Winsteps 項目分析理論軟體
winsteps是一個項目反應理論軟體。項目反應理論（Item Response Theory, IRT）是屬於現代測驗理論,因為古典測驗理論有一些難以克服的缺點，如用不同項目的測驗結果無法比較,數據沒有等距性，測量結果容易受到樣本的影響，以及多變量處理不易,而現代IRT理論,可以有效克服以上的缺點，所以IRT廣泛的應用於教育測驗領域,如GRE，TOEFL等測驗，近年來也擴展應用到各科學領域的測驗評估。
Winsteps constructs Rasch measures from simple rectangular data sets, usually of persons and items. After initial familiarization, it is straightforward to use in combination with other software. Item types that can be combined in one analysis include dichotomous, multiple-choice, and multiple rating-scale and partial credit items. Paired comparisons and rank-order data can also be analyzed. Missing data is no problem. Winsteps is designed as a tool that facilitates exploration and communication. The structure of the items and persons can be examined in depth. Unexpected data points are identified and reported in numerous ways. Powerful diagnosis of multidimensionality through principal components analysis of residuals detects and quantifies substructures in the data. The working of rating scales can be examined thoroughly, and rating scales can be recoded and items regrouped to share rating scales as desired. Measures can be fixed (anchored) at pre-set values. Winsteps is intended for practitioners who must make practical and quick decisions along the path to constructing effective tests, and who must then communicate their results usefully to end users. The developers of Winsteps use the program daily in their own work, and are continually adding new features as a result of their own experience and feedback from users. Typical applications include educational tests, psychological assessments, attitude surveys, patient performance protocols, and calibrating adaptive-test item banks. Winsteps can process up to 1,000,000 persons, 30,000 items, and each item can have a rating scale of up to 255 categories. Training seminars are held regularly.
Rasch analysis has been the IRT method of choice for moderate size data sets since 1965. Now the theoretical advantages and directly meaningful results of Rasch analysis can be easily obtained for large data sets, with the convenience of using your own standard PC.
-
Scores and analyzes dichotomous items, or sets of items with the same or different rating scale, partial credit, rank or count structures for up to 254 ordered categories per structure, with useful estimation of perfect scores.
-
Missing responses or non-administered items are no problem.
-
Analyze several partially linked forms in one analysis.
-
Analyze responses from computer-adaptive tests.
-
Item reports and graphical output include calibrations, standard errors, fit statistics, detailed reports of the particular improbable person responses which cause item misfit, distracter counts, and complete DOS files for additional analysis of item statistics.
-
Person reports and graphical output include measures, standard errors, fit statistics, detailed reports of the particular improbable item responses which cause person misfit, a table of measures for all possible complete scores, and complete DOS files for additional analysis of person statistics.
-
Rating scale, partial credit, rank and count structures reported numerically and graphically.
-
Complete output files of observations, residuals and their errors for additional analyses of differential item function and other residual analyses.
-
Observations listed in conjoint estimate order to display extent of stochastic Guttman order.
-
Option to pre-set and/or delete some or all person measures and/or item calibrations for anchoring, equating and banking, and also to pre-set rating scale step calibrations.
-
Accepts most MSCALE, MSTEPS and BIGSCALE data and control files without alteration.
-
Runs under MS-DOS, Windows 3.1 and Windows. Analysis size up to 1,000,000 people and 30,000 items. Contact winsteps.com using the comment form below about custom versions for larger sample sizes.
-
Winsteps is not 508 compliant.