進階搜尋


下載電子全文  
系統識別號 U0026-2701201411222700
論文名稱(中文) 以不同檢定統計量檢驗巢套結構方程模型的強韌性
論文名稱(英文) The Robustness of Test Statistics in Comparing Nested Structural Equation Models
校院名稱 成功大學
系所名稱(中) 心理學系認知科學碩士班
系所名稱(英) MS in Cognitive Science
學年度 102
學期 1
出版年 103
研究生(中文) 林凊
研究生(英文) Ching Lin
學號 u76014017
學位類別 碩士
語文別 英文
論文頁數 95頁
口試委員 指導教授-鄭中平
口試委員-翁儷禎
口試委員-許文耀
中文關鍵字 巢套結構方程模型  Satorra-Bentler量尺化檢定  Bollen-Stine拔靴法 
英文關鍵字 nested structural equation model  Satorra-Bentler scaled test  Bollen-Stine bootstrapping 
學科別分類
中文摘要 結構方程模型被廣泛使用於社會、行為科學研究中,常見的運用方式包含檢驗單一模型與根據特定的假設比較巢套模型。巢套模型的運用包含如檢驗模型參數是否等於某一特殊值、不同組別的調節效果相同與否及驗證性因素分析的因素數目等。在比較巢套模型之前,研究者須注意資料是否符合一些假設,如多元常態、大樣本與近乎正確的基模型,但是在實徵研究中,資料不一定總是能符合這些假設,當假設被違反時,型一錯誤率可能會膨脹且統計檢定力可能會下降,統計結果可能進而誤導研究者下決策。為解決這些問題,學者們提出了一些方法如Satorra-Bentler量尺化檢定和Bollen-Stine拔靴法,過去研究也證實這些方法在處理單一模型檢定時的實用性,但於比較巢套模型是否依舊可用則鮮少被評估,因此我們將觀察上述這些方法在比較巢套模型時的表現與假設被違反時的強韌性。研究以蒙地卡羅方式進行,操弄之獨變項為假設 (路徑係數、因素負載量)、檢定統計量 (最大概似法、Satorra-Bentler量尺化檢定和Bollen-Stine拔靴法)、基模型的適配程度、分配與樣本數。結果則看到當假設被違反時,最大概似法由於型一錯誤率不合理的膨脹而變得不適用,Bollen-Stine拔靴法則能將型一錯誤率維持在.05,除非假設被違反的太過嚴重,如基模型RMSEA大於.08、分配呈現重度非常態的情境。當基模型不適配,則三種方法均會使得型一錯誤率膨脹而不適用。總括來說,比較巢套模型時,三種統計量中Satorra-Bentler量尺化檢定於假設被違反時的表現最好,但實際運用時,研究者需注意其較低的統計檢定力。
英文摘要 In social and behavioral sciences, structural equation model remains a popular analytic method. Researchers commonly use SEM analysis for testing a model and comparing nested models, the latter being widely used in testing whether specific paths equal specific values, testing moderation across groups, and testing factor numbers in confirmatory factor analysis by the likelihood ratio test or named chi-square difference test. Researchers should note the existence of several assumptions for comparing nested models, including multivariate normality, a large sample size, and an approximately correctly specified base model. However, the assumptions are not always met in empirical research. If the assumptions are violated, the test statistic of the normal theory maximum likelihood method will be biased, Type I error will be inflated and the statistical decision process might be misled. We propose the previously evaluated the Satorra-Bentler scaled test and Bollen-Stine bootstrapping to deal with the violation of the assumptions of normality and large sample size, adding to the literature by using them to test nested models. To understand the performance of ML estimation, the Satorra-Bentler scaled test and Bollen-Stine bootstrapping in comparing nested models under the violation of assumptions, we conduct a Monte Carlo study and manipulate several independent variables, including different hypotheses (e.g., path coefficient and factor loading), test statistics, base model imperfection, distributions, and sample sizes. Our results show that when assumptions are not met, ML estimation inflates Type I error to unacceptable levels. Bollen-Stine bootstrapping holds the Type I error well until the fit of the base model becomes poor (at RMSEA=.08 or above) and the distribution become severely nonnormal. When the fit of a base model is inadequate, all of methods lead to an inflated Type I error rate, making them unsuitable for analysis. According to this study, we conclude that the Satorra-Bentler scaled test performs best for nested-model analysis, but that researchers should be wary of its attenuated power.
論文目次 1. Introduction 1
2. Method 15
3. Results 21
4. Demonstration 38
5. Discussion 43
6. Reference 52
7. Appendices 59
參考文獻 Bentler, P. M., & Yuan, K. H. (1999). Structural Equation Modeling with Small Samples: Test Statistics. Multivariate Behavioral Research, 34(2), 181-197. doi: 10.1207/S15327906Mb340203
Bickel, P. J., & Freedman, D. A. (1981). Some asymptotic theory for the bootstrap. The Annals of Statistics, 9(6), 1196-1217. doi: 10.1214/aos/1176345637
Bollen, K. A. (1989). Structural equations with latent variables. Oxford, England: John Wiley & Sons.
Bollen, K. A., & Stine, R. A. (1992). Bootstrapping Goodness-of-Fit Measures in Structural Equation Models. Sociological Methods & Research, 21(2), 205-229. doi: 10.1177/0049124192021002004
Boomsma, A. (1987). The robustness of maximum likelihood estimation in structural equation models. In P. Cuttance & R. Ecob (Eds.), Structural modeling by example: Applications in educational, sociological, and behavioral research. (pp. 160-188). New York, NY: US: Cambridge University Press.
Boomsma, A., & Hoogland, J. J. (2001). The robustness of LISREL modeling revisited. In R. Cudeck, S. d. Toit & D. Sörbom (Eds.), Structural equation models: Present and future. A Festschrift in honor of Karl Jöreskog (pp. 139-168). Lincolnwood, IL: Scientific Software International. .
Box, G. E. P. (1979). Some Problems of Statistics and Everyday Life. Journal of the American Statistical Association, 74(365), 1-4. doi: 10.1080/01621459.1979.10481600
Browne, M. W., & Cudeck, R. (1992). Alternative Ways of Assessing Model Fit. Sociological Methods & Research, 21(2), 230-258. doi: 10.1177/0049124192021002005
Cheng, C. P., Yen, C. F., Ko, C. H., & Yen, J. Y. (2012). Factor structure of the center for epidemiologic studies depression scale in Taiwanese adolescents. Comprehensive Psychiatry, 53(3), 299-307. doi: http://dx.doi.org/10.1016/j.comppsych.2011.04.056
Chou, C. P., Bentler, P. M., & Satorra, A. (1991). Scaled test statistics and robust standard errors for non-normal data in covariance structure analysis: A Monte Carlo study. British Journal of Mathematical and Statistical Psychology, 44(2), 347-357. doi: 10.1111/j.2044-8317.1991.tb00966.x
Cohen, J. (1988). Statistical power analysis for the behavioral sciences (2 ed.): Hillsdale, NJ: Lawrence Erlbaum.
Cook, A. J., Brawer, P. A., & Vowles, K. E. (2006). The fear-avoidance model of chronic pain: Validation and age analysis using structural equation modeling. Pain, 121(3), 195-206. doi: http://dx.doi.org/10.1016/j.pain.2005.11.018
Cudeck, R., & Browne, M. (1992). Constructing a covariance matrix that yields a specified minimizer and a specified minimum discrepancy function value. Psychometrika, 57(3), 357-369. doi: 10.1007/bf02295424
Curran, P. J., Bollen, K. A., Chen, F., Paxton, P., & Kirby, J. B. (2003). Finite sampling properties of the point estimates and confidence intervals of the RMSEA. Sociological Methods & Research, 32(2), 208-252. doi: 10.1177/0049124103256130
Curran, P. J., Bollen, K. A., Paxton, P., Kirby, J., & Chen, F. (2002). The Noncentral Chi-square Distribution in Misspecified Structural Equation Models: Finite Sample Results from a Monte Carlo Simulation. Multivariate Behavioral Research, 37(1), 1-36. doi: 10.1207/S15327906MBR3701_01
Curran, P. J., West, S. G., & Finch, J. F. (1996). The robustness of test statistics to nonnormality and specification error in confirmatory factor analysis. Psychological Methods, 1(1), 16-29. doi: 10.1037/1082-989X.1.1.16
Efron, B., & Tibshirani, R. (1993). An introduction to the bootstrap. New York: Chapman & Hall.
Fan, X., & Sivo, S. A. (2005). Sensitivity of Fit Indexes to Misspecified Structural or Measurement Model Components: Rationale of Two-Index Strategy Revisited. Structural Equation Modeling: A Multidisciplinary Journal, 12(3), 343-367. doi: 10.1207/s15328007sem1203_1
Fan, X., & Sivo, S. A. (2007). Sensitivity of Fit Indices to Model Misspecification and Model Types. Multivariate Behavioral Research, 42(3), 509-529. doi: 10.1080/00273170701382864
Finney, S. J., & DiStefano, C. (2006). Non-normal and categorical data in structural equation modeling. In G. R. Hancock & R. O. Mueller (Eds.), Structural equation modeling: A second course (pp. 269-314). United State of America: Information Age Publishing.
Fleishman, A. (1978). A method for simulating non-normal distributions. Psychometrika, 43(4), 521-532. doi: 10.1007/bf02293811
Fox, J. (2006). TEACHER'S CORNER: Structural Equation Modeling With the sem Package in R. Structural Equation Modeling: A Multidisciplinary Journal, 13(3), 465-486. doi: 10.1207/s15328007sem1303_7
Herzog, W., Boomsma, A., & Reinecke, S. (2007). The Model-Size Effect on Traditional and Modified Tests of Covariance Structures. Structural Equation Modeling: A Multidisciplinary Journal, 14(3), 361-390. doi: 10.1080/10705510701301602
Hu, L. T., & Bentler, P. M. (1998). Fit indices in covariance structure modeling: Sensitivity to underparameterized model misspecification. Psychological Methods, 3(4), 424-453. doi: 10.1037/1082-989x.3.4.424
Hu, L. T., Bentler, P. M., & Kano, Y. (1992). Can test statistics in covariance structure analysis be trusted? Psychological Bulletin, 112(2), 351-362. doi: citeulike-article-id:2911182
Hund, A. R., & Espelage, D. L. (2006). Childhood emotional abuse and disordered eating among undergraduate females: Mediating influence of alexithymia and distress. Child Abuse & Neglect, 30(4), 393-407. doi: http://dx.doi.org/10.1016/j.chiabu.2005.11.003
Kaplan, D. (1988). The Impact of Specification Error on the Estimation, Testing, and Improvement of Structural Equation Models. Multivariate Behavioral Research, 23(1), 69-86. doi: 10.1207/s15327906mbr2301_4
Kelley, K. (2007). Methods for the Behavioral, Educational, and Social Science: An R Package. Behavior Research Methods, 39(4), 979-984. doi: 10.3758/BF03192993
MacCallum, R. C. (1996). Power analysis and determination of sample size for covariance structure modeling. Psychological Methods, 1(2), 130-149. doi: 10.1037/1082-989X.1.2.130
MacCallum, R. C. (2006). Testing differences between nested covariance structure models: Power analysis and null hypotheses. Psychological Methods, 11(1), 19-35. doi: 10.1037/1082-989X.11.1.19
Moshagen, M. (2012). The Model Size Effect in SEM: Inflated Goodness-of-Fit Statistics Are Due to the Size of the Covariance Matrix. Structural Equation Modeling: A Multidisciplinary Journal, 19(1), 86-98. doi: 10.1080/10705511.2012.634724
Nevitt, J., & Hancock, G. R. (2001). Performance of Bootstrapping Approaches to Model Test Statistics and Parameter Standard Error Estimation in Structural Equation Modeling. Structural Equation Modeling: A Multidisciplinary Journal, 8(3), 353-377. doi: 10.1207/s15328007sem0803_2
Rosseel, Y. (2013, January 8). Re: A warning message: standard errors and cov.lv [Online Forum Comment]. Retrieved from https://groups.google.com/forum/#!searchin/lavaan/warning/lavaan/kn-4nEFjx6w/Fa09mJDTs3AJ
Rosseel, Y. (2012). lavaan: An R Package for Structural Equation Modeling. Journal of Statistical Software, 48(2), 1-36. URL http://www.jstatsoft.org/v48/i02/
Satorra, A., & Saris, W. (1985). Power of the likelihood ratio test in covariance structure analysis. Psychometrika, 50(1), 83-90. doi: 10.1007/BF02294150
Satorra, A., & Bentler, P. (2001). A scaled difference chi-square test statistic for moment structure analysis. Psychometrika, 66(4), 507-514. doi: 10.1007/bf02296192
Satorra, A., & Bentler, P. (2010). Ensuring Positiveness of the Scaled Difference Chi-square Test Statistic. Psychometrika, 75(2), 243-248. doi: 10.1007/s11336-009-9135-y
Satorra, A., & Bentler, P. M. (1994). Corrections to test statistics and standard errors in covariance structure analysis. In A. v. Eye & C. C. Clogg (Eds.), Latent variables analysis: Applications for developmental research (pp. 399-419). Thousand Oaks, CA, US: Sage Publications, Inc.
Steiger, J., Shapiro, A., & Browne, M. (1985). On the multivariate asymptotic distribution of sequential Chi-square statistics. Psychometrika, 50(3), 253-263. doi: 10.1007/BF02294104
Tang, T. C., Yen, C. F., Cheng, C. P., Yang, P., Chen, C. S., Yang, R. C., ... Yu, H. S. (2010). Suicide risk and its correlate in adolescents who experienced typhoon-induced mudslides: a structural equation model. Depression and Anxiety, 27(12), 1143-1148. doi: 10.1002/da.20748

Vale, C. D., & Maurelli, V. (1983). Simulating multivariate nonnormal distributions. Psychometrika, 48(3), 465-471. doi: 10.1007/bf02293687
Yuan, K. H., & Bentler, P. M. (2004). On Chi-Square Difference and z Tests in Mean and Covariance Structure Analysis when the Base Model is Misspecified. Educational and Psychological Measurement, 64(5), 737-757. doi: 10.1177/0013164404264853
論文全文使用權限
  • 同意授權校內瀏覽/列印電子全文服務,於2017-02-17起公開。
  • 同意授權校外瀏覽/列印電子全文服務,於2017-02-17起公開。


  • 如您有疑問,請聯絡圖書館
    聯絡電話:(06)2757575#65773
    聯絡E-mail:etds@email.ncku.edu.tw