SEM: Structural Equation Modeling Nesselroade, SEM Bollen & Curran LGM: Latent Growth Model, McArdle,, LCM: Latent Curve Model, Meredith & Tisak, a LG

Size: px

Start display at page:

Download "SEM: Structural Equation Modeling Nesselroade, SEM Bollen & Curran LGM: Latent Growth Model, McArdle,, LCM: Latent Curve Model, Meredith & Tisak, a LG"

ふじよしひでやま
7 years ago
Views:

1 pp. ISSN Exploring the Patterns of Skill Development by Mixture Growth Modeling: Using the Batting Average Data on Professional Baseball Players Kazuaki SHIMIZU Abstract Reviewing latent growth modeling for longitudinal data and some results using this methodology on career development, mixture modeling methodologies were introduced for identifying clusters of individuals following similar developmental trajectories. For the latent growth model analysis by Amos and the groupbased trajectory model analysis using SAS Traj procedure, the batting average records of Japanese professional baseball players over ten years were selected from the published official records. Results of latent growth modeling demonstrated that the quadratic form trajectory model fit the data well. Six subgroups were also clustered by the same quadratic form using the Traj. Findings of these analyses were discussed with particular reference to the utility of the group-based trajectory modeling of mixture model methodology for analyzing career development processes. Keywords: latent growth model, mixture modeling, group-based trajectory model, baseball, career development, trajectory Amos SAS Traj TRAJ

2 SEM: Structural Equation Modeling Nesselroade, SEM Bollen & Curran LGM: Latent Growth Model, McArdle,, LCM: Latent Curve Model, Meredith & Tisak, a LGM Amos LGM LGMb LGM

3 LGMMcArdle, Meredith & Tisak SEM SEM LGM, LGM LGM LGM SEM Mixture Modeling:, P.F. Clogg, i tyy it G Jones & Nagin,

4 y it = G g= 1 p ( g ) i yˆ ( g ) it G = ( g ) ( g ) pi i g p = 1 g 1 i yˆ ( g ) it LGM SEMLGM Muthén, EM Bollen & Curran SEM SEM Mplus Muthén & Muthén, Amos Ver. LGM SEM G LGM Mplus G Nagin yˆ ( g ) it trajectory ( g ) ( g ) ( g ) ( g ) 2 ( g ) 3 ( g ) 4 y ˆit = β 0 + β1 Tit + β2 Tit + β3 Tit + β 4 Tit + eit ˆ g it y ( ) i t β ( g β ) ( g β ) 2 ( g β ) 3 ( g β ) 4 ( g ) 0 1 T it g p ( g) i

5 Jones, Nagin, & Roeder SASTraj Jones & NaginTraj p ( g) TrajArrandale, Koehoom, MacNab, & Kennedy i OB N OB p.

6 OB N y LGM y = Λ f + u f u LGM Λ

7 y T u f Λ i y 1i y y y 2i 3i 4i = 1f 1i = 1f = 1f 1i 1i = 1f 1i + 0 f + 1f 2i 2i + 2 f + 3 f 2i 2i f f 2 3i 2 3i f 2 3i f 2 3i + u + u 1i 2i + u + u 3i 4i SEM f 1 f 2 f 3 u 1 u 4 Λ LGM Amos LGMa LGMR Bollen & Curran SEM SEM N T., df, P.RMSEA. T., df, P.RMSEA. AIC..

9 ., df, P.RMSEA N SAS Proc Traj URL N G AIC BIC Traj BIC Jones et al.sem Δ BIC = BIC( complex ) BIC( null) G

10 BIC ( g β ) 0 ( g β ) 4 Traj BIC. ***. *..... ***. ***. **... ***. ***. ***.. ***. ***. ***. % **% *% BIC LGM

11 LGM Traj LGM LGM Traj LGM.... BIC

12 Traj BIC. ***. ***. ***. ***. ***. ***.. ***. ***. ***. ***. ***. ***.. ***. ***. ***. ***. ***. ***. ***. **. **. ***. ***. ***.. ***. *.. ***. ***. ***. ***. ***. ***. ***.... ***. ***. **. ***. *.. ***. ***. ***. ***. **.. ***... ***. ***. ***.. ***. ***. **. ***. *.. ***. ***. ***. ***. ***. ***. ***... ***. **. **.. ***... ***. *. *. ***. *.. ***. **.. ***. ***. ***. ***. ***. ***. ***. **. **. ***. *. *.. ***... ***... ***. *.. % *** % **% * BIC Bayesian Information Criterion

13 BIC Traj LGM

14 BIC G ΔBIC

15 LGM BIC Traj BIC

16 LGM a,b, LGM SEM Mplus Muthén & Muthén, LGM Muthén SEM Bollen & Curran, Traj LGM Traj Traj LGM Thissen & Bock TrajMplus Browne Λ structured latent curve Mx Neale, ; Dolan,

17 Schmittman, Lubke, & Neale, LISREL Traj Mplus Yung CFA Bollen & Curran EM i gem Amos p ( g ) i Traj Mplus Muthén, LGMTraj Traj

18 Muthén, Traj Guay, Ratelle, Senécal, Larose, & Deschênes TrajMplus Traj Dodge, Shen, & Ganguli, Jones & Nagin, LGM,

19 LGMBollen & Curran LGM Menard LGM SEM evidence

20 Arrandale, V., Koehoorn, M., MacNab, Y., & Kennedy, S. M.. How to use SAS Proc Traj and SAS Proc Glimmix in respiratory epidemiology. Bollen, K. A. & Curran, P. J.. Latent curve models: A structural equation perspective. Hoboken, NJ: Wiley. Browne, M. W.. Structured latent curve models. In C. M. Cuadras & C. R. Rao Eds. Multivariate analysis: Future directions. pp.. Amsterdam: North-Holland. Clogg, C. C.. Latent class models. In G. Arminger, C. C. Clogg, & M. E. Sobel Eds., Handbook of statistical modeling for the social and behavioral sciences pp.. New York: Plenum. Dodge, H. H., Shen, C., & Ganguli, M.. Application of the pattern-mixture latent trajectory model in an epidemiological study with non-ignorable missingness. Journal of Data Science,,. Dolan, C. V., Schmittmann, V. D., Lubke, G. H., & Neale, M. C.. Regime switching in the latent growth curve mixture model. Structural Equation Modeling, 12,. Guay, F., Ratelle, C. F., Senécal, C., Larose, S., & Deschênes, A.. Distinguishing developmental from chronic career indecision: Self-efficacy, autonomy, and social support. Journal of Career Assessment, 14,., 15,. Jones, B. L. & Nagin, D. S.. Advances in group-based trajectory modeling and SAS Procedure for estimating them. Sociological Methods Research, 35,. Jones, B. L., Nagin, D. S., & Roeder, L.. A SAS Procedure based on mixture models for estimating developmental trajectories. Sociological Methods Research, 29,. McArdle, J. J.. Latent variable growth within behavior genetic models. Behavior Genetics, 16,. McArdle, J. J.. Dynamic but structural equation modeling of repeated measures data. In J. R.

21 Nesselroade & R. B. Cattell Eds., Handbook of multivariate experimental psychology nd ed. pp.. New York, NY: Plenum. Menard, S. Ed.. Handbook of longitudinal research: Design, measurement, and analysis. Burlington, MA: Elservier. Meredith, W., & Tisak, J.. Latent curve analysis. Psychometrika, 55,. Muthén, B. O.. Beyond SEM: General latent variable modeling. Behaviormetrika, 29,. Muthén, L. K. & Muthén, B. O.. Mplus user s guide. Los Angeles, CA: Muthén & Muthén. Nagin, D. S.. Analyzing developmental trajectories : A semiparametric, group-based approach. Psychological Methods, 4,. Neale, M. C.. Mx statistical modeling. Unpublished program manual, Department of Human Genetics, Medical College of Virginia, Virginia Commonwealth University, Richmond, VA. Nesselroade, J. R.. Interindividual differences in intraindividual change. In L. M. Collins & J. L. Horn Eds., Best methods for analysis of change pp.. Washington, DC: American Psychological Association. The Official Baseball Encyclopedia, 15,. a, 30, b, 19,, 11, Thissen, D., & Bock, R. D.. Linear and nonlinear curve fitting. In A. von Eye Ed., Statistical methods in longitudinal research Vol. II : Time series and categorical longitudinal data. pp.. New York: Academic Press. OB Yung, Y.-F.. Finite mixtures in confirmatory factor-analysis models. Psychometrika, 62,. SAS Proc Traj htttp://

<30315F985F95B65F90B490852E696E6464>

<30315F985F95B65F90B490852E696E6464> Modeling for Change by Latent Difference Score Model: Adapting Process of the Student of Freshman at Half Year Intervals Kazuaki SHIMIZU and Norihiro MIHO Abstract The purpose of this paper is to present