國民中學基本學力測驗分數分配與量尺分數轉換之研究

碩士 === 國立彰化師範大學 === 數學系所 === 93 === Number-correct raw scores of the Basic Competence Test for Junior High School Students (BC test) are transformed into scale scores to stabilize measurement error variability. This study examined four density estimation methods applied to the raw-to-scale score tra...

Full description

Bibliographic Details
Main Author: 吳怡靜
Other Authors: 李信宏
Format: Others
Language:zh-TW
Published: 2005
Online Access:http://ndltd.ncl.edu.tw/handle/24224420794469974903
id ndltd-TW-093NCUE5479003
record_format oai_dc
spelling ndltd-TW-093NCUE54790032016-06-03T04:13:55Z http://ndltd.ncl.edu.tw/handle/24224420794469974903 國民中學基本學力測驗分數分配與量尺分數轉換之研究 吳怡靜 碩士 國立彰化師範大學 數學系所 93 Number-correct raw scores of the Basic Competence Test for Junior High School Students (BC test) are transformed into scale scores to stabilize measurement error variability. This study examined four density estimation methods applied to the raw-to-scale score transformations of BC test. Four-parameter beta compound binomial model, extended beta-binomial model, item response model and kernel smoothing were utilized to 50 replications of random samples of 5,000 from 2002, 2003 and 2004 examinees' populations. The performance of each estimation technique was carefully investigated by criteria including bias, variance, and mean square error. It is concluded that the four-parameter beta compound binomial model produced the most accurate estimates. Suggestions for further research are also provided. 李信宏 2005 學位論文 ; thesis 96 zh-TW
collection NDLTD
language zh-TW
format Others
sources NDLTD
description 碩士 === 國立彰化師範大學 === 數學系所 === 93 === Number-correct raw scores of the Basic Competence Test for Junior High School Students (BC test) are transformed into scale scores to stabilize measurement error variability. This study examined four density estimation methods applied to the raw-to-scale score transformations of BC test. Four-parameter beta compound binomial model, extended beta-binomial model, item response model and kernel smoothing were utilized to 50 replications of random samples of 5,000 from 2002, 2003 and 2004 examinees' populations. The performance of each estimation technique was carefully investigated by criteria including bias, variance, and mean square error. It is concluded that the four-parameter beta compound binomial model produced the most accurate estimates. Suggestions for further research are also provided.
author2 李信宏
author_facet 李信宏
吳怡靜
author 吳怡靜
spellingShingle 吳怡靜
國民中學基本學力測驗分數分配與量尺分數轉換之研究
author_sort 吳怡靜
title 國民中學基本學力測驗分數分配與量尺分數轉換之研究
title_short 國民中學基本學力測驗分數分配與量尺分數轉換之研究
title_full 國民中學基本學力測驗分數分配與量尺分數轉換之研究
title_fullStr 國民中學基本學力測驗分數分配與量尺分數轉換之研究
title_full_unstemmed 國民中學基本學力測驗分數分配與量尺分數轉換之研究
title_sort 國民中學基本學力測驗分數分配與量尺分數轉換之研究
publishDate 2005
url http://ndltd.ncl.edu.tw/handle/24224420794469974903
work_keys_str_mv AT wúyíjìng guómínzhōngxuéjīběnxuélìcèyànfēnshùfēnpèiyǔliàngchǐfēnshùzhuǎnhuànzhīyánjiū
_version_ 1718292816552001536