目前普遍施行的二點計分測驗方式答題結果只有對或錯兩種情況，這種單憑最後答案的對錯，以決定受試者能力的方式，並沒有考慮到受試者的作答歷程；多點計分的測驗可較二點計分更精確地估計受試者的特質，然而仍多由人工方式為之，較難透過電腦由受試者主動建構作答歷程。
此外，由於電腦化適性測驗較符合經濟效益，測驗結果亦不失精確性，為未來測驗之主流，因此，本研究旨在結合項目反應理論之部分計分模式、電腦化適性測驗，以及派翠西網路理論，以國小五年級「分數的加減」單元為測驗內容，嘗試發展一部分給分之電腦化適性測驗系統，並進行實際施測以評估系統效能。在本系統中，受試者必須自己建構解題歷程，系統以IRT之方式進行部分給分，並能於測驗之後提供受試者回饋。
研究結果顯示，本研究之部分給分電腦化適性測驗系統能由受試者透過電腦自己表達作答歷程，並能有效地減少施測長度；測驗結果與傳統部分給分測驗呈高相關，亦較二點計分之測驗方式精緻，更能區分受試者之能力。每位受試者不須做完全部題目，所做的題目也不盡相同，不僅節省施測時間，題庫安全性亦較高。再者，測驗結果除呈現分數之外，尚有錯誤類型的分析，可做為學生自我了解及教師補救教學的參考。

The result of testing response scored dichotomously is either right or wrong. This kind of test that estimates an examinee's ability based on the last response without considering the examinee's response process is worth doubt. In contrast to the dichotomously scoring, the polytomously scoring can estimate the examinee's ability more accurately. However, due to the difficulty of producing response process by examinees themselves with computers, most polytomous tests are administered manually.
Moreover, because of the economic effect and the accuracy of the testing result, computerized adaptive testing (CAT) will be the mainstream in future. The purpose of this research is to combine partial credit model of IRT, CAT, and Petri Net theory to develop a partial-credit computerized adaptive testing system, whose testing material is "Fraction Addition and Subtraction" about the 5th grade in elementary schools, and to estimate the efficiency of the system by actually testing rather than simulation. In this system, all examinees must produce the process of solving problem by themselves, the scoring method is based on partial credit model of IRT, and the feedback is presented to the examinee at the end of testing.
The results of this research show that the testing length is shortened efficiently when it is administered by the computerized adaptive testing system of partial credit scoring, and the estimation of examinees' ability is more delicate than the dichotomously scoring. Because examinees needn't do all items in item bank, and the items tested by examinees are not the same, the testing time is saved and the security of item bank is good. Finally, the outputs of the testing system include testing score and the analysis of wrong patterns, which can not only be the reference of teachers when they do remedial teaching, but also let examinees understand their ability more deeply.

何榮桂、賴信仁(民86)。項目參數之線上校準研究。第六屆國際電腦輔助教學研討會大會論文集，p454-463。
何榮桂、蘇建誠(民86)。遠距適性態度測驗系統設計。第六屆國際電腦輔助教學研討會論文集，p175-183。
孫茂鑫(民86)。以派翠西網路為基礎之數學解題系統－高中數學之「圓」單元。國立台灣師範大學資訊教育研究所碩士論文。
孫鵬宗(民87)。一個網路化的數學解題系統－國中數學之「三角函數」單元。國立台灣師範大學資訊教育研究所碩士論文。
許擇基、劉長萱(民81)。試題作答理論簡介。台北：中國行為科學社。
國立編譯館主編(民86)。國民小學第九冊數學教學指引。改編本再版。台北：國立編譯館。
國立編譯館主編(民83)。國民小學第九冊數學。改編本再版。台北：國立編譯館。
黃正志(民86)。問題解決式數學科教學軟體解題流程分析－運用派翠西網路。國立台灣師範大學資訊教育研究所碩士論文。
簡月梅(民87)。互動式提示多點計分電腦化適性測驗。國立台灣師範大學資訊教育研究所碩士論文。
Baker, F. B. (1992). Item response theory : parameter estimation techniques. New York : Marcel Dekker.
De Ayala, R. J., Dodd, B. G. & Koch, W. R.(1991). Partial credit analysis of writing ability. Educational and Psychological Measurement. 51, 103-114.
De Ayala, R. J.(1992). The Normal response model in computerized adaptive testing. Applied psychological measurement. 16(4), 327-343.
De Ayala, R. J., Dodd, B. G. & Koch, W. R. (1992). A comparison of the partial credit and graded response models in computerized adaptive testing. Applied measurement in education. 5(1), 17-34.
Hambleton, R. K., & Swaminathan, H. (1985). Item response theory : Principles and applications, Boston:Kluwer-Nijhoff.
Ho, R. G., & Hsu, T. C. (1989). A comparison of three adaptive testing strategies using MicroCAT. Paper presented at the annual meeting of the American Educational Research Association, San Francisco, CA.
Kaiser, H. F. (1958). The varimax criterion for analytic rotation in factor analysis. Psychometrika, 23, 187-200.
Kelly, T. L. (1939). The selection of upper and lower groups for the validation of test items. Journal of Educational Psychology, 30, 17-24.
Load, F. M. (1980). Applications of item response theory to practical testing problems. Hillsdale, NJ:Erlbaum.
Master, G. N.(1982). A RASH model for partial credit scoring. Psychometrika. 47(2), 149-174.
Molloy, M. K.(1989). Petri Net modeling-The past, the present, and the future. Proceedings of the third international workshop on Petri Nets and performance models. 2-9.
Muraki, E.(1992). A generalizd partial credit model: Application of an EM algorithm. Applied psychological measurement. 16(2), 159-176.
Owen, R. J. (1975). A Bayesian sequential procedure for quantal response in the context of adaptive mental testing. Journal of the American statistical association, 70,351-356.
Peterson, J. L.(1981). Petri Net theory and the modeling of systems. Englewood Cliffs:NJ:Pretice-Hall.
Wainer, H., (1990). Computerized adaptive testing: A primer. Hillsdale, N.J.:Lawrence Erlbaum Associates.