The Item Response Theory framework encompasses a wide range of psychometric methods and mathematical models (latent trait models) to study individual responses to items defining a measurement instrument (multi-item scales such as questionnaires or tests) that is used to assess a specific construct (...

learn more… | top users | synonyms (1)

0
votes
0answers
14 views

How to best approach imputing missing dichotomous data in R for later analysis in a 3PL irt model?

I have data I'm trying to analyze right now and am investigating imputing responses. All information is dichotomous (right/wrong, 0/1), but some cases are left blank because it was a speeded reading ...
0
votes
0answers
17 views

Consequences of violating assumptions about errors in IRT/Rasch based models

In the sorts of measurement models to which one might apply IRT models, including Rasch models, there is not thought to be an error associated with the latent variable. Rather, the latent variable is ...
1
vote
0answers
26 views

IRT modeling for questionnaire develop with a clinical:normal population of 15:1

I am trying to apply IRT to a questionnaire for screening purpose -- I have 3000 clinical population but only 200 normal population, would the result useful? The item plots and information function ...
0
votes
0answers
56 views

Problem in bootstrap analyses (boot package)

I am trying to understand why a subset of 2-parameter binary logistic IRT models I am bootstrapping estimates for (i.e., the discrimination and difficulty parameter estimates) give rise to the same ...
1
vote
1answer
94 views

Plausbility of parameter estimates in a 2PLM IRT model: A case of inherently sparse data

This question relates to my previous query regarding differences in IRT parameter estimates (2PLM model) between the ltm package in R and the Mplus latent variable program which is linked here: 2PLM ...
0
votes
1answer
19 views

Is using Multidimensionsl IRT model for a combined test of English + Maths + Science correct?

We need to score a combined test of English + Maths + Science. Would prefer to take IRT route to classical scoring as want to identify top 0.5% performers. Looked into multidimensional models as an ...
0
votes
0answers
13 views

Maximum acceptable discrimination parameter range in a 2PL model and its effect on SE

2PL model allows the discrimination value to vary for each question, but what is the maximum range beyond which the accuracy of the models suffers significantly? Or it does not matter? I feel that the ...
2
votes
1answer
75 views

2PLM IRT modeling of rare event behavioral data: Why changing discrimination and difficulty values?

I am using the 2PLM (2-parameter logistic model) IRT model to examine how sets of very rare (negative/aversive) maternal behaviors (towards their children) are associated with a priori ...
0
votes
0answers
11 views

testing optimal likert range using grm models (IRT)

My current project involves selecting a single item (for experience sampling) that best represents a multi-item 5-point Likert scale. I have identified the single item I want to use. However, my ...
1
vote
1answer
52 views

Graded Response Model: Combining categories

I have some items, measured with 5-point Likert scale (e.g., Strongly Agree, Agree, Neutral, Disagree, Strongly Disagree), to model using Graded Response Model. However, the analysis runs extremely ...
0
votes
0answers
71 views

negative LRT statistic value

I am still working on an item response theory (IRT) analysis to find differential item functioning (DIF) in any of the items of a 17-item graded response likert scale. To briefly summarize what we'...
0
votes
0answers
30 views

How to calculate test information in computerized adaptive tests

Under Item Response Theory, test information $I(\hat\theta)$ is a function of the examinee's estimated ability $\hat\theta$, discovered a the end of the test, and the items that were answered during ...
0
votes
0answers
25 views

Does it make sense for pairwise correlation to be uniformly higher than an ability?

I am fitting a graded response model to analyze a 16 item, 5 ordered response category scale. It shows univariate properties in an EFA with one very strong principal component. The distribution of ...
0
votes
0answers
37 views

How do you interpret/feedback irt theta scores?

In CTT we would say something like: Your score is higher than 80% of people in the normgroup. How do we interpret/feedback a theta score of 0.85? I know that it is supposed to be 'item-referenced' as ...
1
vote
1answer
46 views

raising the probability of correct answers of nextItem (catR)

Using the catR package I am trying to create a nextItem call that respondents would answer correctly about 65% of the time (even if that means the method is not as efficient as it could be). Children ...
2
votes
1answer
103 views

How should I calculate performance with 3 kinds of response (yes, no and not applicable)?

I am having trouble calculating employee performance. I have an observation form with 34 behaviours, but not all of the behaviours are observed at one given time because it depends on the topic being ...
0
votes
0answers
19 views

Estimating optimal number of items for adaptive testing

I am trying to find out what would be the optimal fixed length of a computer adaptive IRT scored ability test. I have the 2PL parameters of the items. I think the right question to ask is: How to ...
1
vote
1answer
51 views

Dealing with Extreme Response Style

My survey data includes a battery of 36 Likert-scale questions, which are the IVs of interest in my analysis. Respondents rank how "alike" they are to an individual being described in each item. ...
0
votes
0answers
40 views

calculate mirt model with some fixed item parameters

I would like to calculate a 2pl mirt model with parameters for some items fixed. They come from a previous model. ...
0
votes
0answers
37 views

Comparing rasch.mml2 estimates to Winsteps

With the same set of item responses I get different item parameters using Winsteps and the "rasch.mml2" function in the 'sirt' package in R. The difference is about -.61 logits, such that rasch.mml2 ...
0
votes
0answers
23 views

Distractor analysis in language test

The items on my test contain variable number of distractors, and I would like to evaluate the quality of those distractors based on how often they get picked by students. Ideally, I would like to ...
1
vote
0answers
20 views

CFA model with systematic temporal correlation between measures

I'm looking to fit CFA models to data in the case where measures have systematic temporal correlations between them. I'm familiar with autoregressive approaches, such as those described on Dave Kenny'...
1
vote
1answer
46 views

Compare covariance ratio

I am using a nonparametric item response theory method called Mokken scale analysis. One of the coefficients that is calculated is called the item scalability coefficient, and it is calculated as the ...
0
votes
0answers
12 views

runtime calculation of irt person-fit statistics for single person

I currently have a large (500+ items) 2PL model (in the form of item parameters) that I use for irt adaptive testing with catR. Each person do a small subset of these items cc.40 items. Its easy to ...
0
votes
1answer
83 views

Detecting Differential Item Functioning (DIF) using ordered logistic regression

I am in a situation in which I want to investigate whether test items of a questionnaire appear to have DIF. The items are polytomous and ranges from 1 to 5, with 5 being the most positive answer. I'...
2
votes
1answer
89 views

Is empirical reliability in IRT the counterpart of internal consistency in CTT?

In IRT it is not meaningful to compute internal consistency coefficients such as Cronbachs alpha, because standard error of measurement (and thus measurement precision) is not assumed uniform across ...
2
votes
2answers
92 views

Acceptable values for discrimination parameter - 2PL IRT Model

What is the acceptable range for discrimination parameters with the two-parameter IRT model? I have information from Baker (2001) but would love additional information. I have heard discrimination ...
0
votes
0answers
116 views

How to compare theta estimates and its standard errors to true test score in IRT?

I'm working on analysis of a multiple choice test by means of Item Response Theory (IRT) 3-parameter model. I've got the estimates for theta and its standard errors for each examinee. I want to make ...
0
votes
0answers
123 views

Different results in estimating 3PL model parameters in IRTPRO and mirt(R)

Can someone explain why I obtain different a, b, and c parameters estimates when I use IRTPRO3 and the package mirt from R? The method both uses are Bock and Aiken (1981) - IRTPRO calls BAEM and R ...
2
votes
1answer
102 views

Meaning of large values of parameter b (|b| >>) 4 in IRT theory

I'm working with a set of data from a 100 itens, 5 alternatives, medicine test and analyzing them by means of IRT (. The IRT - 3 parameter model yielded some values of b that are very large (...
1
vote
1answer
114 views

how do you estimate irt parameters if Theta and response is given?

I have good Theta estimates for people (from an already existing test). These people have also answered a few (2-5) untried experimental items. How can I get the a,b params for these new items given ...
3
votes
1answer
121 views

How to interpret meaning of regressors in this logistic regression model?

I'm trying to understand the model in this paper where they treat the item response theory model as a form of logistic regression. In the model the probability of getting an item (question) correct ...
1
vote
1answer
27 views

Can the test information function be used for a field test item bank?

I am field testing a few forms of items (with embedded anchor items) and will be analyzing the items using IRT, a 2PL model. These items will likely be used to create an item bank that can then create ...
2
votes
1answer
176 views

MCMC Estimation of Multidimensional 2PL IRT Model Using JAGS

I'm trying to prepare for some more advanced work involving MIRT models I'll be doing later this year by fitting a very simple multidimensional 2PL model to some simulated data using MCMC methods in ...
0
votes
0answers
47 views

Raschmodel on the single dimension as modeltest for mirt?

For unidimensional dichotomous IRT-Models testing the Rasch Model is a necessary requirement. What about applying multdimensional IRT-Models? Are there any other informationscources except AIC and BIC?...
0
votes
1answer
29 views

Internal consistency and other item analyses

Is it appropriate to run internal consistency and other item analyses on a test that has questions with different response formats. To be clearer, all questions have a likert response, but some are 5 ...
5
votes
1answer
70 views

BIC in Item Response Theory Models: Using log(N) vs log(N*I) as a weight

In IRT software packages and in the literature it is common to calculate the BIC as $$ \mathrm{BIC} = -2 \cdot \mathrm{logLik} + \log(N)\mathrm{Npars} $$ where $N$ is the number of rows in wide ...
1
vote
1answer
88 views

Questions regarding interpretation of item parameters: inconsistent results between classical item analysis and item response analysis

I was not trained as a psychometrician, so my questions may be concept-related. If you know different resources, books, or articles that can clear my confusions, please let me know. Thank you very ...
3
votes
1answer
143 views

Is it possible to do IRT distractor analysis using R?

I've been using the mirt package to analyse a few response matrixes I have through IRT. However, every time I need to perform distractor analysis, I end up having ...
4
votes
1answer
295 views

Questions Regarding Item Response Models – the 3PL model vs. the mixture of 2PL and 3PL model

I currently work on an item analysis for an assessment. The assessment consists of 25 multiple-choice questions. Each question has 4 choices with one correct answer. I used different IRT models to ...
2
votes
1answer
107 views

Item discrimination of poorly targeted items

In test theory, it appears to be widely recognized that very "easy" or "very difficult" items, relative to the ability of the sample of respondents, will have deflated correlations with the rest of ...
1
vote
0answers
32 views

How to calculate the parameter value for a test with Item Response Theory?

Given a set of responses to a test with multiple choice I wish to analyse it with Item Response Theory: wikipedia on IRT. I am planing to use the 3PL (3 parameters) in the Item response function. How ...
0
votes
0answers
34 views

Is a representative sample necessary to assess construct validity?

To generalize results to a greater population, a representative sample is necessary. In developing a psychometrically valid instrument, via confirmatory factor analysis or item response theory, we are ...
0
votes
1answer
162 views

Misfitting of drift rate in Wiener model

In a binary-decision experiment, the accuracy and response time of some subjects were recorded. My goal is to fit a Wiener model to response time and accuracy data. The binary experiment has three ...
1
vote
0answers
63 views

Recode Binary to scale Variables

I'm looking to find information to recode a set of dichotomous response variables to preferable a 1-5 scale. I have several response variables which when combined with PCA clearly depict certain ...
1
vote
1answer
562 views

Calculate Cronbach's alpha for polytomous items in R

Does anyone know whether there is a function which can calculate Cronbach's alpha for polytomous items with different categories in R?
0
votes
0answers
173 views

Itemfit to IRT model with missing data

I have matrix of dichotomus correct/false answers with many random missing data. (The data comes from an ability test where questions were randomly drawn from an item bank.) I am trying to find out ...
1
vote
1answer
75 views

Cut Score Determination in IRT

Cut score or cut point is a minimum achievement or ability that examinees should get in order to get a 'Pass'. In CTT, MCQ scoring in the form of percent-correct scores are applied. Let say we ...
0
votes
0answers
38 views

Validity in IRT Style

From my reading, I found that IRT generally provides more sophisticated information. Therefore, in regards of unidimensional 3PL IRT model, how should I report the finding about validity in ...
1
vote
1answer
40 views

Reading recommendations for psychometric refinement

a research project turned up a large number of survey instruments on a specific topic. There is a great deal of conceptual item overlap in these instruments, but they do differ in some key ways, ...