運用資料探勘技術於電腦化適性測驗之研究｜國立臺灣科技大學博碩士論文系統

簡易檢索 / 詳目顯示

回結果列表

研究生：	張裕昌 YU-CHANG CHANG
論文名稱：	運用資料探勘技術於電腦化適性測驗之研究 Applying Data Mining Techniques in Computerized Adaptive Test
指導教授：	吳宗成 Tzong-Chen Wu
口試委員:	欒斌 Pin Luarn 周子銓 Tzu-Chuan Chou 蔡憲唐 Tsai, Hsien-Tang 翁崇雄 Chorng-Shyong Ong
學位類別：	博士 Doctor
系所名稱：	管理學院 - 管理研究所 Graduate Institute of Management
論文出版年：	2015
畢業學年度：	103
語文別：	英文
論文頁數：	62
中文關鍵詞：	電腦化適性測驗、KNN 方法、不完整作答題目
外文關鍵詞：	not reached, K-Nearest Neighbor solution, Computerized Adaptive Test
相關次數：	點閱：243 下載：7
分享至:	分享至facebook 分享至twitter

查詢本校圖書館目錄查詢臺灣博碩士論文知識加值系統勘誤回報

上一筆

缺失資料對於一般的調查研究或實驗數據都有相當的影響。而在電腦適應化測試中(CAT)，不完整作答題目(not-reached items)就是一種缺失資料，此會導致嚴重的能力估計錯誤。以往的研究皆試圖從評分規則的角度來解決這個問題。本研究利用資料探勘中的KNN方法來推算能力估計值。結果發現KNN方法優於以往的方式，KNN方法的性能顯然比以前提出的方法更好。結論發現，運用資料探勘技術於電腦化適性測驗，有相當好的效果，其效能也較佳。

Missing data is an inherent feature of most surveys or assessments that involve human subjects. In a Computerized Adaptive Test (CAT), not reached item is a kind of missing data issue which causes serious ability estimation problem. Previous studies tried to resolve this issue from the perspective of scoring rule. This study utilized a K-Nearest Neighbor (KNN) solution based on data mining method to imputethe ability estimation for not-reached items. The results indicated that the predominant of KNN methodwas not obvious when the value of k was less than 10. While the number of neighbor was larger than 20, the performance of KNN method was apparently better thanprevious proposed methods. Overall, the results indicated that the data mining mechanism might provide a better solution for not reached item problem.

Chapter 1.Introduction.............................................................................................2
RESEARCH BACKGROUND..............................................................................................2
RESEARCH PURPOSE......................................................................................................3
RESEARCH METHODOLOGY...........................................................................................4
RESEARCH LIMITATION..................................................................................................4
Chapter 2.Literature Review....................................................................................5
ITEM RESPONSE THEORY...............................................................................................5
COMPUTERIZED ADAPTIVE TESTING..............................................................................9
MICROSOFT CERTIFICATION TEST................................................................................15
NOT-REACHED ITEMS IN CAT.......................................................................................21
DATA MINING...............................................................................................................27
K-NEAREST NEIGHBOR IMPUTATION METHOD............................................................38
Chapter 3.Methodology.........................................................................................41
PARTICIPANTS...............................................................................................................41
ITEM BANK...................................................................................................................41
ALGORITHM OF KNN...................................................................................................43
SIMULATION PROCEDURE.............................................................................................47
Chapter 4.Results...................................................................................................49
THE EFFECT OF THE NUMBER OF NOT-REACHED ITEMS................................................49
THE EFFECT OF THE NEIGHBORHOOD SIZE...................................................................53
THE ACTUAL EFFECT OF THE APPLICATION IN REAL CERTIFICATION TEST....................54
Chapter 5.Conclusion & Suggestion.....................................................................55
References………………………………………………………………………59

                                

Brown, J. (1997). Computers in language testing: Present research and some future directions. Language Learning & Technology, 1(1), 44-59.
Liu, P., & Lei, L. (2005). A review of missing data treatment methods. An International Journal: Intelligent Information Management Systems and Technologies, 1(3), 412-419.
Lord, F. (1974). Estimation of latent ability and item parameters when there are omitted responses. Psychometrika, 39(2), 247-264.
Lord, F. (1980). Applications of item response theory to practical testing problems. Hillsdale, NJ: Lawrence Erlbaum Associates.
Lord, F. (1983). Unbiased estimators of ability parameters, of their variance, and of their parallel-forms reliability. Psychometrika, 48(2), 233-245.
Lord, F. (1986). Maximum likelihood and Bayesian parameter estimation in item response theory. Journal of Educational Measurement, 23, 157-162.
Ludlow, L. H., & O'leary, M. (1999). Scoring Omitted and Not-Reached Items: Practical Data Analysis Implications. Educational and Psychological Measurement, 59(4), 615-630.
McBride, J. R., Wetzel, C. D., & Hetter, R. D. (1997). Preliminary psychometric research for CAT-ASVAB: Selecting an adaptive testing strategy. In W. A. Sands, B. K. Waters & J. R. McBride (Eds.), Computerized adaptive testing: From 60

inquiry to operation(pp. 83–95). Washington, DC: American Psychological Association.
Mills, C., & Steffen, M. (2000). The GRE computer adaptive test: Operational issues. Computerized adaptive testing: Theory and practice, 75-99.
Mislevy, R., & Wu, P. (1988). Inferring Examinee Ability When Some Item Responses Are Missing. Princeton, N. J.: Educational Testing Service.
Mislevy, R. J., & Wu, P. (1996). Missing responses and IRT ability estimation: Omits, choice, time limits, and adaptive testing.Princeton, N. J.: Educational Testing Service.
Owen, R. (1975). A Bayesian sequential procedure for quantaresponse in the context of adaptive mental testing. Journal of the American Statistical Association, 70, 351-356.
Papanastasiou, E. C., & Reckase, M. (2007). A "rearrangement procedure" for scoring adaptive tests with review options. International Journal of Testing, 7(4), 387–407.
Segall, D. O. (1988). A procedure for scoring incomplete adaptive tests in high stakes testing. Unpublished manuscript. San Diego, CA: Navy Personnel Research and Development Center.61

Segall, D. O., & Moreno, K. E. (1999). Development of the CAT-ASVAB. In F. Drasgow & J. B. Olson-Buchanan (Eds.), Innovations in Computerized Assessment (pp. 35-65). Hillsdale, NJ: Lawrence Erlbaum Associates.
Slater, S., & Schaeffer, G. (1996). Computing Scores for Incomplete GRE General Computer Adaptive Tests. Paper presented at the the Annual Meeting of the National Council on Measurement in Education.
Tuikkala, J., Elo, L., Nevalainen, O. S., &Aittolallio, T. (2006). Improving missing value estimation in microarray data with gene ontology. Bioinformatics, 22, 566–572.
Warm, T. (1989). Weighted likelihood estimation of ability in item response theory. Psychometrika, 54(3), 427-450.
Yi, O., Widiatmo, H., Hanson, B. A., Ban, J.-C., & Harris, D. J. (2001, April). Impact of Scoring Options for Not Reached Items in CAT. Paper presented at the annual meeting of the National Council on Measurement in Education, Seattle WA.
Zhang, C., Qin, Y., Zhu, X., Zhung, S., & Zhang, J. (2006). Clustering-based missing value imputation for data preprocessing. Paper presented at the Industrial Informatics, 2006 IEEE International Conference on n: Proceedings of the 4th International IEEE Conference on Industrial Informatics, INDIN'06:1081-1086. (oral paper)62
Yen Y.C., R.G.Ho, W.W.Liao., L.J.Chen.(2011). Reducing the Impact of Inappropriate Items on Reviewable Computerized Adaptive Testing. An International Journal: Educational Technology & Society, 15 (2) , 213-243.

簡易檢索 / 詳目顯示

相關論文