Multilevel Random Mediation Analysis: A Comparison of Analytical Alternatives

  • Fang Luo
  • Hongyun Liu
Part of the Springer Proceedings in Mathematics & Statistics book series (PROMS, volume 89)


The present article focuses on the multilevel random mediation effects model (1-1-1) and examines its various analytical procedures. The performances of these procedures under a variety of conditions were compared using Monte Carlo simulations. We compared the multilevel random mediation model with two compact models: the multilevel fixed mediation model and the single-level traditional mediation model. The results showed better performance for the multilevel random mediation model. The results also indicated that we can obtain unbiased estimation of the mediation effect, the correct standard error, and proper hypothesis testing results from the multilevel random mediation model. Moreover, the differences between the multilevel fixed mediation model and the single-level traditional mediation model are minimal. Several implications and recommendations for this application are discussed.


Multilevel random mediation model Multilevel fixed mediation model Single-level mediation model Restricted maximum likelihood 


  1. Baron RM, Kenny DA (1986) The moderator–mediator variable distinction in social psychological research: conceptual, strategic, and statistical considerations. J Pers Soc Psychol 51(6): 1173–1182CrossRefGoogle Scholar
  2. Bauer DJ, Preacher KJ, Gil KM (2006) Conceptualizing and testing random indirect effects and moderated mediation in multilevel models: new procedures and recommendations. Psychol Methods 11(2):142–163CrossRefGoogle Scholar
  3. Bryk AS, Raudenbush SW (2002) Hierarchical linear models: applications and data analysis methods, 2nd edn. Sage, Newbury ParkGoogle Scholar
  4. Goodman LA (1960) On the exact variance of products. J Am Stat Assoc 55:708–713CrossRefzbMATHGoogle Scholar
  5. Imai K, Keele L, Tingley D (2010) A general approach to causal mediation analysis. Psychol Methods 15(4):309–334CrossRefGoogle Scholar
  6. Kenny DA, Korchmaros JD, Bolger N (2003) Lower level mediation in multilevel models. Psychol Methods 8(2):115–128CrossRefGoogle Scholar
  7. Kreft IGG (1996) Are multilevel techniques necessary? An overview, including simulation studies. California State University, Los AngelesGoogle Scholar
  8. Krull JL, MacKinnon DP (1999) Multilevel mediation modeling in group-based intervention studies. Eval Rev 23:418–444CrossRefGoogle Scholar
  9. Krull JL, MacKinnon DP (2001) Multilevel modeling of individual and group level mediated effects. Multivar Behav Res 36:249–277CrossRefGoogle Scholar
  10. Liu D, Zhang S, Wang L, Lee TW (2011) The effects of autonomy and empowerment on employee turnover: test of a multilevel model in teams. J Appl Psychol 96(6):305–1316Google Scholar
  11. MacKinnon DP (2008) Introduction to statistical mediation analysis. Erlbaum, New YorkGoogle Scholar
  12. MacKinnon DP, Lockwood CM, Hoffman JM, West SG, Sheets V (2002) A comparison of methods to test mediation and other intervening variable effects. Psychol Methods 7(1):83–104CrossRefGoogle Scholar
  13. MacKinnon DP, Lockwood CM, Williams J (2004) Confidence limits for the indirect effect: distribution of the product and resampling methods. Multivar Behav Res 39:99–128CrossRefGoogle Scholar
  14. Pituch KA, Stapleton LM (2008) The performance of methods to test upper-level mediation in the presence of nonnormal data. Multivar Behav Res 43:237–267CrossRefGoogle Scholar
  15. Pituch KA, Whittaker TA, Stapleton LM (2005) A comparison of methods to test for mediation in multisite experiments. Multivar Behav Res 40:1–23CrossRefGoogle Scholar
  16. Pituch KA, Stapleton LM, Kang JY (2006) A comparison of single sample and bootstrap methods to assess mediation in cluster randomized trials. Multivar Behav Res 41:367–400CrossRefGoogle Scholar
  17. Preacher KJ, Selig JP (2012) Advantages of monte carlo confidence intervals for indirect effects. Commun Methods Meas 6:77–98Google Scholar
  18. Preacher KJ, Zyphur MJ, Zhang Z (2010) A general multilevel SEM framework for assessing multilevel mediation. Psychol Methods 15(3):209–233CrossRefGoogle Scholar
  19. Preacher KJ, Zhang Z, Zyphur MJ (2011) Alternative methods for assessing mediation in multilevel data: the advantages of multilevel SEM. Struct Equ Model 18:161–182CrossRefMathSciNetGoogle Scholar
  20. Raudenbush SW, Sampson R (1999) Assessing direct and indirect effects in multilevel designs with latent variables. Sociol Methods Res 28:123–153CrossRefGoogle Scholar
  21. Shrout PE, Bolger N (2002) Mediation in experimental and nonexperimental studies: new procedures and recommendations. Psychol Methods 7(4):422–446CrossRefGoogle Scholar
  22. Shrout PE, Fleiss JL (1979) Intraclass correlations: uses in assessing rater reliability. Psychol Bull 86(2):420–428CrossRefGoogle Scholar
  23. Sobel M (1982) Some new results on indirect effects and their standard errors in covariance structure models. Sociol Methodol 16:159–186CrossRefGoogle Scholar
  24. Vandenabeele W (2009) The mediating effect of job satisfaction and organizational commitment on self-reported performance: more robust evidence of the PSM-performance relationship. Int Rev Adm Sci 75(1):11–34CrossRefGoogle Scholar
  25. Zhang Z, Zyphur MJ, Preacher KJ (2009) Testing multilevel mediation using hierarchical linear models: problems and solutions. Organ Res Methods 12:695–719CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Fang Luo
    • 1
  • Hongyun Liu
    • 1
  1. 1.National Innovation Center for Assessment of Basic Education QualitySchool of Psychology, Beijing Normal UniversityBeijingChina

Personalised recommendations