Are we in right path for mediation analysis? Reviewing the literature and proposing robust guidelines

被引:118
作者
Rasoolimanesh, S. Mostafa [1 ]
Wang, Mingzhuo [2 ]
Roldan, Jose L. [3 ]
Kunasekaran, Puvaneswaran [1 ]
机构
[1] Taylors Univ, Ctr Res & Innovat Tourism CRiT, Fac Social Sci & Leisure Management, 1 Jalan Taylors, Subang Jaya 47500, Selangor, Malaysia
[2] Weifang Univ Sci & Technol, Dept Econ & Management, 166 Xueyuan Rd, Weifang 262700, Shandong, Peoples R China
[3] Univ Seville, Dept Business Adm & Mkt, C Ramon & Cajal 1, Seville 41018, Spain
关键词
Mediation analysis; Mediator construct; Mediation hypothesis; Statistical assessment of mediation; Interpretation of mediation analysis; STATISTICAL SIGNIFICANCE; CONFIDENCE-INTERVALS; TESTING MEDIATION; PRODUCT; VARIABLES; LIMITS; BARON;
D O I
10.1016/j.jhtm.2021.07.013
中图分类号
F [经济];
学科分类号
02 ;
摘要
This research proposes guidelines for hypothesizing and assessing mediation concepts for tourism and hospitality research. The mediation analysis plays a significant role in theory development and advancement in social science disciplines and is significantly increasing in recent years. However, following questionable hypothesis development, statistical assessment, and interpretation of results cause biased and unreliable understanding of mediation analysis and questionable findings for theory building and development. Drawing from a systematic review of 536 mediation papers published in five recent years (2016-2020) in top tier tourism and hospitality journals, the findings revealed several critical issues in different mediation analysis steps, including hypothesis development, mediation assessment and interpretation of results. The results highlighted the common methodological mistakes and misconceptions for mediation analysis. This paper provides robust guidelines for mediation analysis by highlighting those methodological issues and has significant theoretical and methodological contributions in the tourism and hospitality field.
引用
收藏
页码:395 / 405
页数:11
相关论文
共 52 条
[1]   STATISTICAL INFERENCE WITH PLSC USING BOOTSTRAP CONFIDENCE INTERVALS [J].
Aguirre-Urreta, Miguel I. ;
Ronkko, Mikko .
MIS QUARTERLY, 2018, 42 (03) :1001-+
[2]  
[Anonymous], 2017, ORGAN RES METHODS, DOI [10.1177/1094428115627498, DOI 10.1177/1094428115627498]
[3]  
[Anonymous], 2012, INTRO STAT MEDIATION
[4]   THE MODERATOR MEDIATOR VARIABLE DISTINCTION IN SOCIAL PSYCHOLOGICAL-RESEARCH - CONCEPTUAL, STRATEGIC, AND STATISTICAL CONSIDERATIONS [J].
BARON, RM ;
KENNY, DA .
JOURNAL OF PERSONALITY AND SOCIAL PSYCHOLOGY, 1986, 51 (06) :1173-1182
[5]   Controlling for endogeneity with instrumental variables in strategic management research [J].
Bascle, Guilhem .
STRATEGIC ORGANIZATION, 2008, 6 (03) :285-327
[6]  
Bollen K. A., 1990, Sociol. Methodol, V20, P115, DOI [10.2307/271084, DOI 10.2307/271084]
[7]   Yes, But What's the Mechanism? (Don't Expect an Easy Answer) [J].
Bullock, John G. ;
Green, Donald P. ;
Ha, Shang E. .
JOURNAL OF PERSONALITY AND SOCIAL PSYCHOLOGY, 2010, 98 (04) :550-558
[8]   Testing mediation and suppression effects of latent variables - Bootstrapping with structural equation models [J].
Cheung, Gordon W. ;
Lau, Rebecca S. .
ORGANIZATIONAL RESEARCH METHODS, 2008, 11 (02) :296-325
[9]   On the frequency function of xy [J].
Craig, CC .
ANNALS OF MATHEMATICAL STATISTICS, 1936, 7 :1-15
[10]  
Danks NP, 2019, APPLYING PARTIAL LEAST SQUARES IN TOURISM AND HOSPITALITY RESEARCH, P35, DOI 10.1108/978-1-78756-699-620181003