Generalized Varying Coefficient Mediation Models

Abstract

Motivated by an analysis of causal mechanism from economic stress to entrepreneurial withdrawals through depressed affect, we develop a two-layer generalized varying coefficient mediation model. This model captures the bridging effects of mediators that may vary with another variable, by treating them as smooth functions of this variable. It also allows various response types by introducing the generalized varying coefficient model in the first layer. The varying direct and indirect effects are estimated through spline expansion. The theoretical properties of the estimated direct and indirect coefficient functions including estimation biases, asymptotic distributions and so forth, are explored. Simulation studies validate the finite-sample performance of the proposed estimation method. A real data analysis based on the proposed model discovers some interesting behavioral economic phenomenon, that self-efficacy influences the deleterious impact of economic stress, both directly and indirectly through depressed affect, on business owners’ withdrawal intentions.

Keywords

Mediation analysis / Varying coefficient model / Direct and indirect effect / Generalized linear model

References

[1] Bandura, A., Freeman, W., Lightsey, R.: Self-efficacy: The Exercise of Control (1997)

[2] Baron RA. The role of affect in the entrepreneurial process. Acad. Manag. Rev.. 2008, 33 2 328-340

[3] Baron RM, Kenny DA. The moderator-mediator variable distinction in social psychological research: Conceptual, strategic, and statistical considerations. J. Pers. Soc. Psychol.. 1986, 51 6 1173

[4] Baum A, Fleming R, Reddy DM. Unemployment stress: loss of control, reactance and learned helplessness. Soc. Sci. Med.. 1986, 22 5 509-516

[5] Cai Z, Fan J, Li R. Efficient estimation and inferences for varying-coefficient models. J. Am. Stat. Assoc.. 2000, 95 451 888-902

[6] Chen CC, Greene PG, Crick A. Does entrepreneurial self-efficacy distinguish entrepreneurs from managers?. J. Bus. Ventur.. 1998, 13 4 295-316

[7] De Boor C. A Practical Guide to Splines. 1978 New York: Springer

[8] Dekker SW, Schaufeli WB. The effects of job insecurity on psychological health and withdrawal: a longitudinal study. Aust. Psychol.. 1995, 30 1 57-63

[9] Ditlevsen S, Christensen U, Lynch J . A comparison of methods to test mediation and other intervening variable effects. Epidemiology. 2005, 16 114-120

[10] Egan V, Tosanguan P. Coping strategies of entrepreneurs in economic recession: a comparative analysis of Thais and European expatriates in pattaya, thailand. J. Asia Entrepreneurship Sustain.. 2009, 5 3 17

[11] Hellgren J, Sverke M. Does job insecurity lead to impaired well-being or vice versa? estimation of cross-lagged effects using latent variable modelling. J. Org. Behav.: Int. J. Ind. Occup. Org. Psychol. Behav.. 2003, 24 2 215-236

[12] Huang JZ, Wu CO, Zhou L. Varying-coefficient models and basis function approximations for the analysis of repeated measurements. Biometrika. 2002, 89 1 111-128

[13] Huang JZ, Wu CO, Zhou L. Polynomial spline estimation and inference for varying coefficient models with longitudinal data. Stat. Sin.. 2004, 14 763-788

[14] Huang Y, Pan W. Hypothesis test of mediation effect in causal mediation model with high-dimensional continuous mediators. Biometrics. 2016, 72 2 402-413

[15] Huang Y, Vander Weele TXL. Joint analysis of SNP and gene expression data in genetic association studies of complex diseases. Ann. Appl. Stat.. 2014, 8 1 352 3981558

[16] Lange T, Hansen J. Direct and indirect effects in a survival context. Epidemiology. 2011, 22 4 575-581

[17] Latham S. Contrasting strategic response to economic recession in start-up versus established software firms. J. Small Bus. Manag.. 2009, 47 2 180-201

[18] Liao, Y., Liu, J., Coffman, D., et al.: Varying coefficient mediation model and application to analysis of behavioral economics data. J. Bus. Econ. Stat. https://doi.org/10.1080/07350015.2021.197108 (2021)

[19] Luo C, Fa B, Yan Y . High-dimensional mediation analysis in survival models. PLoS Comput. Biol.. 2020, 16 4

[20] MacKinnon DP. Introduction to Statistical Mediation Analysis. 2008 New York: Routledge

[21] MacKinnon DP, Lockwood CM, Hoffman JM . A comparison of methods to test mediation and other intervening variable effects. Psychol. Methods. 2002, 7 1 83-104 2819363

[22] Pollack JM, Vanepps EM, Hayes AF. The moderating role of social ties on entrepreneurs’ depressed affect and withdrawal intentions in response to economic stress. J. Org. Behav.. 2012, 33 6 789-810

[23] Seligman ME. Learned helplessness. Annu. Rev. Med.. 1972, 23 1 407-412

[24] Sequeira J, Mueller SL, McGee JE. The influence of social ties and self-efficacy in forming entrepreneurial intentions and motivating nascent behavior. J. Dev. Entrep.. 2007, 12 3 275-293

[25] Sohn MB, Hongzhe L. Compositional mediation analysis for microbiome studies. Ann. Appl. Stat.. 2019, 13 1 661-681

[26] Valeri L, Lin X, VanderWeele T. Mediation analysis when a continuous mediator is measured with error and the outcome follows a generalized linear model. Stat. Med.. 2014, 33 28 4875-4890 4224977

[27] VanderWeele T, Tchetgen EJ. Mediation analysis with time varying exposures and mediators. J. R. Stat. Soc.: Ser. B (Stat. Methodol.). 2017, 79 3 917-938

[28] VanderWeele T, Vansteelandt S. Odds ratios for mediation analysis for a dichotomous outcome. Am. J. Epidemiol.. 2010, 172 12 1339-1348 2998205

[29] VanderWeele T, Vansteelandt S. Mediation analysis with multiple mediators. Epidemiol. Methods. 2014, 2 1 95-115 4287269

[30] Verhasselt A. Generalized varying coefficient models. Stat. Sin.. 2014, 24 1 147-171

[31] Wang L, Zhang Z. Estimating and testing mediation effects with censored data. Struct. Equ. Model.. 2011, 18 1 18-34

[32] Wright S. On the nature of size factors. Genetics. 1918, 3 4 367 1200442

[33] Wright S. The method of path coefficients. Ann. Math. Stat.. 1934, 5 3 161-215

[34] Yang G, Yang S, Li R. Feature screening in ultrahigh dimensional generalized varying-coefficient models. Stat. Sin.. 2020, 30 1049-1067 7516887

[35] Zhou R, Wang L, Zhao S. Estimation and inference for the indirect effect in high-dimensional linear mediation models. Biometrika. 2020, 107 3 573-589

Funding

NNSFC(11701034, 71988101)

Directorate for Mathematical and Physical Sciences(1820702, 1953196 and 2015539)