Different Sets Of Items Research Articles

Additive and interactive effects of stimulus degradation: No challenge for CDP+.

S. O'Malley and D. Besner (2008) showed that additive effects of stimulus degradation and word frequency in reading aloud occur in the presence of nonwords but not in pure word lists. They argued that this dissociation presents a major challenge to interactive computational models of reading aloud and claimed that no currently implemented model is able to simulate additive effects in these conditions. In the current article, it is shown that the connectionist dual process model (CDP+) can simulate these effects because its nonlexical route is thresholded. The authors present a series of simulations showing that CDP+ can not only simulate the precise dissociation observed by O'Malley and Besner but more generally can produce additive effects for a wide range of parameter combinations and different sets of items. The nonlexical route of CDP+ was not modified post hoc to deal with the effects of stimulus quality, but it had been thresholded for principled reasons before it was known that these effects existed. Together, the effects of stimulus quality on word frequency do not challenge CDP+ but rather provide unexpected support for its architecture and processing dynamics.

Analysis of longitudinal randomized clinical trials using item response models

Patient-relevant outcomes, such as impairments, disability and health-related quality of life, are becoming increasingly popular as outcome measures in clinical research. These outcomes are generally assessed using questionnaires. In a longitudinal randomized clinical trial where the outcome is measured by a questionnaire or some other instrument consisting of a set of discretely scored items, treatment effects can be analyzed using item response theory. The problem addressed is how to take the estimation error in the estimates of the latent outcome variables into account in the estimation of the treatment effects. Three approaches are compared: plausible value imputation (PVI), concurrent marginal maximum likelihood (MML) estimation and a limited information two-step marginal maximum likelihood method. The results show that the power of the former two methods to detect small and moderate effect sizes is considerably larger than the power of the latter approach. An additional advantage of the PVI method as compared to MML is that the treatment effects can be estimated with standard software. An example using data from a longitudinal randomized clinical trial illustrates the use of the methods in a practical setting. It is shown that even when responses on different sets of items for different groups of patients are used for the data analysis, the power to detect the experimental effects is comparable to the power obtained when responses to all items for all patients are used in the analysis. This creates considerable flexibility in the design and use of measures in experiments.

The nature of phonological awareness throughout the elementary grades: An item response theory perspective

In the present study, the nature of Dutch children's phonological awareness was examined throughout the elementary school grades. Phonological awareness was assessed using five different sets of items that measured rhyming, phoneme identification, phoneme blending, phoneme segmentation, and phoneme deletion. A sample of 1405 children from kindergarten through fourth grade participated. Results of modified parallel analysis and analyses within the context of item response theory (IRT) showed phonological awareness to be unidimensional across different tasks and grades. Despite the evidence for a single underlying ability, the cognitive task requirements for the various tasks were found to differ. In addition to some overlap between the item sets, those for rhyming, phoneme identification, and phoneme blending were easier than those for phoneme segmentation and phoneme deletion. The results lend support to the assumption that phonological awareness is a continuum of availability for phonological representations which can range from partial availability (i.e., access) to full availability (i.e., access).

Quality of life in infants and children with atopic dermatitis: Addressing issues of differential item functioning across countries in multinational clinical trials

BackgroundA previous study had identified 45 items assessing the impact of atopic dermatitis (AD) on the whole family. From these it was intended to develop two separate scales, one assessing impact on carers and the other determining the effect on the child.MethodsThe 45 items were included in three clinical trials designed to test the efficacy of a new topical treatment (pimecrolimus, Elidel cream 1%) in the treatment of AD in infants and children and in validation studies in the UK, US, Germany, France and the Netherlands. Rasch analyses were undertaken to determine whether an internationally valid, unidimensional scale could be developed that would inform on the direct impact of AD on the child.ResultsRasch analyses applied to the data from the trials indicated that the draft measure consisted of two scales, one assessing the QoL of the carer and the other (consisting of 12 items) measuring the impact of AD on the child. Three of the 12 potential items failed to fit the measurement model in Europe and five in the US. In addition, four items exhibiting differential item functioning (DIF) by country were identified. After removing the misfitting items and controlling for DIF it was possible to derive a scale; The Childhood Impact of Atopic Dermatitis (CIAD) with good item fit for each trial analysis. Analysis of the validation data from each of the different countries confirmed that the CIAD had adequate internal consistency, reproducibility and construct validity.The CIAD demonstrated the benefits of treatment with Elidel over placebo in the European trial. A similar (non-significant) trend was found for the US trials.ConclusionThe study represents a novel method of dealing with the problem of DIF associated with different cultures. Such problems are likely to arise in any multinational study involving patient-reported outcome measures, as items in the scales are likely to be valued differently in different cultures. However, where all items in a scale fit both a single theoretical construct and the Rasch measurement model, it is feasible to conceive of outcome measures with a different set of items in each language.

Screening of phonological awareness in the early elementary grades: an IRT approach

The purpose of the present study was to explore the possibilities for the assessment of growth in phonological awareness of children in kindergarten and first grade. Phonological awareness was measured using four sets of items involving rhyming, phoneme identification, phoneme blending, and phoneme segmentation. The results of an exploratory factor analysis and analyses conducted within the framework of item response theory showed one latent ability to underlie the different sets of items, which nevertheless differed in difficulty. Analyses in terms of the children's ability further showed the phonological awareness measures to be sensitive to growth. The amount of information supplied by the different sets of items depended on the children's level of ability. The conclusion that it is possible to accurately monitor the development of children's phonological awareness in the early elementary grades appears to be justified, and this possibility opens up new perspectives for the early screening for reading problems and dyslexia.

High Dimensional Multivariate Mixed Models for Binary Questionnaire Data

SummaryQuestionnaires that are used to measure the effect of an intervention often consist of different sets of items, each set possibly measuring another concept. Mixed models with set-specific random effects are a flexible tool to model the different sets of items jointly. However, computational problems typically arise as the number of sets increases. This is especially true when the random-effects distribution cannot be integrated out analytically, as with mixed models for binary data. A pairwise modelling strategy, in which all possible bivariate mixed models are fitted and where inference follows from pseudolikelihood theory, has been proposed as a solution. This approach has been applied to assess the effect of physical activity on psychocognitive functioning, the latter measured by a battery of questionnaires.

Consumer‐based brand equity: improving the measurement – empirical evidence

PurposeThe present research aims to improve the measurement of consumer‐based brand equity. Current measurement of consumer‐based brand equity suffers from limitations, including: a lack of distinction between the dimensions brand awareness and brand associations, the use of non‐discriminant indicators in the measurement scales and of student samples.Design/methodology/approachBased on the recommendations of extant research, the scale constructed to measure consumer‐based brand equity in this study included brand personality measures. Brand associations were measured using a different set of items. Unlike many of the previous studies that had used student samples, the present study used a sample of actual consumers from an Australian state capital city. Confirmatory factor analysis employing structural equations modelling was used to measure consumer‐based brand equity in two product categories and across six brands.FindingsResults support the hypothesised four‐dimension model of consumer‐based brand equity across two product categories and six brands. Brand awareness and brand associations were found to be two distinct dimensions of brand equity as conceptualised in the marketing literature. The present study contributes to the understanding of consumer‐based brand equity measurement by examining the dimensionality of this construct.Originality/valueThe principal contribution of the present research is that it provides empirical evidence of the multidimensionality of consumer‐based brand equity, supporting Aaker's and Keller's conceptualisation of brand equity. The present research also enriched consumer‐based brand equity measurement by incorporating the brand personality measures, as recommended by previous researchers. While earlier studies were conducted using US and Korean samples, the present study also used a sample of Australian consumers.

Sequential estimation in variable length computerized adaptive testing

With the advent of modern computer technology, there have been growing efforts in recent years to computerize standardized tests, including the popular Graduate Record Examination (GRE), the Graduate Management Admission Test (GMAT) and the Test of English as a Foreign Language (TOEFL). Many of such computer-based tests are known as the computerized adaptive tests, a major feature of which is that, depending on their performance in the course of testing, different examinees may be given with different sets of items (questions). In doing so, items can be efficiently utilized to yield maximum accuracy for estimation of examinees’ ability traits. We consider, in this article, one type of such tests where test lengths vary with examinees to yield approximately same predetermined accuracy for all ability traits. A comprehensive large sample theory is developed for the expected test length and the sequential point and interval estimates of the latent trait. Extensive simulations are conducted with results showing that the large sample approximations are adequate for realistic sample sizes.

Use of item response theory to link 3 modules of functional status items from the Asset and Health Dynamics Among the Oldest Old study

McHorney CA. Use of item response theory to link 3 modules of functional status items from the Asset and Health Dynamics Among the Oldest Old study. Arch Phys Med Rehabil 2002;83:383-94. Objective: To link, by using item response theory (IRT), 3 modules of functional status items in the Asset and Health Dynamics Among the Oldest Old (AHEAD) study. Design: Secondary data analysis of the functional status items in the AHEAD study. In that study, participants completed a common set of functional status items and were randomly assigned to complete 1 of 2 modules containing different functional status items. Setting: A nationally representative panel study of elderly. Participants: US baseline data from 4655 respondents. Interventions: Not applicable. Main Outcome Measures: Nineteen common items and 2 sets of supplemental items that measure functional status. Results: A 2-parameter model for dichotomous items was used for linking the 3 modules of items. By using this model, both sets of supplemental items were successfully linked to the common items, allowing the placement of all items on the same underlying measure of ability. The small-muscle instrumental activities of daily living were the easiest of all the items for respondents to perform. The item on walking from the Longitudinal Study of Aging was the most difficult for respondents to perform. Conclusions: IRT-based linking methods were a useful way to overcome test dependency and to place items on a common metric even if different respondents answer different sets of items. Numerous important design features can degrade linking results and should be attended to in future linking studies. © 2002 by the American Congress of Rehabilitation Medicine and the American Academy of Physical Medicine and Rehabilitation

From primed to learn: the saturation of repetition priming and the induction of long-term memory

Although practice can make perfect, it is not clear how much practice is needed to trigger long-lasting performance gains on a given task. Here, using a letter enumeration task, we show that the transition of experience dependent performance gains to a relatively stable form, as well as the triggering of delayed, long-lasting, between session gains (both effects are considered manifestations of consolidation processes) is amount-of-practice dependent. We then show (a) that consolidation processes, once triggered, can proceed without further practice as a function of time and (b) that the triggering of consolidation processes is related to repetition priming effects—performance gains in processing a previously experienced item. However, we show that repetition priming effects saturate after a limited number of consecutive repetitions and reflect an initial, but potentially reversible, response to the repeated experience. Moreover, we show that one critical parameter determining the occurrence of repetition priming (but not skill learning) is the presence of interference (by a somewhat different set of items) prior to the primer presentation. Thus, our results suggest that the saturation of repetition priming effects, rather than priming per se, may be critical to the induction of slow learning processes and consolidation.

Convergent Validity of Alternative MMPI-2 Personality Disorder Scales

The Morey, Waugh, and Blashfield (1985) MMPI (Hathaway et al., 1989) personality disorder scales provided a significant contribution to personality disorder research and assessment. However, the subsequent revisions to the MMPI and the multiple revisions to the diagnostic criteria sets that have since occurred may have justified comparable revisions to these scales. Somwaru and Ben-Porath (1995) selected a substantially different set of items from the MMPI-2 (Butcher, Dahlstrom, Graham, Tellegen, & Kaemmer, 1989) to assess Diagnostic and Statistical Manual of Mental Disorders (4th ed.; American Psychiatric Association, 1994) personality disorder diagnostic criteria. In our study, we compared the convergent validity of these alternative MMPI-2 personality disorder scales with respect to 3 self-report measures of personality disorder symptomatology in a sample of 82 psychiatric outpatients. The results suggested that Somwaru and Ben-Porath's scales are as valid as the original Morey et al. scales and might be even more valid for the assessment of borderline, antisocial, and schizoid personality disorder symptomatology.

Manipulations of irrelevant information: Suffix effects with articulatory suppression and irrelevant speech

Numerous studies have demonstrated impaired recall when the to-be-remembered information is accompanied or followed by irrelevant information. However, no current theory of immediate memory explains all three common methods of manipulating irrelevant information: requiring concurrent articulation, presenting irrelevant speech, and adding a stimulus suffix. Five experiments combined these manipulations to determine how they interact and which theoretical framework most accurately and completely accounts for the data. In Experiments 1 and 2, a list of auditory items was followed by an irrelevant speech sound (the suffix) while subjects engaged in articulatory suppression. Although articulatory suppression reduced overall recall compared to a control condition, comparable suffix effects were seen in both conditions. Experiments 3 and 4 found reliable suffix effects when list presentation was accompanied by irrelevant speech. Experiment 5 found a suffix effect even when the irrelevant speech was composed of a set of different items. Implications for working memory, pre-categorical acoustic store, the changing-state hypothesis, and the feature model are discussed.

Neighborhood frequency does affect performance in the Reicher task: encoding or decision?

Three experiments using the Reicher task show that performance on low-frequency words is disrupted if the incorrect alternative forms a higher frequency word. This neighborhood frequency effect occurs for both energy and pattern masks and for different sets of items. When the upcoming word is primed and its accessibility is enhanced, the neighborhood frequency effect is eliminated. Experiments 4a and 4b tested the neighborhood frequency effect using a same-different task and a signal-detection analysis. Neighborhood frequency affected the decision criterion but not the sensitivity of the perceptual system. Experiment 5 showed that many words with a frequency in the range from 1 to 5 per million are not recognized out of context. These results are consistent with the hypothesis that frequency effects in the Reicher task are caused by a bias in the decision system and can be simulated with the stochastic activation-verification model.

The Relative Contributions of Injury Severity and Likelihood Information on Hazard-Risk Judgments and Warning Compliance

Research suggests that people base their judgments of product hazardousness on perceptions of the severity of potential injury. However, other research suggests that people base their risk perceptions on the likelihood of being injured. Four studies are presented that attempt to reconcile these findings. Studies 1 and 2 investigated whether the discrepancy could be attributed to the particular item lists used in the respective research. Study 1 showed that injury severity was the foremost predictor of perceived hazard in one list, but that injury likelihood was the best predictor in the other list. The two lists differed significantly on all the rating dimensions, suggesting that the items in the lists are at least partly responsible for the conflicting findings. Study 2, using a different set of items, confirmed that injury severity is the foremost predictor of hazard perceptions for consumer products. The last two studies examined the effects of injury likelihood and severity information in warnings on perceived product hazard and behavioral compliance. In Study 3, participants evaluated a set of product labels under the guise of a consumer marketing study in which the conveyed levels of injury severity and likelihood were incidentally manipulated. The results showed high severity warnings produced higher hazard ratings than low severity warnings. Injury likelihood produced no effect. Study 4 showed that a higher severity warning produced greater behavioral compliance than a low severity warning, but only for low injury likelihoods. Overall, this research: (a) provides an explanation for the conflicting results in hazard and risk perception research; and (b) demonstrates that injury severity is the primary determinant of lay persons' hazard perceptions for consumer products. The findings suggest that safety communications might have greater impact if they focused on injury severity, rather than (or to a lesser extent) the likelihood of getting hurt.

A Lognormal Approximation for the Collector's Problem

The collector's problem has been well-known for many years and is discussed in several texts on probability, for example Feller. Recent interest has focused on generalizations of the problem and, in line with our present objective, approximations to the distribution of the number TV of items that must be bought or collected to obtain a complete set of different items (Dawkins; Levin). The lognormal distribution provides a good approximation to the distribution of TV, and appropriate parameter values are found by the matching of moments, which has intuitive appeal.

Factor analysis, causal indicators and quality of life.

Exploratory factor analysis (EFA) remains one of the standard and most widely used methods for demonstrating construct validity of new instruments. However, the model for EFA makes assumptions which may not be applicable to all quality of life (QOL) instruments, and as a consequence the results from EFA may be misleading. In particular, EFA assumes that the underlying construct of QOL (and any postulated subscales or 'factors') may be regarded as being reflected by the items in those factors or subscales. QOL instruments, however, frequently contain items such as diseases, symptoms or treatment side effects, which are 'causal indicators'. These items may cause reduction in QOL for those patients experiencing them, but the reverse relationship need not apply: not all patients with a poor QOL need be experiencing the same set of symptoms. Thus a high level of a symptom item may imply that a patient's QOL is likely to be poor, but a poor level of QOL need not imply that the patient probably suffers from that symptom. This is the reverse of the common EFA model, in which it is implicitly assumed that changes in QOL and any subscales 'cause' or are likely to be reflected by corresponding changes in all their constituent items; thus the items in EFA are called 'effect indicators.' Furthermore, disease-related clusters of symptoms, or treatment-induced side-effects, may result in different studies finding different sets of items being highly correlated; for example, a study involving lung cancer patients receiving surgery and chemotherapy might find one set of highly correlated symptoms, whilst prostate cancer patients receiving hormone therapy would have a very different symptom correlation structure. Since EFA is based upon analyzing the correlation matrix and assuming all items to be effect indicators, it will extract factors representing consequences of the disease or treatment. These factors are likely to vary between different patient subgroups, according to the mode of treatment or the disease type and stage. Such factors contain little information about the relationship between the items and any underlying QOL constructs. Factor analysis is largely irrelevant as a method of scale validation for those QOL instruments that contain causal indicators, and should only be used with items which are effect indicators.

To Be Young, Gifted, and Strategic: Advantages for Memory Performance

Gifted and nongifted children's use of an organizational strategy was contrasted on multitrial free-recall tasks, using different sets of items on each trial. In an initial experiment, gifted children initially had higher levels of recall and strategic functioning than nongifted children, but this advantage was lost on later trials. While overall there was an advantage to memory of being strategic, this advantage was statistically significant for the gifted children only at trial 1, whereas it was significant for the nongifted children on trials 2 through 5. A sort-recall procedure was used in Experiment 2, with results indicating that gifted children benefited more than nongifted children when strategy use was simplified, while the results of Experiment 3, which used nonsense words as stimuli, demonstrated that gifted children demonstrated greater use of active strategies than nongifted children. The results of these experiments were interpreted as evidence that at least a portion of gifted children's advantage on free recall tasks lies in nonstrategic processes.

Two Cheers for the Big Five!

The degree of consensus on the Big Five is remarkable: When before in the history of personality has there been such substantive agreement? Pervin is concerned lest this consensus be overstated and overinterpreted as a major advance in personality as a whole rather than just in a restricted part of the personality domain. He has reason to be concerned. These factors keep recurring in different sets of items and in different languages, and they seem fairly stable over time. The recurrence and stability are important. They give us a bit of fairly solid ground on which to stand as we explore the wetlands of personality. But these are language-embedded folk concepts, as Tellegen (1991) reminded us. And they are only one level in the hierarchy of potential descriptors: Each factor can readily be analyzed into several distinguishable subfactors. These five do not cover many facets of personality that professional psychologists are interested in-goals, current concerns, attitudes, conflicts, anxieties, variabilities, and so forth. They certainly are of little use in understanding a complex personality such as that of Henry Murray as portrayed in the troublesome and startling biography by Robinson (1992). Not only is personality a large and variegated territory or collection of territories, but it is also one that we don't know how to divide into units. How can we conceptualize and study it without knowing what size and kind its pieces should be? The Big Five have their own units-the responses to the rating scales or questionnaires. These units are comparable to but not identical with the units used by other instruments. Granted that there is considerable consensus on the Big Five, granted that we can conclude that personality (or, at least, the perceptions of persons) can be summarized rather well by the Big Five, what is the next step in research in this area? Appropriate questions are: Why 5, and not 3, 7, or 16? Why these five? As Pervin says, the data indicate that something is there-what is it? Goldberg (1981) suggested that these factors are the five pieces of information we need to have when meeting a stranger. Digman (1990) suggested that the five may be related to limitations on human informationprocessing. Taking an evolutionary perspective, Buss (1991) wrote:

Relationship between two ways of measuring alcohol dependence

One of the main difficulties hampering research with the concept of the alcohol dependence syndrome is the lack of a set of agreed-upon operational definitions of each element composing the syndrome. To illustrate the possible impact of these different operationalizations of alcohol dependence on research results, this article shows the correlation between two different sets of items used to operationalize DSM-III-R alcohol dependence in a clinical sample. Results show that the correlations between the various sets of items are low. About 60% of the correlations are in between .21 and .40. These results suggest that different operationalizations of dependence may not be measuring the same phenomena, and should not be seen as interchangeable.

An irt-based model for dichotomous longitudinal data

The LLRA (linear logistic model with relaxed assumptions; Fischer, 1974, 1977a, 1977b, 1983a) was developed, within the framework of generalized Rasch models, for assessing change in dichotomous item score matrices between two points in time; it allows to quantify change on latent trait dimensions and to explain change in terms of treatment effects, treatment interactions, and a trend effect. A remarkable feature of the model is that unidimensionality of the item set is not required. The present paper extends this model to designs with any number of time points and even with different sets of items presented on different occasions, provided that one unidimensional subscale is available per latent trait. Thus unidimensionality assumptions within subscales are combined with multidimensionality of the item set. Conditional maximum likelihood methods for parameter estimation and hypothesis testing are developed, and a necessary and sufficient condition for unique identification of the model, given the data, is derived. Finally, a sample application is presented.