본문 바로가기
KERD
논문

이분형 종속변수를 포함하는 모형의 매개효과 검정

Testing the mediated effect of a model with a binary dependent variable

0

조회

0

다운로드

12

인용

0

참고문헌

키워드

주제분류심리과학

초록

매개효과 모형은 심리학 등의 여러 사회과학 분야에서 가장 활발히 이용되는 분석 방법 중하나지만, 이분형 등의 범주형 종속변수를 포함하는 경우의 매개효과 검정 방법은 상대적으로 잘 알려져 있지 않다. 본 연구는 지난 30여 년간 이루어진 이분형 종속변수를 포함하는매개모형의 효과 추정 방법에 관한 연구 흐름들을 통합하고, 연구자들이 자신의 자료에 적합한 접근 방식을 선택할 수 있도록 핵심 쟁점들을 체계적으로 논의하는 것을 목적으로 한다. 이에 따라 이분형 종속변수를 포함하는 모형의 매개효과 추정 방법을 크게 두 가지 접근법으로 나누어 탐색한다. 먼저, 선형 구조방정식 모형을 비선형 모형으로 확장하는 전통적인 접근의 관점에서 이분형 종속변수를 포함하는 모형의 매개효과 추정 방법을 다룬다. 다음으로는 매개모형의 형태나 자료의 분포를 특정하지 않고 비모수적으로 매개효과를 추정하는 인과추론 접근법을 소개하고, 이를 이분형 종속변수를 포함하는 모형으로 확장한다. 그리고 통계 프로그램을 이용하여 전통적인 접근법과 인과추론 접근법을 실제자료에 적용한 예시를 보이며, 마지막으로 여러 결과를 종합하여 두 접근법의 원리 및 특징과 한계점 등을 논의한다.

Abstract

The mediational model is one of the most actively used analytical methods in the social sciences or psychology. However, the methods of testing the mediated effect with categorical dependent variables have been relatively unknown. The aims of the present study are to integrate studies on the methods of estimating the mediated effect of the model with a binary dependent variable over the last 30 years and to discuss key issues in order to encourage researchers to choose the most appropriate approach to their data. To achieve this goal, we explore the two streams of estimating the mediated effect of the model with a binary dependent variable, traditional vs. causal inference approaches. For the traditional approach,we introduce and integrate several extended structural equation modeling methods that accommodate a binary dependent variable in the mediational model. Then, we introduce the causal inference approach which allows researchers to estimate the mediated effect non-parametrically without specifying the form or distribution of the model before estimation, and extend it into a model that includes a binary dependent variable. Finally, we illustrate the procedures for applying the traditional and the causal inference approaches using real data and discuss the results.

참고문헌 (74)

  1. 김덕준, "사회과학에서의 인과관계 추론", 사회과학연구, 29(1), pp.79~96 (2010)
  2. 김미정, "(의학 및 사회과학 연구를 위한) 통계적 인과 추론" (2018), 교우사
  3. 김준엽, "Drawing Causal Inferences Using Propensity Score Methods in Educational Research", 교육평가연구, 21(3), pp.219~242 (2008), 한국교육평가학회
  4. 박선미, "종단, 다층 및 범주형 자료의매개효과 분석방법", 박사, pp.2015
  5. Amos, "(SPSS", pp.배병렬, LISREL
  6. 강상진, "경향점수 추정 모형에 따른 매칭 및 인과효과 검정 결과 비교: 다층자료의 모의분석", 교육평가연구, 28(3), pp.701~730 (2015), 한국교육평가학회
  7. 신나래, "여성의 근로소득이 가정폭력 피해경험에 미치는 영향: 남성의 배우자 만족도 매개효과를 중심으로", 사회과학연구, 28(1), pp.23~39 (2017), 사회과학연구소[DOI]
  8. 신성자, "재한 몽골 노동자들의 사회적 고립감과 문제음주가 결혼불안정성에 미치는 영향: 문제음주의 매개효과 검증을 중심으로", 사회과학연구, 25(1), pp.375~402 (2014), 사회과학연구소
  9. 이은진, "의료사회복지사의 직무요구가 직무만족, 이직의도에 미치는 영향에 관한 연구", 사회복지연구, 48(2), pp.233~266 (2017), 한국사회복지연구회[DOI]
  10. 최세경, "자원획득 능력과 전략적 자원이 조직 정당성에 미치는 영향 : 제도적 동형화의 매개효과를 중심으로", 박사, 조직이론ㆍ인사관리, pp.2011
  11. 하여진, "인과매개모형을 활용한 영어 사교육 참여의 학업성취도 향상효과 분석: 서울시 중학생을 대상으로", 교육평가연구, 28(1), pp.77~95 (2015), 한국교육평가학회
  12. 한지나, "부모와의 갈등관계가 청소년의 외현화된 문제행동에 미치는 영향: 친구와의 갈등관계의 매개효과를 중심으로", 청소년복지연구, 18(2), pp.21~40 (2016), 한국청소년복지학회[DOI]
  13. Agresti, A., "Categorical data analysis" (2013), John Wiley & Sons
  14. Aiken, L. S., "Multiple regression: Testing and interpreting interactions" (1991), Sage
  15. Albert, J. M., "Generalized causal mediation analysis", Biometrics, 67(3), pp.1028~1038 (2011)
  16. Albert, J. M., "Sensitivity analyses for parametric causal mediation effect estimation", Biostatistics, 16(2), pp.339~351 (2015)
  17. Alwin, D. F., "The decomposition of effects in path analysis", American Sociological Review, 40(1), pp.37~47 (1975)
  18. Bareinboim, E., "Artificial Intelligence and Statistics", pp.100~108 (2012)
  19. Baron, R. M., "The moderator-mediator variable distinction in social psychological research : Conceptual, strategic, and statistical considerations", Journal of Personality and Social Psychology, 51(6), pp.1173~1182 (1986)
  20. Bollen, K. A., "Direct and indirect effects : Classical and bootstrap estimates of variability", Sociological Methodology, 20, pp.115~140 (1990)
  21. Cox, D. R., "The regression analysis of binary sequences", Journal of the Royal Statistical Society. Series B (Methodological), 20(2), pp.215~242 (1958)
  22. Daniel, R. M., "Causal mediation analysis with multiple mediators", Biometrics, 71(1), pp.1~14 (2015)
  23. De Stavola, B. L., "Mediation analysis with intermediate confounding : Structural equation modeling viewed through the causal inference lens", American Journal of Epidemiology, 181(1), pp.64~80 (2015)
  24. Efron, B., "Computers and the theory of statistics : Thinking the unthinkable", SIAM Review, 21(4), pp.460~480 (1979)
  25. Feinberg, S. E., "The analysis of cross-classified categorical data" (1977), MIT Press
  26. Finney, D. J., "Probit analysis" (1952), Cambridge
  27. Hayes, A. F., "Beyond Baron and Kenny : Statistical mediation analysis in the new millennium", Communication Monographs, 76(4), pp.408~420 (2009)
  28. Causal inference, path analysis and recursive structural equations models, "Holland, P. W.", ETS, 50~, pp.ETS Research Report Series, 1988(1) (1988)
  29. Hosmer, D. W., "Applied logistic regression (Vol. 398)" (2013), John Wiley & Sons
  30. Imai, K., "A general approach to causal mediation analysis", Psychological Methods, 15(4), pp.309~334 (2010)
  31. Imai, K., "Identification, inference and sensitivity analysis for causal mediation effects", Statistical Science, 25(1), pp.51~71 (2010)
  32. Imai, K., "Causal inference with differential measurement error : Nonparametric identification and sensitivity analysis", American Journal of Political Science, 54(2), pp.543~560 (2010)
  33. Judd, C. M., "Process analysis : Estimating mediation in treatment evaluations", Evaluation Review, 5(5), pp.602~619 (1981)
  34. Karlson, K. B., "Comparing regression coefficients between same-sample nested models using logit and probit : A new method", Sociological Methodology, 42(1), pp.286~313 (2012)
  35. Kaufman, J. S., "A further critique of the analytic strategy of adjusting for covariates to identify biologic mediation", Epidemiologic Perspectives &Innovations, 1(1), pp.4~ (2004)
  36. Lockwood, C. M., "Bootstrapping the standard error of the mediated effect", Proceedings of the 23rd annual meeting of SAS Users Group International, pp.997~1002 (1998)
  37. Long, J. S., "Regression models for categorical and limited dependent variables", Advanced quantitative techniques in the social sciences, pp.7~ (1997)
  38. MacKinnon, D. P., "Introduction to statistical mediation analysis" (2008), Routledge
  39. MacKinnon, D. P., "Estimating mediated effects in prevention studies", Evaluation Review, 17(2), pp.144~158 (1993)
  40. MacKinnon, D. P., "The intermediate endpoint effect in logistic and probit regression", Clinical Trials, 4(5), pp.499~513 (2007)
  41. MacKinnon, D. P., "A comparison of methods to test mediation and other intervening variable effects", Psychological methods, 7(1), pp.83~104 (2002)
  42. MacKinnon, D. P., "Confidence limits for the indirect effect : Distribution of the product and resampling methods", Multivariate Behavioral Research, 39(1), pp.99~128 (2004)
  43. MacKinnon, D. P., "A simulation study of mediated effect measures", Multivariate Behavioral Research, 30(1), pp.41~62 (1995)
  44. McKelvey, R. D., "A statistical model for the analysis of ordinal level dependent variables", Journal of Mathematical Sociology, 4(1), pp.103~120 (1975)
  45. Millsap, R. E., "The SAGE handbook of quantitative methods in psychology" (2009), Sage Publications
  46. Muthén, B. O., "A structural probit model with latent variables", Journal of the American Statistical Association, 74(368), pp.807~811 (1979)
  47. Muthén, B. O., "A general structural equation model with dichotomous, ordered categorical, and continuous latent variable indicators", Psychometrika, 49(1), pp.115~132 (1984)
  48. Muthén, B. O., "Applications of causally defined direct and indirect effects in mediation analysis using SEM in Mplus", Manuscript submitted for publication, 1~110 (2011)
  49. Muthén, B. O., "Causal effects in mediation modeling : An introduction with applications to latent variables", Structural Equation Modeling, 22(1), pp.12~23 (2015)
  50. Muthén, B. O., "Regression and mediation analysis using Mplus" (2016), Muthén & Muthén
  51. Neyman, J. S., "On the application of probability theory to agricultural experiments. Essay on principles. Section 9.(Translated and edited by DM Dabrowska and TP Speed, Statistical science (1990), 5, 465-480)", Annals of Agricultural Sciences, 10, pp.1~51 (1990)
  52. Nguyen, T. Q., "Causal mediation analysis with a binary outcome and multiple continuous or ordinal mediators : Simulations and application to an alcohol intervention", Structural Equation Modeling, 23(3), pp.368~383 (2016)
  53. Pearl, J., "Causal diagrams for empirical research", Biometrika, 82(4), pp.669~688 (1995)
  54. Pearl, J., "Proceedings of the seventeenth conference on uncertainty in artificial intelligence", pp.411~420 (2001), Morgan Kaufman
  55. Pearl, J., "Causality" (2009), Cambridge university press
  56. Pearl, J., "The foundations of causal inference", Sociological Methodology, 40(1), pp.75~149 (2010)
  57. Pearl, J., "The causal mediation formula-a guide to the assessment of pathways and mechanisms", Prevention Science, 13(4), pp.426~436 (2012)
  58. Pearl, J., "Interpretation and identification of causal mediation", Psychological Methods, 19(4), pp.459~481 (2014)
  59. Pearl, J., "Causal inference in statistics: a primer" (2016), John Wiley & Sons
  60. Powers, D., "Statistical methods for categorical data analysis" (2008), Emerald Group Publishing
  61. Preacher, K. J., "SPSS and SAS procedures for estimating indirect effects in simple mediation models", Behavior Research Methods, Instruments, & Computers, 36(4), pp.717~731 (2004)
  62. Preacher, K. J., "Asymptotic and resampling strategies for assessing and comparing indirect effects in multiple mediator models", Behavior Research Methods, 40(3), pp.879~891 (2008)
  63. Robins, J., "A new approach to causal inference in mortality studies with a sustained exposure period-Application to control of the healthy worker survivor effect", Mathematical Modelling, 7, pp.1393~1512 (1986)
  64. Robins, J. M., "Highly structured stochastic systems", pp.70~81 (2003), Oxford University Press
  65. Robins, J. M., "Identifiability and exchangeability for direct and indirect effects", Epidemiology, 3(2), pp.143~155 (1992)
  66. Rubin, D. B., "Estimating causal effects of treatments in randomized and nonrandomized studies", Journal of Educational Psychology, 66(5), pp.688~701 (1974)
  67. Rubin, D. B., "Direct and indirect causal effects via potential outcomes", Scandinavian Journal of Statistics, 31(2), pp.161~170 (2004)
  68. Shrout, P. E., "Mediation in experimental and nonexperimental studies : new procedures and recommendations", Psychological Methods, 7(4), pp.422~445 (2002)
  69. VanderWeele, T. J., "Bias formulas for sensitivity analysis for direct and indirect effects", Epidemiology, 21(4), pp.540~551 (2010)
  70. VanderWeele, T. J., "Explanation in causal inference: methods for mediation and interaction" (2015), Oxford University Press
  71. VanderWeele, T. J., "Conceptual issues concerning mediation, interventions and composition", Statistics and its Interface, 2(4), pp.457~468 (2009)
  72. VanderWeele, T. J., "Odds ratios for mediation analysis for a dichotomous outcome", American Journal of Epidemiology, 172(12), pp.1339~1348 (2010)
  73. Wang, W., "Estimation of causal mediation effects for a dichotomous outcome in multiple‐mediator models using the mediation formula", Statistics in Medicine, 32(24), pp.4211~4228 (2013)
  74. Winship, C., "Structural equations and path analysis for discrete data", American Journal of Sociology, 89(1), pp.54~110 (1983)

관련 논문AI추천

이 간행물의 다른 논문 (5건)