Multiple Group Method Research Articles

Comparison of Methods for Adjusting Incorrect Assignments of Items to Subtests

A common question in test evaluation is whether an a priori assignment of items to subtests is supported by empirical data. If the analysis results indicate the assignment of items to subtests under study is not supported by data, the assignment is often adjusted. In this study the authors compare two methods on the quality of their suggestions to adjust incorrect assignments of items to subtests. The confirmatory common factor (CCF) method is often used in practice. However, previous research reported rather poor quality of the suggested adjustments. Therefore, the CCF method is compared with a less often used but promising method, the oblique multiple group (OMG) method. The authors compared both methods with a simulation study taken under various conditions. For each method, several adjustment procedures were studied. The best adjustment procedure within the OMG method performed better than or highly comparable to the procedures within the CCF method.

The Empirical Verification of an Assignment of Items to Subtests

This study compares two confirmatory factor analysis methods on their ability to verify whether correct assignments of items to subtests are supported by the data. The confirmatory common factor (CCF) method is used most often and defines nonzero loadings so that they correspond to the assignment of items to subtests. Another method is the oblique multiple group (OMG) method, which defines subtests as unweighted sums of the scores on all items assigned to the subtest, and (corrected) correlations are used to verify the assignment. A simulation study compares both methods, accounting for the influence of model error and the amount of unique variance. The CCF and OMG methods show similar behavior with relatively small amounts of unique variance and low interfactor correlations. However, at high amounts of unique variance and high interfactor correlations, the CCF detected correct assignments more often, whereas the OMG was better at detecting incorrect assignments.

Scoring ordinal variables for constructing composite indicators

In order to provide composite indicators of latent variables, for example of customer satisfaction, it is opportune to identify the structure of the latent variable, in terms of the assignment of items to the subscales defining the latent variable. Adopting the reflective model, the impact of four different methods of scoring ordinal variables on the identification of the true structure of latent variables is investigated. A simulation study composed of 5 steps is conducted: (1) simulation of population data with continuous variables measuring a two-dimensional latent variable with known structure; (2) draw of a number of random samples; (3) discretization of the continuous variables according to different distributional forms; (4) quantification of the ordinal variables obtained in step (3) according to different methods; (5) construction of composite indicators and verification of the correct assignment of variables to subscales by the multiple group method and the factor analysis. Results show that the considered scoring methods have similar performances in assigning items to subscales, and that, when the latent variable is multinormal, the distributional form of the observed ordinal variables is not determinant in suggesting the best scoring method to use.

TRS 상의 개별/그룹 통신을 위한 효율적인 키 분배 기법

주파수공용통신(TRS: Trunked Radio Service)이란 무선통신을 하는 사람이 특정한 주파수를 이용하던 종래의 무선통신방식과는 달리 중계소에 할당된 소수의 주파수를 다수의 이용자가 공동으로 사용하는 방식을 말한다. TRS 시스템의 가장 큰 특징은 일대 다수의 그룹 및 지령 통신방식이다. TRS 시스템의 구성은 여러 개의 그룹으로 구성되며, 각 그룹은 업무내용에 관련된 유사한 목적을 가진 사용자들의 단말기로 구성된다. 위와 같은 여러 목적에 따라 다양한 형태의 연결이나 그룹 통신이 이뤄질 경우, 여러 가지 형태의 공격에 노출될 수 있으며, 대규모 통신을 위한 키 분배 혹은 설정에 많은 문제점을 가질 수 있다. 본고에서는 TRS 상에서 안전한.통신을 수행하는데 있어 필수 요소인 그룹 키 분배방식을 고찰하며, 통신 횟수를 줄이면서도 참여자 인증을 수행할 수 있는 효율적인 그룹 키 분배 방식을 제안하였다. It used exclusively the radio communication where is the TRS(Trunked Radio Service) at frequency where the person whom it does is specific with hitherto radio communication method differently frequency of the decimal which is allocated to the relay station it talks the at the room which the multiple user uses with commonness. The TRS system the most big feature is the region multiple group and order communication method. The TRS the composition of system is composed of the multi mind group, the each group is composed of the terminal of the users who have the objective which is similar relates in business contents. With above it follows in same multi objective and the connection of the form which is various or group communication accomplishes and quality case, a possibility a or of having many problem point in key distribution for a large scale communication there is it could be exposed to attack of the form which is various. There is a place where it accomplishes the communication which is safe at the TRS from research which it sees it investigates group key distribution method which is an essential element. The method which it sees when it reduces a communication frequency, it stands but is the user, it proposes the efficient group key distribution method it will be able to accomplish.

Invariance of SCL‐90‐R dimensions of symptom distress in patients with peri partum pelvic pain (PPPP) syndrome

There are no studies available that have examined the factorial invariance of dimensions underlying the Symptom Checklist-90-Revised (SCL-90-R) across at least three distinct samples. In the following study, we wished to determine whether a dimensional model comprising eight primary factors previously identified in psychiatric out-patients, phobics and the general population (Arrindell & Ettema, 2003) could be extended to a homogeneous sample of pain patients comprising females suffering from peri partum pelvic pain (PPPP) syndrome (N = 413). The internal consistency and discriminant validity of the dimensions were also examined. The SCL-90-R and measures of disability, pain-related fear, pain intensity and fatigue were administered to the participants. The multiple group method was used to determine factorial invariance. Pearson correlations were determined between the SCL-90-R and aforementioned measures. The factorial invariance of an 8-dimensional model of primary factors underlying the SCL-90-R, namely, agoraphobia, anxiety, depression, somatization, cognitive-performance deficits, interpersonal sensitivity-mistrust, acting-out hostility and sleep difficulties, was extended with success to the present sample of PPPP patients. In spite of substantial correlations between the internally consistent SCL-90-R symptom dimensions, some evidence of discriminant validity was reported in that specific subscales showed different patterns of correlations with measures of disability, pain-related fear, pain intensity and fatigue. The 8-dimensional system based on the work of Arrindell and Ettema (2003) was invariant across psychiatric patients, phobics, the general population and pain patients. The invariance of the SCL-90-R hostility dimensions may have implications for a re-formulation of Watson and Clark's tripartite model of general distress, specific anxiety and specific depression.

Organisational citizens or reciprocal relationships? An empirical comparison

PurposeThis paper aims at contributing to the debate on organisational citizenship behaviour (OCB) by developing a theory‐driven measure of cooperative behaviour within organisations, called organisational solidarity (OS).Design/methodology/approachData are gathered through a survey among 674 employees from nine organisations. Scales are constructed using the multiple group method. OLS regression is used to test the hypotheses.FindingsThe data analyses show that reciprocity is an important mechanism to bring about cooperation within organisations. Based on this, a distinction is made between horizontal and vertical OS.Research limitations/implicationsThe major shortcoming of this research is that some of the results may be influenced by same source bias. The research implies that cooperative types of employee behaviour – such as OCB – depend on the behaviour of others. Furthermore, these kinds of behaviour can be divided into a horizontal and a vertical dimension.Practical implicationsThe findings suggest that supervisors can play a facilitating role in creating and sustaining cooperative behaviour of employees.Originality/valueThis paper contributes to the literature on OCB by examining how this kind of behaviour is affected by the behaviour of supervisors and co‐workers. Secondly, whereas other articles focus on either horizontal or vertical dimensions of cooperative behaviour, this paper focuses on both dimensions simultaneously.

Validating the Level of Stability Index for Children

Objective: The Level of Stability Index for Children (LSIC) is a multidimensional, self-report, rapid assessment instrument for assessing emotional and behavioral tendencies children may exhibit toward self or others. The LSIC describes children’s propensity toward depression, suicidal ideation, anger, and aggression. Method: Self-report survey instruments, including the LSIC and two measures for construct validation, were administered to a purposive sample of 426 children from various school and agency settings. Results: Strong evidence was found for reliability, content, and factorial validity. Alpha coefficients ranged from .74 to .87 for LSIC subscales. Confirmatory factor analyses were conducted using the multiple group method and structural equation modeling. Convergent and discriminant analyses produced preliminary evidence for LSIC construct validity. Conclusion: The LSIC showed strong evidence of reliability and validity for younger children (7-12) and adolescents (13-18). Assessment tools can shed light on the complex mental health issues that social workers encounter when working with children in care.

Success factors for information technology supported international technology transfer: Finding expert consensus

Information technology (IT)-supported international technology transfer (ITT) is complex, risky, and fails often. No empirical studies are available on the factors that affect the success of IT-supported ITT. We review applicable theories (i.e. diffusion of innovation theory) and empirical research in conventional technology transfer to develop such a model. We carry out a multiple focus group method to rank factors that affect the success of IT-supported ITT and then apply a branch and bound method to derive a consensus ranking of these factors. The identified consensus ranking sheds light on factors that are similar to those of DOI theory and suggests a pattern of factors that affect IT-supported ITT.

Multiple GMDH models for estimating resource requirements

Accurate estimation or prediction of the resource required for a project is very important for construction. The more accurate the prediction model, the greater the potential for cost savings will be through elimination of any redesign and the minimization of the maintenance expenses. Contractors can also make use of the models for last‐minute bid estimation. In the past the estimators perform the task by analogy with similar previous projects. This approach highly relies on their experience and knowledge. Owing to the lack of a scientific and easily apprehensible method in resource estimation, prediction outcomes are mainly based on humans’ perception, which is inconsistent and exhibits large variations. This paper proposes the use of multiple Group Method of Data Handling (GMDH) models in developing models for resource estimation. The illustrative example has demonstrated the high accuracy of the approach which is superior to other architectures based on artificial neural networks.

A confirmatory factor analysis of the Brief Psychiatric Rating Scale in a homeless sample.

This study used a confirmatory factor analysis procedure, the Oblique Multiple Group Method (OMG), with the Brief Psychiatric Rating Scale (BPRS) on a sample of homeless individuals who had both a severe mental illness and a substance use disorder. The hypothesized five-factor model of Guy (1976) accounted for 93% of the possible variance, and all the appropriate scales had their highest loading on their respective hypothesized factor. In addition, the Guy model accounted for more variance than did an alternative model. The five factors were labelled: thinking disorder, anergia, anxiety-depression, hostility-suspicion, and activity.

Phobic anxiety in 11 nations: Part I: Dimensional constancy of the five-factor model

The Fear Survey Schedule-III (FSS-III) was administered to a total of 5491 students in Australia, East Germany, Great Britain, Greece, Guatemala, Hungary, Italy, Japan, Spain, Sweden, and Venezuela, and submitted to the multiple group method of confirmatory analysis (MGM) in order to determine the cross-national dimensional constancy of the five-factor model of self-assessed fears originally established in Dutch, British, and Canadian samples. The model comprises fears of bodily injury–illness–death, agoraphobic fears, social fears, fears of sexual and aggressive scenes, and harmless animals fears. Close correspondence between the factors was demonstrated across national samples. In each country, the corresponding scales were internally consistent, were intercorrelated at magnitudes comparable to those yielded in the original samples, and yielded (in 93% of the total number of 55 comparisons) sex differences in line with the usual finding (higher scores for females). In each country, the relatively largest sex differences were obtained on harmless animals fears. The organization of self-assessed fears is sufficiently similar across nations to warrant the use of the same weight matrix (scoring key) for the FSS-III in the different countries and to make cross-national comparisons feasible. This opens the way to further studies that attempt to predict (on an a priori basis) cross-national variations in fear levels with dimensions of national cultures.

Factor structure of the expanded Brief Psychiatric Rating Scale.

This study investigated the factor structure of the expanded Brief Psychiatric Rating Scale (BPRS) on a sample of severe mentally ill homeless individuals. A confirmatory factor analysis using the Oblique Multiple Group method supported the typical five factor solution found in previous studies with the original BPRS. The five factors were labeled Thinking Disorder. Withdrawal. Anxiety-Depression, Hostility-Suspicion, and Activity. Alpha coefficients for four of the scales ranged from .73 to .81; however, the alpha coefficient for the Hostility-Suspicion scale was only .49.

Factor structure of the expanded Brief Psychiatric Rating Scale

This study investigated the factor structure of the expanded Brief Psychiatric Rating Scale (BPRS) on a sample of severe mentally ill homeless individuals. A confirmatory factor analysis using the Oblique Multiple Group method supported the typical five factor solution found in previous studies with the original BPRS. The five factors were labeled Thinking Disorder, Withdrawal, Anxiety-Depression, Hostility-Suspicion, and Activity. Alpha coefficients for four of the scales ranged from .73 to .81; however, the alpha coefficient for the Hostility-Suspicion scale was only .49. © 1997 John Wiley & Sons, Inc. J Clin Psychol 53: 451–454, 1997.

Cross-national validity of dimensions of family functioning: First experiences with the Dutch version of the McMaster Family Assessment Device (FAD)

The present study describes the first psychometric findings obtained in The Netherlands with the Dutch version of the Family Assessment Device (FAD) which was originally developed in the Anglo-American cultural context. In a sample of community volunteers, confirmatory analysis (multiple-group method) provided evidence of factorial validity of the FAD measuring constructs. Only 3 out of 60 items were found to be biased and had to be deleted from their a priori defined scales. Reliability and homogeneity indices pertaining to each FAD dimension were good. Despite (very) high correlations among FAD factors/scales, further analyses were focused on determining their convergent and divergent validity which offered good support for such. A higher-order analysis which incorporated reliable scales of the FAD and the Family Environment Scale yielded a two-factor composition: General Family Functioning and Family Influence / Power and Integration. There was evidence to support the viewpoint that a general measure of family functioning may be utilized which is broader in terms of content than the already existing subscale measure termed General Functioning. In line with findings pointing to the ability of the FAD to distinguish between families of psychiatric patients and nonclinical families, the great majority of the FAD subscales, especially Problem Solving and General Functioning, were found to correlate with psychological symptom states as assessed with the Symptom Checklist-90-R. Specific subscales were found to be affected by educational level, while none were affected by sex, age, or religious affiliation. All in all, the findings confirm the further use of the FAD in the Dutch national context.

Effects of anomalous alpha particle diffusion on fusion power coupling into tokamak plasma

The alpha particle power coupling efficiency to the bulk plasma, ηalpha identical to Pα(coupled)/Pα(birth), is reduced when the energetic alpha particles are subject to anomalous radial diffusion, Dαan, caused by alpha particle instabilities. If ηα is appreciably smaller than 1, this has a strong effect on the ignition margin MI [≡ Palpha (coupled)/Ploss] of a tokamak plasma. First, a simple analytical form of ηα is found to be ηα = 1 - (τSD/τL), where τL ≃ α2/4Dα is the spatial loss time and τSD is the slowing down time. The power coupling efficiency ηα decreases with increasing Te and increases with ne. Second, a reduced time dependent alpha particle kinetic equation containing the term ∇.Dα ∇nα, where Dα can be a non-linear function of δnα/δτ, is derived and solved using a multiple energy group method. An Alfven wave turbulence theory by Gang (Phys. Fluids B 4 (1992) 3152) is used to parametrize Dα from first principles. When Dαan ≈ 3 m2/s, ηα is reduced to 0.95. The consequence for the accessible operating regimes of an ITER-like fusion device are also discussed

Agoraphobic, animal, death-injury-illness and social stimuli clusters as major elements in a four-dimensional taxonomy of self-rated fears: First-order level confirmatory evidence from an australian sample of anxiety disorder patients

In a recent review article, Arrindell, Pickersgill, Merckelbach, Ardon, and Cornet (1991) ( Advances in Behaviour Research and Therapy, 13, 73–130) proposed an a priori four-dimensional categorization system for the description of self-rated fears on the basis of suggestions from previous reviews and research. The categories were described as: (I) Interpersonal events or situations, (II) Death, injuries, illness, blood and surgical procedures, (III) Animals, and (IV) Agoraphobia. While it has proven to be feasible to categorize fear factors/components derived in different empirical studies reliably into each of these categories, no confirmatory evidence is as yet available to support the factorial validity of the relevant dimensional system. Using the multiple-group method, clear evidence was found at the primary level for such in a sample of 398 anxiety disorder patients. In addition, the corresponding component scales were demonstrated to be highly consistent internally and to be moderately to highly intercorrelated, with none of the intercorrelations exceeding or even approaching the internal consistencies in magnitude — thus clearly indicating that a reliable distinction can be made between the four fear dimensions. The findings are discussed in relation to other classes of fear reactions described in the clinical-theoretical literature and to Endler's interactional model of personality. Following the line of research from the area of personality testing, it is, among other things, suggested that psychobiological, developmental, and behavioral-social studies should, in the future, be organized around the now well-established dimensions of fear described above.

Rotation to Perfect Congruence and the Cross Validation of Component Weights Across Populations.

This paper deals with strategies of congruence studies, aimed at evaluating recoverableness of a given set of components from a first population in a second population where the same variables have been used. Five decisions inherent to congruence studies are analysed in detail. Confirmatory evidence with respect to recoverableness can be obtained from an independent component analysis for the second population, parallel to that of the first population. Disconfirmatory evidence requires oblique rotation to perfect congruence, which can always be attained. Rotation to perfect congruence is advocated as a new strategy, in which amounts of variance explained are of major concern. The perfect congruence strategy can be applied to variable-component correlations and to weights. The latter approach is to be preferred for two reasons. First, rotating weights to perfect congruence can be easily understood as a cross-validation method, closely related to the well-known multiple group method. Second, this approach appears to give more satisfactory results in practical applications than are obtained from rotating variable-component correlations to perfect congruence.

Factors In The Natural Language Of Personality: Re-Analysis, Comparison, And Interpretation Of Six Major Studies.

Psychometric studies of the organization of the "natural language of personality" have typically employed rating scales as measurement medium and factor analysis as statistical technique. The results of such investigations over the past 30 years have varied greatly, both with respect to number of factors and with respect to the constructs generated. Re-analysis of the correlations of six studies, including the classical work of Cattell, indicated that the domain appears to be well described by five factors, with some suggestion of a sixth. The five factors were related across studies, using the Kaiser-Hunka-Bianchini method. Generally, the factors were highly related, with most indices of relatedness exceeding .90. The five-factor model was tested by the multiple-group method, used to factor a large-scale study of teachers' ratings of children. With slight modification of the originally hypothesized structure, the five-factor model accounted for the observed relationships quite well. The five constructs suggested by the factors appear to be domains of research effort and theoretical concern which have long been of interest to psychologists.

A note on Multiple Group Method of Factor Analysis

This article extends and generalizes Guttman’s works on multiple group method of factor analysis when data matrix is Gramian**, where data matrix can be considered as covariance matrix or correlation matrix

The organization of spatial abilities in older men and women.

The objective of this study was to test the cognitive identity of older male and female populations with reference to raw score, component structure, and component score measures of spatial and verbal performance. One hundred women (average age, 70.2) and 96 men (average age, 69.0) were administered three verbal and six nonverbal congnitive subtests. The equivalence of four-factor principal component analyses of the male and female correlation matrices, corrected for restriction of range, were tested with the multiple group method of factor analysis. High coefficients of congruence for the three spatial and single verbal factors argue strongly for similar congnitive structures. Multivariate analysis of the factor scores, however, showed a significant mean difference between the older men and women. But when Jöreskog's procedures are applied to test the equivalence of covariance structures, the best fit was obtained for a model involving equivalence of factor means, factor structure, factor coefficients and factor correlations.