley & Sons, Ltd.