脈絡變數的多層次潛在變數模式分析：口試評分者效應的多層次結構方程模式應用

Multilevel Latent Variable Modeling of Contextual Variables: Application of Multilevel Structural Equation Modeling on Rater Effects

10.6129/CJP.2007.4904.05

邱皓政(Haw-Jeng Chiou)

脈絡變數 ； 潛在脈絡變數 ； 多層次資料 ； 多層次結構方程模式 ； 評分者效應 ； contextual variables ； latent contextual variables ； multilevel data ； multilevel structural equation modeling ； rater effects

中華心理學刊

49卷4期（2007 / 12 / 01）

383 - 405

繁體中文

潛在構念的估計是社會與行為科學研究的重要命題，結構方程模式取向是當代據以進行潛在構念估計與關係探究重要典範，但是，如果研究樣本涉及叢集抽樣而呈現階層結構，研究者即必須進行多層次結構方程模式分析(MSEM)。階層資料的重要特性是低階層次變數在高階會形成脈絡變數，因此MSEM分析必需能夠處理潛在脈絡變數模型的萃取與模型評估。本文的目的，即在說明如何利用MSEM程序來進行潛在脈絡變數的因素模型與結構模型分析，並以一項口試實證資料（76位教師甄試口試委員針對841位考生的口試評分資料），以Mplus4進行單層次與多層次結構方程模式分析。分析結果證實了MSEM程序可以有效分離考生共變矩陣與評審共變矩陣，並證實了個體層次與總體層次的潛在因素模型並不相同，為一非等值模型(non-equivalent model)。個體層次測量變數在評審層次是一個單一完整的潛在構念，亦即方法效應或月暈效果的概念，但在考生層次則仍保有原先的二因素架構。本文的結論指出，MSEM比傳統的MLM取向在處理脈絡變數上更具有彈性，在方法學上具有重要的價值，但是在技術層次仍有諸多有待突破的瓶頸，值得進一步深究。

The estimation of latent construct is the core issue of social and behavioral science. Structural equation modeling is the most important paradigm for estimation and for exploring the relationships among constructs. If the data for analysis involving multilevel or clustered structure, however, the multilevel SEM have to be applied for the special form of dataset. One of the features of multilevel data is that the observed variables in the individual level could be aggregated as a contextual variable into higher level. In terms of latent construct, contextual variable may behave as a latent form and should be estimated in a way of factorial analysis instead of manifest procedure. In a circumstance that the latent contextual variables have significant effects on dependent variable is called latent contextual effects. The purpose of present paper is to clarify the significance of the latent contextual effects in the social research. Rating data of oral examination examined in the present study contains a total of 76 raters and 841 interviewees. A series of single and multiple level SEM models was proposed for examining the latent contextual effects. Results of Mplus indicated that the MSEM modeling can effectively extract the latent contextual variables and furthermore used to explain the dependent variables. Different factorial structure on latent contextual variables in both macro and micro level reveals that the contextual model is not equivalent across levels. The present study proved that the MSEM approach to examine contextual variables is more flexibility than traditional MLM paradigm. However, technical as well as methodological issues have to be solved.

1. Allen, M. J.,Yen, W. M.(2002).Introduction to measurement theory.Long Grove, IL:Waveland Press, Inc.
2. Anderson, J. C.,Gerbing, D. W.(1988).Structural equation modeling in practice: A review and recommended two-step approach.Psychological Bulletin,103,411-423.
3. Anderson, N.,Shackleton, V.(1990).Decision making in the graduate selection interview: A field study.Journal of Occupational Psychology,63,63-76.
4. Bagozzi, R.P.,Yi, Y.(1988).On the Evaluation of Structural Equation Models.Journal of the Academy of Marketing Science,16,74-94.
5. Bandalos, D. L.(2001).The effects of item parceling on goodness-of-fit and parameter estimate bias in structural equation modeling.Structural Equation Modeling,9,78-102.
6. Bandalos, D. L.,Finney, S. J.,G. A. Marcoulides,R. E. Schumacker (Eds.)(2001).New developments and techniques in structural equation modeling.Mahwah, NJ:Lawrence Erlbaum Associates.
7. Baskett, G. D.(1973).Interview Decision as Determined by Competency and Attitude Similarity.Journal of Applied Psychology,57(3),343-345.
8. Bentler, P. M.,Lee, S. Y.(1979).A statistical development of three-mode factor analysis.British Journal of Mathematical and Statistical Psychology,32,87-104.
9. Bentler, P. M.,Liang, J.,S. P. Reise,N. Duan (Eds.)(2003).Multilevel modeling: Methodological advances, issues, and applications.Mahwah, NJ:Lawrence Erlbaum Associates.
10. Bollen, K. A.(1989).Structural equation modeling with latent variables.New York:John Wiley.
11. Campbell, D. T.,Fiske, D. W.(1959).Convergent and discriminant validation by multitrait-multimethod matrix.Psychological Bulletin,56,81-105.
12. Cheng, M.,Au, K.(2005).Applications of multilevel structural equation modeling into cross-cultural research.Structural Equation Modeling,12(4),598-619.
13. Cohen, J.(1988).Statistical power analysis for the behavioral sciences.Hillsdale, NJ:Eribaum.
14. Courgeau, D.(2003).Methodology and epistemology of multilevel analysis: Approaches from different social sciences.Norwell, MA:Kluwer.
15. Cronbach, L. J.,Webb, N.(1979).Between class and within class effects in a reported aptitude × treatment interaction: a reanalysis of a study by G. L. Anderson.Journal of Educational Psychology,67,717-724.
16. Curran, P. J.(2003).Have multilevel models been structural equation models all along?.Multivariate Behavioral Research,38,529-569.
17. De Silva, M.(2005).UK,Department of Epidemiology and Population Health, London School of Hygiene and Tropical Medicine.
18. Duncan, O. D.,Curzort, R. P.,Duncan, R. P.(1966).Statistical geography: Problems in analyzing areal data.Glencoe, IL:Free Press.
19. Ferron, J.,Dailey, R. F.,Yi, Q.(2002).Effects of misspecifying the first-level error structure in two-level models of change.Multivariate Behavioral Research,37,379-403.
20. Ferron, J.,Hess, M. R.,Hogarty, K. Y.,Dedrick, R. F.,Kromrey, J. D.,Lang, T. R.,Niles, J.(2004).Hierarchical linear modeling: A review of methodological issues and applications.Paper presented at the 2004 annual meeting of American Educational Research Association,San Diego:
21. Goldstein, H.(2003).Multilevel statistical models.London:Arnold.
22. Goldstein, H.,Browne, W.,G.A. Marcoulides,I. Moustaki (Eds.)(2001).Latent variable and latent structure models.Mahwah: NJ:Lawrence Erlbaum Associates.
23. Goldstein, H.,McDonald, R.(2003).A general model for the analysis of multilevel data.Psychometrika,53,455-467.
24. Graves, L. M.,Powell, G. N.(1988).An investigation of sex discrimination in recruiters` evaluations of actual applicants.Journal of Applied Psychology,73,20-29.
25. Graves, L. M.,Powell, G. N.(1995).The effect of sex similarity on recruiters` evaluations of actual applicants: A test of the similarity-attraction paradigm.Personnel Psychology,48,85-98.
26. Heck, R. H.,G.A. Marcoulides,R.E. Schumacker (Eds.)(2001).New developments and techniques in structural equation modeling.Mahwah, NJ:Lawrence Erlbaum Associates.
27. Heck, R. H.,Thomas, S. L.(2000).An introduction to multilevel modeling techniques.Mahwah, NJ:Lawrence Erlbaum Associates.
28. Applied multilevel analysis
29. Hox, J. J.(2002).Multilevel analysis: Techniques and applications.Mahwah, NJ:Lawrence Erlbaum Associates.
30. Hox, J. J.,Maas, C. J. M.(2001).The accuracy of multilevel structural equation modeling with pseudobalanced groups and small samples.Structural Equation Modeling,8,157-174.
31. Jedidi, K.,Ansari, A.,G. A. Marcoulides,R. E. Schumacker (Eds.)(2001).New developments and techniques in structural equation modeling.Mahwah, NJ:Lawrence Erlbaum Associates.
32. Jöreskog, K. G.,A. S. Goldberger,O. D. Duncan (Eds.)(1973).Structural equation models in the social science.New York:Academic.
33. Jöreskog, K. G.,Sorbom, D.(2004).LISREL 8.7.Lincolnwood, IL:Scientific Software International, Inc.
34. Kaplan, D.,Elliott, P. R.(1997).A didactic example of multilevel structural equation modeling applicable to the study of organizations.Structural Equation Modeling,4,1-24.
35. Kaplan, D.,R. H. Hoyle (Ed.)(1995).Structural equation modeling: concepts, issues, and applications.Newbruy Park, CA:Sage.
36. Kenny, D. A.,Kashy, D. A.(1992).The analysis of the multitrait-multimethod matrix by Confirmatory factor analysis.Psychological Bulletin,112,165-172.
37. Kreft, I.,de Leeuw, J.(1998).Introducing multilevel modeling.Newbury Park, CA:Sage.
38. Lee, S. Y.,Shi, J.Q.(2001).Maximum likelihood estimation of two-level latent variable models with mixed continuous and polytomous data.Biometrics,57,787-794.
39. Loehlin, J. C.(2004).Latent variable models: An introduction to factor, path, and structural equation analysis.Mahwah, NJ:Lawrence Erlbaum Associates.
40. Lord, F. M.(1977).A broad-range tailored test of verbal ability.Applied Psychological Measurement,14,117-138.
41. Lowe, N. K.,Ryan-Wenger, N. M.(1992).Beyond Campbell and Fiske: Assessment of convergent and discriminant validity.Research in Nursing and Health,15,67-75.
42. MacCallum, R. C.,Widaman, K. F.,Zhang, S.,Hong, S.(1999).Sample size in factor analysis.Psychological Methods,4,84-99.
43. Macintyre, S.,Ellaway, A.,Cummins, S.(2002).Place effects on health: How can we conceptualise, operationalise and measure them?.Social Science and medicine,55,125-139.
44. Macintyre, S.,Ellaway, A.,I. Kawachi,L. Berknman,F. Oxford (Eds.)(2003).Neighbourhoods and health.Oxford University Press.
45. Marsh, H. W.,Hocevar, D.(1988).A new, more powerful method of multitrait-multimethod analysis.Journal of Applied Psychology,73,107-117.
46. McDonald, R. P.(1994).The bilevel reticular action model for path analysis with latent variables.Sociological Methods and Research,22,399-413.
47. McDonald, R. P.,Ho, M. R.(2002).Principles and practice in reporting structural equation analysis.Psychological Methods,7,64-82.
48. Muthén, B. O.(1989).Latent variable modeling in heterogeneous populations.Psychometrika,54,557-585.
49. Muthén, B. O.(1990).Means and covariance structure analysis of hierarchical data.Los Angeles:UCLA Statistics series.
50. Muthén, B. O.(1994).Multilevel covariance structure analysis.Sociological Methods and Research,22,376-398.
51. Muthén, B. O.,Satorra, A.,Bock, R.D. (Ed.)(1989).Multilevel analysis of educational data.San Diego:Academic Press.
52. Muthén, L. K.,Muthén, B. O.(2004).Mplus user`s guide.Log Angeles, CA:Muthen & Muthen.
53. Niu, W.,Sternberg, R. J.(2001).Cultural influences on artistic creativity and its evaluation.International Journal of Psychology,36(4),225-241.
54. Podsakoff, P.M.,MacKenzie, S.B.,Lee, J.Y.,Podsakoff, N.P.(2003).Common method biases in behavioral research: A critical review of the literature and recommended remedies.Journal of Applied Psychology,88(5),879-903.
55. Rabe-Hesketh, S.,Skrondal, A.,Zheng, X.,S.-Y. Lee (Ed.)(2007).Handbook of Latent Variable and Related Models.Amsterdam:Elsevier.
56. Rand, T. M.,Wexely, K. N.(1975).Demonstration of the effect, "similar to me", in simulated employment interview.Psychological Reports,36,535-544.
57. Raudenbush, S. W.,Bryk, A. S.(2002).Hierarchical linear models: Applications and data analysis methods.Newbury Park, CA:Sage.
58. Raudenbush, S. W.,Bryk, A. S.,Cheong, Y. F.,Congdon, R. T.(2004).HLM 6: Hierarchical Linear and Nonlinear Modeling.Lincolnwood, IL:Scientific Software International, Inc.
59. Raudenbush, S. W.,I. Kawachi,L. Berknman,F. Oxford (Eds.)(2003).Neighbourhoods and health.Oxford University Press.
60. Raudenbush, S. W.,Sampson, R. J.(1999).Ecometrics: Toward a science of assessing ecological settings, with application to the systematic social observation of neighbourhoods.Sociological Methodology,29,1-41.
61. Raza, S. M.,Carpenter, B.N.(1987).A model of hiring decisions in real employment interviews.Journal of Applied Psychology,72,596-603.
62. Roberts, J. K.(2002).The importance of the intraclass correlation in multilevel and hierarchical linear modeling design.Multiple Linear Regression Viewpoints,28,19-31.
63. Robinson, W. S.(1950).Ecological correlations and the behaviour of individuals.American Sociological Review,15,351-357.
64. Snijders, T.,Bosker, R.(1999).Multilevel Analysis: An Introduction to Basic and Advanced Multilevel Modelling.Thousand Oaks, CA:Sage.
65. Stephenson, R.(2006).Contextual influences on the use of health facilities for childbirth in Africa.American Journal of Public Health,96,84-93.
66. Tabachnick, B. G.,Fidell, L. S.(2006).Using Multivariate Statistics.Boston, MA:Allyn and Bacon.
67. 余民寧(2006)。潛在變數模式：SIMPLIS的應用。台北市:高等教育出版公司。
68. 呂秋萍(2005)。碩士論文(碩士論文)。國立政治大學教育研究所未出版之碩士論文。
69. 邱皓政(2003)。結構方程模式：LISREL的理論、技術與應用。台北市:雙葉書廊有限公司。
70. 邱皓政、溫福星(2007)。脈絡效果的階層線性模式：以組織創新氣氛與創意表現爲例。教育與心理研究，30(1)，1-35。
71. 黃芳銘(2003)。結構方程模式理論與應用。台北市:五南圖書公司。
72. 溫福星(2006)。階層線性模式：原理、方法與運用。台北市:雙葉書廊有限公司。
73. 謝臥龍(1997)。優良國中教師特質之德懷術分析。教育研究資訊，5(3)，14-28。

1. 蔡心怡、葉允棋、陳美燕(2014)。以多層次線性模型探討大型運動賽會服務品質知覺之研究。台灣體育運動管理學報，14(1)，1-26。
2. 曾明基(2016)。家庭與學校差異對國中生數學成就影響之研究。臺北市立大學學報，47(1)，23-40。
3. 陳尚綾、林美珠、王麗斐、王郁琮(2012)。個人知覺與團體脈絡之團體氣氛：多層次潛在變數分析應用。中華輔導與諮商學報，32，33-55。
4. 黃彥融(2016)。學齡前特殊兒童溝通能力與相關影響因素之縱貫研究。特殊教育與復健學報，32，1-20。
5. 黃宗堅(2010)。大學生親子三角關係配對類型及其親密關係滿意度：一個對偶資料的分析研究。中華心理學刊，52(1)，25-46。
6. 簡瑋成(2023)。國中教師觀點探討校長超越領導、教師組織公民行為與學生組織公民行為之關係。教育研究與發展期刊，19(2)，1-45。
7. 李仁豪、余民寧(2008)。二層次結構方程式模型的應用：以教育心理學為例。師大學報：教育類，53(3)，95-123。
8. 羅寶鳳、曾明基、張德勝、邱于真(2011)。學生評鑑教師教學量表跨層級構念的分析。教育科學研究期刊，56(3)，31-60。
9. 羅寶鳳、曾明基、張德勝、邱于真(2012)。學生評鑑教師教學題目安排順序不同對學生評鑑教師的影響：MI與MMI分析取向。測驗學刊，59(1)，131-156。
10. 蘇聖珠、婁文信、李政達、王如鈺(2012)。顧客滿意與其前置變項之多層次分析。顧客滿意學刊，8(2)，145-182。
11. 溫福星、邱皓政(2009)。多層次模型方法論：階層線性模式的關鍵議題與試解。臺大管理論叢，19(2)，263-293。
12. 吳勁甫(2011)。校長領導對學校效能影響模式之探析。教育經營與管理研究集刊，7，1-25。
13. 嚴佳代、黃同圳、王正慧(2011)。記者任務互賴、衝突與績效─合作性衝突之再議。管理學報，28(5)，427-446。
14. 嚴雅音、黃曉靈、黃正銘、陳富莉、許志成、林雅瑩、李建宏、嚴雅音、黃曉靈、黃正銘、陳富莉、許志成、林雅瑩、李建宏、嚴雅音、黃曉靈、黃正銘、陳富莉、許志成、林雅瑩、李建宏(2010)。學校層次菸害防制政策與個人層次特質對於學童吸菸行為之多層次分析：以屏東縣的國小為例。臺灣公共衛生雜誌，29(2)，145-157。
15. 葉勝雄、黃琳淇、高瑞鍾、高瑞新(2011)。船舶貨物裝卸承攬業於轉換型領導、組織氣氛、組織承諾及組織公民行為關係之跨層次實證分析。運輸計劃季刊，40(1)，99-132。
16. 葉允棋、陳美燕(2013)。體育統計分析與層次研究概念之介紹。體育學報，46(1)，1-12。
17. 游錦雲、陳敏瑜(2017)。學生知覺教師期望、能力信念、實用價值與內在價值對臺灣八年級學生數理成就之影響：以TIMSS 2011 多層次結構方程式模型為例。教育科學研究期刊，62(1)，59-102。
18. (2011)。國中校長教學領導、學校知識管理與教師教學效能之多層次分析。教育與心理研究，34(2)，1-31。
19. (2015)。國小校長正向領導對學校效能影響之研究：教師心理資本的多層次中介效果。教育與心理研究，38(3)，1-36。
20. (2018)。國中校長學習領導、教師專業學習社群與學生學習表現關係之研究。教育與心理研究，41(1)，1-30。
21. (2021)。國中學校組織公平、兼任行政教師情緒勞務與留任意願之跨層次研究。教育與心理研究，44(3)，1-34。
22. (2021)。校長翻轉領導、教師翻轉教學與學生翻轉學習之關聯性探究。教育政策論壇，24(4)，35-81。
23. (2022)。探討學校層級的社經文化背景對學習成就之影響及其制度性成因。臺灣教育社會學研究，22(2)，1-46。
24. (2023).Internationalization of quality assurance and the international quality of higher education in Taiwan.高教評鑑與發展,17(2),113-128.
25. (2024)。日常社會互動中的愛之重要性：正向共鳴累積生命意義感。中華心理學刊，66(3)，361-388。