共查询到20条相似文献，搜索用时 15 毫秒
1.
Item response theory (IRT) models can be subsumed under the larger class of statistical models with latent variables. IRT models are increasingly used for the scaling of the responses derived from standardized assessments of competencies. The paper summarizes the strengths of IRT in contrast to more traditional techniques as well as in contrast to alternative models with latent variables (e. g. structural equation modeling). Subsequently, specific limitations of IRT and cases where other methods might be preferable are lined out. 相似文献
2.
L L Bailet 《Journal of learning disabilities》1990,23(2):121-128
Spelling performance of students with learning disabilities (LD) was compared with that of same-age normally achieving subjects and younger normally achieving subjects. Subjects with learning disabilities were divided into two groups: poor readers/poor spellers and good readers/poor spellers. A spelling battery was administered that included one task of phoneme-grapheme correspondence rule usage and four tasks of suffix rule usage. The groups with learning disabilities performed significantly below the same-age normally achieving group on all tasks. No significant differences among the two groups with learning disabilities and their achievement-level peers emerged in primary analyses. However, secondary analyses revealed differences in mastery of the past tense spelling rule ed, and in some subskills related to the spelling of words with suffixes. The cognitive-linguistic significance of these results is discussed. 相似文献
3.
早期的单维IRT模型忽视了测验多维性的可能,而多维IRT模型对各维度的划分不够明确,不能很好地反映各维度能力的内涵。高阶IRT模型承认测验的多维性,以分测验划分维度,同时又将多个维度的能力统一到一个高阶的能力中,能够在了解被试各维度的能力同时,为被试提供整体的能力估计,它能更好地反映实际,并且适应大规模测验的需求。 相似文献
4.
The general concern of the present article is to contribute to an understanding of the contextual determination of cognitive activities. More specifically, the focus of the empirical research reported has been to study how pupils define and deal with cognitive tasks in situations that are recognised as pedagogical in character. Within the context of their everyday mathematics teaching, 206 twelve year old primary school pupils were given work sheets containing elementary arithmetic problems. The experimental treatment consisted of introducing (through headings and instructions) pedagogical definitions of problems that were in conflict with the nature of the problems themselves. The results indicate that the predefinitions of cognitive activities typical of educational contexts have a strong impact on the way problems are dealt with. Clear differences could be discerned between groups at different achievement levels in the extent to which the cues present in pedagogical contexts were used in defining the problem. A crucial aspect of what are conventionally conceived as differences in mathematical ability seems, judging from the present results, to have more to do with the capacity to decipher ambiguous communicative situations than with the mastery of a mathematical algorithm per se. 相似文献
5.
Eiji Muraki 《Journal of Educational Measurement》1999,36(3):217-232
Bock, Muraki, and Pfeiffenberger (1988) proposed a dichotomous item response theory (IRT) model for the detection of differential item functioning (DIF), and they estimated the IRT parameters and the means and standard deviations of the multiple latent trait distributions. This IRT DIF detection method is extended to the partial credit model (Masters, 1982; Muraki, 1993) and presented as one of the multiple-group IRT models. Uniform and non-uniform DIF items and heterogeneous latent trait distributions were used to generate polytomous responses of multiple groups. The DIF method was applied to this simulated data using a stepwise procedure. The standardized DIF measures for slope and item location parameters successfully detected the non-uniform and uniform DIF items as well as recovered the means and standard deviations of the latent trait distributions.This stepwise DIF analysis based on the multiple-group partial credit model was then applied to the National Assessment of Educational Progress (NAEP) writing trend data. 相似文献
6.
Lawrence T. DeCarlo 《Journal of Educational Measurement》2005,42(1):53-76
An approach to essay grading based on signal detection theory (SDT) is presented. SDT offers a basis for understanding rater behavior with respect to the scoring of construct responses, in that it provides a theory of psychological processes underlying the raters' behavior. The approach also provides measures of the precision of the raters and the accuracy of classifications. An application of latent class SDT to essay grading is detailed, and similarities to and differences from item response theory (IRT) are noted. The validity and utility of classifications obtained from the SDT model and scores obtained from IRT models are compared. Validity coefficients were found to be about equal in magnitude across SDT and IRT models. Results from a simulation study of a 5-class SDT model with eight raters are also presented. 相似文献
7.
In this study, we compared 41 adults in a basic literacy class with 92 achievement-level-matched children on their use of English print conventions, as inferred by a qualitative analysis of spelling errors. The two groups followed similar patterns in their mastery of basic spelling features, including letter reversals, consonant blends, and short vowels, with the adults showing relatively more advanced skill in using orthographic patterns. However, the adults made a preponderance of misspellings that were rarely made by the children, including omissions, substitutions, and additions of derivational and inflectional morphemes, and neglect of word endings in general. The findings indicate clear morphological difficulties along with more subtle phonological coding deficits. We suggest that low literacy adults would benefit from specific direct instruction in linguistic analysis, with particular attention to the morphological principles underlying inflections and derivations. Such instruction should be based on a careful assessment of reading and spelling knowledge. 相似文献
8.
This exploratory study aimed to evaluate the spelling of derived words by dyslexic adolescents and to verify whether this is associated with lack of vocabulary and/or morphological knowledge. A cross-sectional reading level-design was employed in order to determine differences in spelling, derivational morphology and vocabulary tasks between dyslexic students aged 13+ and age-matched and reading level matched control groups. The study confirmed a profound spelling impairment of dyslexic students in comparison with two control groups but this was not associated with poor vocabulary in relation with their age-peers. In contrast, they exhibited lower levels of morphological knowledge than age-matched controls but equivalent with the reading level controls. These results are interpreted in the light of current developmental models of spelling that support a reciprocal interaction between spelling and metamorphology. 相似文献
9.
Computerized adaptive testing in instructional settings 总被引：3，自引：0，他引：3
R. Edwin Welch Theodore W. Frick 《Educational technology research and development : ETR & D》1993,41(3):47-62
Item response theory (IRT) has most often been used in research on computerized adaptive testing (CAT). Depending on the model
used, IRT requires between 200 and 1,000 examinees for estimating item parameters. Thus, it is not practical for instructional
designers to develop their own CAT based on the IRT model. Frick improved Wald's sequential probability ratio test (SPRT)
by combining it with normative expert systems reasoning, referred to as an EXSPRT-based CAT. While previous studies were based
on re-enactments from historical test data, the present study is the first to examine how well these adaptive methods function
in a real-time testing situation. Results indicate that the EXSPRT-I significantly reduced test lengths and was highly accurate
in predicting mastery. EXSPRT is apparently a viable and practical alternative to IRT for assessing mastery of instructional
objectives. 相似文献
10.
林明贤 《华侨大学学报(哲学社会科学版)》2004,(2):83-87
调查了基础阶段的留学生与中国小学三年级的学生对汉语不同频率等级词汇的掌握情况,并对测试结果进行定量分析。研究表明：(1)甲级单音节词最易为学生掌握;(2)在词语的理解与掌握方面,全日制二年级上留学生的水平与中国小学三年级的学生相当,而全日制一年级下的留学生与中国小学三年级的学生还存在较大的差距。 相似文献
11.
认知诊断模型是新一代心理测量理论——认知诊断理论的核心。它可分为潜在特质模型和潜在分类模型两大类。其中,潜在分类模型主要用于分析被试的作答过程从而探讨被试的潜在知识结构,克服了CCT和IRT的缺陷,开创了教育与心理测量领域新的里程碑。本文首先介绍作为该类模型基础的规则空间模型,然后集中探讨在此基础上发展起来的较新的潜在分类模型,最后对这类模型进行了评价和展望。 相似文献
12.
《Structural equation modeling》2013,20(4):544-565
Both structural equation modeling (SEM) and item response theory (IRT) can be used for factor analysis of dichotomous item responses. In this case, the measurement models of both approaches are formally equivalent. They were refined within and across different disciplines, and make complementary contributions to central measurement problems encountered in almost all empirical social science research fields. In this article (a) fundamental formal similiarities between IRT and SEM models are pointed out. It will be demonstrated how both types of models can be used in combination to analyze (b) the dimensional structure and (c) the measurement invariance of survey item responses. All analyses are conducted with Mplus, which allows an integrated application of both approaches in a unified, general latent variable modeling framework. The aim is to promote a diffusion of useful measurement techniques and skills from different disciplines into empirical social research. 相似文献
13.
Veera Kallunki 《Research in Science Education》2013,43(2):827-845
Pupils’ qualitative understanding of DC-circuit phenomena is reported to be weak. In numerous research reports lists of problems in understanding the functioning of simple DC-circuits have been presented. So-called mental model surveys have uncovered difficulties in different age groups, and in different phases of instruction. In this study, the concept of qualitative understanding, and the content or position of reported mental models of DC-circuit phenomena are discussed. On the grounds of this review, new tools for investigating qualitative understanding and analysing external representations of DC-circuit phenomena are presented. According to this approach, the external representations of DC-circuit phenomena that describe pupils’ expressed conceptions of the topic should include both empirical-based models and theoretical explanations. In the empirical part of this study, third-graders (9-year-olds) learning DC-circuit phenomena in a comprehensive school in a small group were scrutinised. The focus of the study is the external representations manifested in the talk of the small group. The study challenges earlier studies, which claim that children exhibit a wide range of qualitative difficulties when learning DC-circuit phenomena. In this study it will be shown that even in the case of abstract subject matter like DC-circuit phenomena, small groups that highlight empirical-based modelling and activate talk can be a fruitful learning environment, where pupils’ qualitative understanding really develops. Thus, the study proposes taking a closer look at pupils’ external representations concerning DC-circuit phenomena. 相似文献
14.
Jennifer Hurstfield 《牛津教育评论》2013,39(2):137-149
Abstract Examination results for fifth‐year pupils in six different local education authorities are analysed with a view to establishing what differences in their performance can be assigned to the schools they attend. Using multi‐level models it is shown that, whilst in general the differences between schools are relatively small, the actual size in examination points is certainly not trivial. These differences are estimated for the schools in each LEA. Distinctions are drawn between explanatory models based on information about pupils’ background as opposed to prior attainment; the latter are shown to be more appropriate for comparisons between schools. Amongst the 11 data sets analysed there was little evidence that schools were differentially effective with different groups of pupils. 相似文献
15.
《Learning and Instruction》2003,13(1):53-72
The goal of this exploratory study was to uncover the construction processes which occur when pupils are taught to work with models in primary maths education. Two approaches were studied: ‘providing models’ versus ‘designing models in co-construction’. A qualitative observational study involved two groups of pupils of a primary school in the Netherlands. A series of lessons involving problem-oriented tasks was given. For this article’s purpose, we studied the learning processes of one pupil per condition in detail. Interpreting the results it is assumed that upper-grade pupils may be able to design models in co-construction as long as they receive sufficient teacher guidance. 相似文献
16.
Jean Cardinet 《European Journal of Psychology of Education - EJPE》1987,2(2):133-144
Proposals by psychologists to improve educational measurement lead to the construction of tests or of scales of development. For the assessment of pupils’ productions in the classroom, teachers seem to have other needs. Precise measurement is not required; what is wanted instead is qualitative information of a diagnostic nature, suggesting possible ways for doing remedial work. Information concerning one pupil rarely permits locating his position on a continuous scale of development, since learning does not proceed linearly. Assessment in the classroom should rather be considered as a communication process between teacher and pupils, leading after an unpredictable number of interactions, to a state of mastery of the educational objective. As experimental social psychology recently demonstrated, this mastery is not to be conceived as a personal characteristic of the pupil, but as the result of his adaptation to his social situation. Consequently, generalizing on the basis of this assessment is hazardous. 相似文献
17.
To what extent does phonology play a role in spelling English words? The written responses of deaf students and groups of hearing children to five tasks were subjected to quantitative and qualitative analyses. The first three tasks were used to see if deaf students utilized phonology when they generated their own words and to compare their spelling performance with that of hearing subjects. The fourth and fifth tasks were designed to compare the spelling performance of deaf and hearing subjects when they were required to reproduce visually presented common words. Results showed that deaf students, who were chronologically much older, were not better spellers than hearing children from the fifth grade. Analysis of data revealed little evidence that the deaf students involved in the present study utilize phonology in spelling. Nor did word-specific visual memory for entire words appears to play a role in spelling by deaf students. Rote visual memory for letter patterns and sequences of letters within words, however, appears to play a role in the spelling by deaf students. It is concluded that sensitivity to the stochastic-dependent probabilities of letter sequences may aid spelling up to certain point but phonology is essential for spelling words whose structure is morphophonemically complex.
相似文献18.
The study aimed to compare the differential effectiveness of explicit and implicit instruction of two Dutch spelling rules. Students with and without spelling disabilities were instructed a spelling rule either implicitly or explicitly in two experiments. Effects were tested in a pretest-intervention-posttest control group design. Experiment 1 suggested that explicit instruction of a morphological spelling rule led to instance-based knowledge in students with spelling disabilities and to rule-based knowledge in students without. Implicit instruction led to instance-based knowledge in students with spelling disabilities, and in the group without spelling disabilities no learning at all occurred. Experiment 2 revealed that explicit and implicit instruction of an orthographical spelling rule were equally effective in both groups and that the spelling knowledge they had acquired was instance-based. Findings suggest that explicit instruction is more effective than implicit instruction for the teaching of spelling rules when generalization is aimed at. 相似文献
19.
Until recently the majority of research undertaken into dyslexia focused on English‐speaking dyslexics, who tend to make significantly more phonological than visual errors. This led to a major assumption about the possible cause of dyslexia being a lack of phonological awareness. According to the phonological deficit theory, the level of phonological consistency of a language determines not only the reading speed but also the amount and types of reading and spelling errors made by dyslexic people. This theory has been seriously challenged by the results of a number of studies in more phonologically consistent languages, such as Greek, Italian and Japanese, where morphology seemed to play a more crucial role than the phonological structure of a language per se. The 116 dyslexic people who took part in this experiment were matched on age, sex, IQ and psycho‐educational performance. A total of 58 US English‐speaking dyslexic people were compared to 58 Greek dyslexic people. Both groups met the diagnostic criteria. Results demonstrated that Greek dyslexics were found to make significantly fewer phonological errors (11.0%) than the US dyslexics (85.5%, p < .000), but comparatively more visual (66.8% to US 14.0%, P < .000) and grammatical errors (22.2% to US 0.1%, p < .000) than their English‐speaking counterparts. These data showed highly significant quantitative and qualitative spelling differences. Greek dyslexics could be accurately differentiated from the US English dyslexics based on the three types of spelling errors. 相似文献
20.
A cross-sectional study tested Danish students' mastery of links between grammar and spelling (cf. the English link between past tense verbs and the -ed spelling for a word final /t/, e.g., miss
ed vs. mis
t). One hundred and forty-two students aged 10–17 spelled pseudo-word items with ambiguous phonemes, where the choice between a 'conditional' spelling (cf. English ed for /t/) and a simple spelling (cf. t for /t/) was predictable from the grammatical context but not from the sound. Overgeneralisations (conditional spellings used where simple spellings were appropriate) were controlled to obtain pure measures of grammatical spelling competence. The oldest group of participants performed near ceiling on four of five spelling problems studied while three younger groups in the experiment never did. The nature of the apparent grammatical hurdle in Danish spelling acquisition is discussed. 相似文献