Estimating the severity of intellectual disability in adults: A Mokken scaling analysis of the Learning Disability Screening Questionnaire.

Murray, Aja Louise; McKenzie, Karen

doi:10.1037/a0032369

Cited by 7 publications

(7 citation statements)

References 30 publications

(36 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A single uni-dimensional model was specified, representing the theoretical assumption that the LDSQ measures a uni-dimensional construct of ID. This assumption has been supported in previous psychometric analyses of the LDSQ (Murray & McKenzie, 2013). Further, with only 7 items (6 with 'Read' and 'Write' combined into 'Literacy'); any model with more than one latent variable would have poor factor determination.…”

Section: Statistical Procedures Item Response Theory Analysismentioning

confidence: 65%

“…It is unfortunate that we were unable to assess this item because previous research has suggested that this item is a useful indicator of ID. For example, it has shown a high RUNNING HEAD: Gender Invariance LDSQ discrimination parameter (a scalability coefficient of 0.75 in a Mokken analysis) in previous research (Murray & McKenzie, 2013). Furthermore, because it represents a skill that is relatively easier than the other skills measured by the LDSQ (see the endorsement rates in Table 1), it contributes to the reliable measurement of ID at the more severe levels of impairment.…”

Section: Discussionmentioning

confidence: 95%

“…However, Murray and McKenzie (2013) did identify some additional benefits to the scale in terms of clinical and research applications. They found that the 6 out of 7 of the items exhibiting invariant item ordering: a property which means that information about levels of RUNNING HEAD: Gender Invariance LDSQ severity is contained not only in overall scores, but in individual item responses.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

An analysis of differential item functioning by gender in the Learning Disability Screening Questionnaire (LDSQ)

Murray

Booth

McKenzie

2015

Research in Developmental Disabilities

Self Cite

View full text Add to dashboard Cite

The Learning Disability Screening Questionnaire (LDSQ; McKenzie & Paxton, 2006) was developed as a brief screen for intellectual disability. Although several previous studies have evaluated the LDSQ with respect to its utility as a clinical and research tool, no studies have considered the fairness of the test across males and females. In the current study we, therefore, used a multi-group item response theory approach to assess differential item functioning across gender in a sample of 211 males and 132 females assessed in clinical and forensic settings. Although the test did not show evidence of differential item functioning by gender, it was necessary to exclude one item due to estimation problems and to combine two very highly related items (concerning reading and writing ability) into a single literacy item Thus, in addition to being generally supportive of the utility of the LDSQ, our results also highlight possible areas of weakness in the tool and suggest possible amendments that could be made to test content to improve the test in future revisions.

show abstract

Section: Statistical Procedures Item Response Theory Analysismentioning

confidence: 65%

Section: Discussionmentioning

confidence: 95%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An analysis of differential item functioning by gender in the Learning Disability Screening Questionnaire (LDSQ)

Murray

Booth

McKenzie

2015

Research in Developmental Disabilities

Self Cite

View full text Add to dashboard Cite

show abstract

“…For example, Mokken scaling analysis has proven useful in disability research where estimating the severity or predicting the progression of difficulties is a key consideration in understanding and treating a disorder (Kingston et al, 2012;Watson et al, 2012). Similarly, Murray and McKenzie (2013) for a number of reasons: it was developed specifically as a screen for ID; it was designed to have a very short administration and scoring time; it does not require the user to have a particular professional qualification or training; and a series of studies have found it to have good psychometric properties (see section 2.2). In addition, two recent reviews of screening tools that have been used specifically to screen for ID in children (McKenzie & Megson, 2012) and those that have screened for a range of disabilities, including ID (Maulik & Darmstadt, 2007) indicated that none of the reviewed tools displayed sufficiently robust psychometric properties to recommend their use for specific screening for ID in children.…”

Section: Introductionmentioning

confidence: 99%

Estimating the level of functional ability of children identified as likely to have an intellectual disability

Murray¹,

McKenzie²,

Booth³

et al. 2013

Research in Developmental Disabilities

Self Cite

View full text Add to dashboard Cite

Screening tools can provide an indication of whether a child may have an intellectual disability (ID). Item response theory (IRT) analyses can be used to assess whether the statistical properties of the tools are such that their utility extends beyond their use as a screen for ID. We used non-parametric IRT scaling analyses to investigate whether the Child and Adolescent Intellectual Disability Screening Questionnaire (CAIDS-Q) possessed the statistical properties that would suggest its use could be extended to estimate levels of functional ability and to estimate which, (if any), features associated with intellectual impairment are consistently indicative of lower or higher levels of functional ability. The validity of the two proposed applications was assessed by evaluating whether the CAIDS-Q conformed to the properties of the Monotone Homogeneity Model (MHM), characterised by uni-dimensionality, local independence and latent monotonicity and the Double Monotone Model (DMM), characterised by the assumptions of the MHM and, in addition, of nonintersecting item response functions. We analysed these models using CAIDS-Q data from 319 people referred to child clinical services. Of these, 148 had a diagnosis of ID. The CAIDS-Q was found to conform to the properties of the MHM but not the DMM. In practice, this means that the CAIDS-Q total scores can be used to quickly estimate the level of a person's functional ability. However, items of the CAIDS-Q did not show invariant item ordering, precluding the use of individual items in isolation as accurate indices of a person's level of functional ability.

show abstract

“…The item selection is based on a nonparametric item response theory (NIRT) model known as the monotone homogeneity model (Sijtsma & Molenaar, 2002, Chapter 2). Mokken scale analysis is used to construct tests in various research areas such as psychology, for assessing psychological distress and well-being (Watson, Wang, Thompson, & Meijer, 2014), depression and anxiety (Bech, Bille, Moller, Hellström, & Ostergaard, 2014), disability in activities of daily living (Kingston et al, 2012), learning disability (Murray & McKenzie, 2013), and sexual sadism (Nitschke, Osterheider, & Mokros, 2009). Mokken scale analysis uses three types of scalability coefficients for assessing the quality of (a) item pairs, (b) individual items, and (c) a set of items.…”

mentioning

confidence: 99%

Bias in Point Estimates and Standard Errors of Mokken’s Scalability Coefficients

Kuijpers

Ark

Croon

et al. 2016

Applied Psychological Measurement

View full text Add to dashboard Cite

Mokken scale analysis uses three types of scalability coefficients to assess the quality of (a) pairs of items, (b) individual items, and (c) an entire scale. Both the point estimates and the standard errors of the scalability coefficients assume that the sample ordering of the item steps is identical to the population ordering, but due to sampling error, the sample ordering may be incorrect and, consequently, the estimates and the standard errors may be biased. Two simulation studies were used to investigate the bias of the estimates and the standard errors of the scalability coefficients, as well as the coverage of the 95% confidence intervals. Distance between item steps was the most important design factor. In addition, sample size, number of items, number of answer categories, and item discrimination were included in the design. Bias of the standard errors was negligible. Bias of the estimates was largest when all item steps were identical in the population, especially for small sample sizes. Furthermore, bias of the estimates decreased as number of answer categories increased and as item discrimination decreased. Coverage of the 95% confidence intervals was close to .950, but for small sample size coverage deteriorated. Coverage also became poorer as number of items increased, in particular for dichotomous items.

show abstract

Estimating the severity of intellectual disability in adults: A Mokken scaling analysis of the Learning Disability Screening Questionnaire.

Cited by 7 publications

References 30 publications

An analysis of differential item functioning by gender in the Learning Disability Screening Questionnaire (LDSQ)

An analysis of differential item functioning by gender in the Learning Disability Screening Questionnaire (LDSQ)

Estimating the level of functional ability of children identified as likely to have an intellectual disability

Bias in Point Estimates and Standard Errors of Mokken’s Scalability Coefficients

Contact Info

Product

Resources

About