Spelling suggestions: "subject:"[een] EXPLORATORY FACTOR ANALYSIS"" "subject:"[enn] EXPLORATORY FACTOR ANALYSIS""
51 |
A cross-cultural examination of measurement invariance of smallholders in Kenya, Uganda, Mali and LesothoFornito, Matthew C. 27 May 2014 (has links) (PDF)
Cross-cultural research requires tests of measurement invariance to determine if different populations have equivalent latent constructs. A psychometric assessment of the Agricultural Production Perspectives Scale (APPS) was necessary to determine the validity of the scale constructed and whether data from multiple countries could be compared. Using 918 farmers sampled from Kenya, Uganda, Mali, and Lesotho, I conducted exploratory factor analysis and scale reliability tests to determine whether the item loadings and factors were equivalent across populations. No factor structure could be obtained across country or agroecological populations. The data were reanalyzed within each agroecology to determine localized factor structures. Results indicate that a market driven factor and agrarian driven factor tend to emerge across multiple agroecologies suggesting some emergence of latent variables. Recommendations for scale revisions are included to increase reliability and measurement invariance. / Master of Science / CCRA-8 (Technology Networks for Sustainable Innovation)
|
52 |
Social Justice Advocacy Trends Related to Gay/Straight Alliance Advisors' Experiences in SchoolsGraybill, Emily 07 May 2011 (has links)
Social justice within education increasingly has been emphasized over the past decade (Kraft, 2007; Oakes et al., 2000; Riester et al., 2002). Little is known about the demographic trends and the advocacy experiences of school-based social justice advocates such as Gay/Straight Alliance (GSA) advisors despite the established importance of teachers engaging in social justice advocacy within schools. Data were collected from a national sample (N = 262) of GSA advisors to further the understanding of the demographic characteristics and the experiences of these social justice advocates and to investigate the relationships between these variables. An ethnographic survey (Schensul, Schensul, & LeCompte, 1999) was utilized for data collection in which the language and experiences reported by GSA advisors (Graybill et al., 2009; Watson et al., 2010) were incorporated. Using an ecological model established in a previous study with GSA advisors (Watson et al., 2010), the individual-, school-, and sociocultural-level characteristics that affect advisors were examined. The results suggested that this sample of GSA advisors was a demographically homogenous group with 67.3% female, 85.7% White, 72.2% who voted Democrat, and 77.1% who were educated at the Master‟s level or higher. Exploratory factor analysis identified two dimensions (i.e., Barriers, Facilitators) by which the advisors appeared to define their experiences when advocating for LGBT youth. Hierarchical regression analyses suggested that at the individual level, experiencing negative personal and professional consequences to advocating and thelevel of self-perceived preparedness to advocate based on prior training contributed to the variability in the advisors‟ experiences with social justice advocacy. At the sociocultural level, advisors in rural schools reported more barriers and fewer facilitators to advocating. Overall, all seven predictors entered, including those at the individual (i.e., experiencing negative personal or professional consequences to advocating, level of self-perceived preparedness to advocate), school (i.e., school resources, school size), and sociocultural levels (i.e., region of the country, community type), accounted for 33.0% (p < .05) of the variance in the Barriers and 10.6% (p < .05) of the variance in the Facilitators to advocating for LGBT youth in schools.
|
53 |
Drug Courts Work, but How? Preliminary Development of a Measure to Assess Drug Court Structure and ProcessesBarrett, Blake 01 January 2011 (has links)
The high prevalence of substance use disorders is well-documented among criminal offenders. Drug courts are specialty judicial programs designed to: 1) improve public safety outcomes; 2) reduce criminal recidivism and substance abuse among offenders with substance use disorders; and 3) better utilize scarce criminal justice and treatment resources. Drug courts operate through partnerships between the criminal justice, behavioral health and public health systems. Offenders participate in an intensive regimen of substance abuse treatment and case management while under close judicial supervision. Drug courts' effectiveness in reducing criminal recidivism and drug use has been documented through numerous primary studies as well as meta-analytic reviews. The task remains now to determine the causal mechanisms of drug courts.
The current study conducted preliminary activities to develop a measure to assess drug court structures and practices based upon the Ten Key Components of drug courts (NADCP, 1997). The creation and use of such a measure is necessary to the understanding of how drug courts work, why and how best to invest scarce judicial and treatment resources to optimize drug court participant and program outcomes. An iterative process was conducted such that results from previous activities informed subsequent steps in the measurement development process. Participants consisted of a convenience sample of drug court personnel at three local drug courts as well as academic experts in drug courts and measurement.
Preliminary measurement development activities included: 1) a comprehensive review of the literature; 2) semi-structured interviews with key stakeholders to inform item development; 3) construction of a draft survey protocol; 4) expert reviews of the draft survey protocol and initial item pool to assess item construct and content validity, response format and clarity; 5) pile sort activity, wherein participants sorted items into piles, one for each measure sub-construct and one `other' pile; 6) exploratory factor analyses based on a joint-proportion matrix derived from pile sort activity data on which items best represent measure sub-constructs; 7) cognitive interviews completed by key stakeholders to review items retained from exploratory factor analyses; and 8) final revisions to the item pool based upon results from cognitive interviews.
The item pool developed through the current research will be used as the basis for a future large-scale pilot test to determine the true factor structure underlying the preliminary measure developed. Results of this future research are expected to identify similarities and differences in the underlying factor structure compared to the Ten Key Components.
|
54 |
Towards establishing the equivalence of the IsiXhosa and English versions of the Woodcok Munoz language survey : an item and construct bias analysis of the verbal analogies scaleRoomaney, Rizwana January 2010 (has links)
This study formed part of a larger project that is concerned with the adaptation of a test of cognitive academic language proficiency, the Woodcock Muñoz Language Survey (WMLS). The WMLS has been adapted from English into isiXhosa and the present study is located within the broader study that is concerned with establishing overall equivalence between the two language versions of the WMLS. It was primarily concerned with the Verbal Analogies (VA) scale. Previous research on this scale has demonstrated promising results, but continues to find evidence of some inequivalence. This study aimed to cross-validate previous research on the two language versions of the WMLS and improve on methodological issues by employing matched groups. It drew upon an existing dataset from the larger research project. The study employed a monolingual matched two-group design consisting of 150 mainly English speaking and 149 mainly isiXhosa learners in grades 6 and 7. This study had two sub aims. The first was to investigate item bias by identifying DIF items in the VA scale across the isiXhosa and English by conducting a logistic regression and Mantel-Haenszel procedure. Five items were identified by both techniques as DIF. The second sub aim was to evaluate construct equivalence between the isiXhosa and English versions of the WMLS on the VA scale by conducting a factor analysis on the tests after removal of DIF items. Two factors were requested during the factor analysis. The first factor displayed significant loadings across both language versions and was identified as a stable factor. This was confirmed by the Tucker’s Phi and scatter plot. The second factor was stable for the English version but not for the isiXhosa version. The Tucker’s phi and scatter plot indicated that this factor is not structurally equivalent across the two language versions / Magister Artium (Psychology) - MA(Psych)
|
55 |
Εφαρμογή της παραγοντικής ανάλυσης για την ανίχνευση και περιγραφή της κατανάλωσης αλκοολούχων ποτών του ελληνικού πληθυσμούΡεκούτη, Αγγελική 21 October 2011 (has links)
Σκοπός της εργασίας αυτής είναι να εφαρμόσουμε την Παραγοντική Ανάλυση στο δείγμα μας, έτσι ώστε να ανιχνεύσουμε και να περιγράψουμε τις καταναλωτικές συνήθειες του Ελληνικού πληθυσμού ως προς την κατανάλωση 9 κατηγοριών αλκοολούχων ποτών. Η εφαρμογή της μεθόδου γίνεται με την χρήση του στατιστικού προγράμματος SPSS.
Στο πρώτο κεφάλαιο παρουσιάζεται η οικογένεια μεθόδων επίλυσης του προβλήματος και στο δεύτερο η μέθοδος που επιλέχτηκε για την επίλυση, η Παραγοντική Ανάλυση. Προσδιορίζουμε το αντικείμενο, τα στάδια σχεδιασμού και τις προϋποθέσεις της μεθόδου, καθώς και τα κριτήρια αξιολόγησης των αποτελεσμάτων.
Τα κεφάλαια που ακολουθούν αποτελούν το πρακτικό μέρος της εργασίας. Στο 3ο κεφάλαιο αναφέρουμε την πηγή των δεδομένων μας και την διεξαγωγή του τρόπου συλλογής τους. Ακολουθεί ο εντοπισμός των «χαμένων» απαντήσεων και εφαρμόζεται η Ανάλυση των Χαμένων Τιμών (Missing Values Analysis) για τον προσδιορισμό του είδους αυτών και την αποκατάσταση τους στο δείγμα. Στην συνέχεια παρουσιάζουμε το δείγμα μας με τη βοήθεια της περιγραφικής στατιστικής και τέλος δημιουργούμε και περιγράφουμε το τελικό μητρώο δεδομένων το οποίο θα αναλύσουμε παραγοντικά.
Στο 4ο και τελευταίο κεφάλαιο διερευνάται η καταλληλότητα του δείγματος για την εφαρμογή της Παραγοντικής Ανάλυσης με τον έλεγχο της ικανοποίησης των προϋποθέσεων της μεθόδου. Ακολουθεί η παράλληλη μελέτη του δείγματος συμπεριλαμβάνοντας και μη στην επίλυση τις ακραίες τιμές (outliers) που εντοπίστηκαν. Καταλήγοντας στο συμπέρασμα ότι οι ακραίες τιμές δεν επηρεάζουν τα αποτελέσματα της μεθόδου, εφαρμόζουμε την Παραγοντική Ανάλυση με τη χρήση της μεθόδου των κυρίων συνιστωσών και αναφέρουμε αναλυτικά όλα τα βήματα μέχρι να καταλήξουμε στα τελικά συμπεράσματα μας. / The purpose of this paper is to apply the Factor Analysis to our sample in order to detect and describe patterns concerning the consumption of 9 categories of alcoholic beverages by the Greek population. For the application of the method, we use the statistical program SPSS.
The first chapter presents the available methods for solving this problem and the second one presents the chosen method, namely Factor Analysis. We specify the objective of the analysis, the design and the critical assumptions of the method, as well as the criteria for the evaluation of the results.
In the third chapter we present the source of our data and how the sampling was performed. Furthermore, we identify the missing values and we apply the Missing Values Analysis to determine their type. We also present our sample using descriptive statistics and then create and describe the final matrix which we analyze with Factor Analysis.
In the fourth and last chapter we investigate the suitability of our samples for applying Factor Analysis. In the sequence, we perform the parallel study of our sample both including and not including the extreme values that we identified (which we call “outliers”). We conclude that the outliers do not affect the results of our method and then apply Factor Analysis using the extraction method of Principal Components. We also mention in detail all steps until reaching our final conclusions.
|
56 |
[en] PSYCHOMETRIC PROPERTIES AND THE LATENT STRUCTURE OF THE PORTUGUESE VERSION OF THE PENN STATE WORRY QUESTIONNAIRE / [pt] PROPRIEDADES PSICOMÉTRICAS E ESTRUTURA LATENTE DA VERSÃO EM PORTUGUÊS DO QUESTIONÁRIO DE PREOCUPAÇÃO DO ESTADO DA PENSILVÂNIACRISTIAN DOS SANTOS CASTILLO 20 August 2007 (has links)
[pt] O objetivo do presente trabalho consistia em traduzir o
Questionário de
Preocupação do Estado da Pensilvânia (PSWQ) para o
português e avaliar as
propriedades psicométricas e a estrutura latente desta
versão traduzida em uma amostra
representativa de universitários no Brasil para determinar
sua confiabilidade e validade
psicométricas. Um primeiro estudo utilizou 871 graduandos
de diferentes Universidades
do Rio de Janeiro apresentando uma faixa de idade de 17 a
68 anos. Uma análise
fatorial exploratória (AFE) foi realizada para examinar a
estrutura latente dos 16 itens
que compõem esta escala. Um segundo estudo utilizou 978
graduandos com as mesmas
características do estudo 1. Uma análise fatorial
confirmatória (AFC) foi usada para
inspecionar eventuais artefatos fatoriais da escala,
previamente descritos na literatura.
Os resultados indicaram que o PSWQ apresentou uma adequada
consistência interna.
No primeiro estudo, uma AFE indicou uma solução de dois
fatores. Um fator foi
relacionado com a preocupação presente e incorporou todos
os 11 itens escritos na
forma afirmativa. O outro foi associado com a preocupação
ausente e incorporou todos
os 5 itens escritos na forma negativa. No segundo estudo,
uma AFC ajustou uma
solução de três fatores. Um fator incorporou todos os
itens do PSWQ, onde os outros
dois fatores foram relacionados com os itens na afirmativa
e negativa. Coeficientes de
correlação destes dois fatores de itens na afirmativa e
negativa com o total do PSWQ e a
subescala traço do Inventário de Ansiedade Traço-Estado
sugerem que o fator composto
pelos 5 itens na negativa não contribui significativamente
para a estrutura latente do
PSWQ. A avaliação psicométrica da versão em português do
PSWQ indicou que esta
escala pode medir confiavelmente a presença do construto
de preocupação em uma
amostra não clínica. Análises de sua estrutura fatorial
sugeriram que o fator da
preocupação ausente deve ser um artefato metodológico
atribuído ao efeito da forma
escrita dos itens na negativa. / [en] Translate the Penn State Worry Questionnaire (PSWQ) to
Portuguese and
evaluate the psychometric properties and the latent
structure of the translated version in
a large Brazilian college student sample to determine its
psychometric reliability and
validity. A first study employed 871 undergraduate
students from different Universities
of Rio de Janeiro ranging from 17 to 68 years of age. An
exploratory factor analysis
(EFA) was employed to analyze its latent structure of 16
items that composes the scale.
A second study employed 978 college students with the same
characteristics from Study
1. A confirmatory factor analysis (CFA) was used to
investigate eventual factorial
artifacts of the scale previously described in the
literature. Results indicated that PSWQ
had an adequate internal consistency. In the first study,
the EFA yields a two-factor
solution. One factor was related to worry presence and
incorporated all the 11
positive-worded items stated in a non-reversed form. The
other was associated to
worry absence and incorporated all the five negative-
worded items stated in a
reversed form. In a second study, the CFA leads to a three-
factor solution. One factor
incorporated all the PSWQ items whereas the two other
factors were linked to the
reversed and non-reversed items. Correlations coefficients
of these two reversed and
non-reversed factors with the total scores of the PSWQ and
the trait subscale of the
State-Trait Anxiety Inventory suggest that the factor
composed by the five items do not
contribute in a meaningful way to the PSWQ latent
structure. Psychometric evaluation
of the Portuguese version of the PSWQ indicated that the
scale can reliably measure the
presence of the worry construct in a non-clinical sample.
Analysis of its factorial
structure suggested that the worry absence factor might be
a methodological artifact due
to a wording effect of the reversed items.
|
57 |
O movimento pecuário nordestinoSilva, Emerson de Sousa 12 August 2011 (has links)
Drawing on data released by the Census of Agriculture 2006, this paper aims to identify, among all those micro-regions of northeastern Brazil where the volume of livestock movement (represented by the quantity of purchase, sale and slaughter of goats, sheep, cattle, pigs and in poultry farms) would allow a high frequency of transactions with animals - between the segments of production and processing - which would result in market governance structures. The research is grounded in two theoretical pillars: the Transaction Cost Economics (TCE), of Oliver Williamson, and the Commodity System Approach (CSA) compiled by John Davis and Ray Goldberg. The first theory is that, due to the bounded rationality of agents and the tendency to assume such an opportunistic behavior, it is impossible to fully and agents rationally anticipate outcomes of their decisions and that they protect themselves from possible flaws in the implementation of the economic transactions from the establishment of contracts between the parties involved. So that, CSA argues that the process of agricultural production can t be addressed so tight, that is, without understanding its systemic character, ranging from the decision of what and how to produce the end consumer. The tool used was exploratory factor analysis, multivariate statistical technique that allows the identification of latent factors that explain the interrelationships among the variables under study. The results showed that the cattle drive in the Northeast is a focused and dedicated event in the sense that largely takes place in a few territories and rarely stands out in a location more than one culture. Therefore, the coordination of the interface market for production / processing of agricultural products is suitable for a small number of locations in the brazilian Northeast. / Valendo-se dos dados disponibilizados pelo Censo Agropecuário 2006, a presente dissertação objetiva identificar dentre as cento e oitenta e oito microrregiões do Nordeste brasileiro aquelas em que o volume de movimentação pecuária (representada pelo quantitativo de compra, venda e abate de caprinos, ovinos, bovinos, suínos e galináceos nas propriedades rurais) permitiria uma alta freqüência de comercialização de animais entre os segmentos de produção e transformação o que resultaria em estruturas de governança de mercado. O trabalho assentou-se sobre dois pilares teóricos: a economia dos custos de transação (ECT), de Oliver Williamson, e a Commodity System Approach (CSA), elaborada por John Davis e Ray Goldberg. A primeira teoria defende que, em função da racionalidade limitada dos agentes e da tendência desses em assumirem um comportamento oportunista, é impossível aos agentes anteverem plena e racionalmente os resultados de suas decisões e que esses se protegem de possíveis falhas na execução das transações econômicas a partir da constituição de contratos entre as partes envolvidas. Já a CSA advoga que o processo produtivo da agropecuária não pode ser abordado de forma estanque, ou seja, sem a compreensão do seu caráter sistêmico, que vai desde a decisão do que e como produzir até o consumidor final. O ferramental utilizado foi a Análise Fatorial Exploratória, técnica estatística multivariada que permite a identificação de fatores latentes que explicariam o inter-relacionamento entre as variáveis sob estudo. Os resultados mostraram que a movimentação pecuária nordestina é um evento concentrado e especializado no sentido de que grande parte dá-se em poucas microrregiões e raramente uma localidade se destaca em mais de uma cultura. Logo, a coordenação de mercado para a interface produção/processamento de produtos agrícolas é indicada para um pequeno número de microrregiões nordestinas.
|
58 |
Vetor de sucesso: abordagem de um pmo no sistema eletrobrasArduino, Eduardo Gurgel do Amaral 24 August 2015 (has links)
Submitted by Marcia Silva (marcia@latec.uff.br) on 2016-07-15T20:54:28Z
No. of bitstreams: 1
DISSERT EDUARDO GURGEL DO AMARAL ARDUINO.pdf: 2065093 bytes, checksum: cff22b2b72c45eeee85f4facfd01289c (MD5) / Made available in DSpace on 2016-07-15T20:54:28Z (GMT). No. of bitstreams: 1
DISSERT EDUARDO GURGEL DO AMARAL ARDUINO.pdf: 2065093 bytes, checksum: cff22b2b72c45eeee85f4facfd01289c (MD5)
Previous issue date: 2015-08-24 / O objeto do estudo foi elaborar uma modelo estrutural completo dos fatores que influenciam o sucesso da atuação do PMO e que benefícios essa atuação positiva traria para a gestão de projetos no Sistema Eletrobras e a partir disso, realizar um aperfeiçoamento do modelo estrutural por meio de métodos estatísticos. Para isso foi realizado uma pesquisa de campo (survey) no intuito de levantar dados junto aos profissionais envolvidos em Gestão de Projetos dentro do Sistema Eletrobras, a partir do modelo proposto e foram evidenciados os fatores de sucesso na atuação do PMO (Project Management Office) que possibilitam o escritório de gerenciamento de projetos tornar-se um vetor de gestão por excelência na empresa. Para alcançar o objetivo idealizado, realizou-se (a) Levantamento bibliográfico para conceituar gerenciamento de projetos e PMOs, (b) identificou-se os fatores que influenciam o sucesso de atuação do PMO, (c) identificou-se as abordagens teóricas dos fatores diretos que mais contribuem para que o PMO da Eletrobras possa atuar como um vetor de gestão por excelência, otimizando o aumento da eficiência da sua atuação e o sucesso na gestão de projetos. Averiguou-se quais abordagens teóricas, a partir do sucesso de atuação do PMO, traziam benefícios para a gestão de Projetos no Sistema Eletrobras. Assim, para realizar os trabalhos estatísticos para a avaliação de adequação do modelo, foi utilizado o software SPSS Statistics, para a execução da AFE (Análise Fatorial Exploratória), em busca de testar o modelo baseado na teoria previamente apresentada. Foram obtidas 116 respostas válidas preenchidas por colaboradores com envolvimento em gerenciamento de projetos no sistema Eletrobras. No início o modelo teórico era composto por vinte abordagens teóricas e três fatores independentes. Após as etapas do SEM, obteve-se dezessete abordagens e dois fatores independentes, diferentes do modelo proposto. Com isso, a hipóteses H1 e H2 não foram rejeitadas, pois apresentaram fator significante com (P < 0,05). A hipótese H3 teve que ser excluída, pois na AFE suas abordagens teóricas compuseram um único conjunto com a hipótese H2, visto que a Matriz da Variância Total Explicada demonstrou ser o modelo mais ajustado com somente dois fatores. Todas as análises foram validadas pelo alpha de cronbach. / The object of study was preparing a full structural model of the factors that influence the success of the PMO acting and that this positive performance would bring benefits for project management in the Eletrobras System and from this, carry out an improvement of the structural model through methods Statistical. For it was conducted a field survey (survey) in order to collect data with professionals involved in Project Management within the Eletrobras System, from the proposed model and were shown the success factors in the performance of the PMO (Project Management Office) which enable the project management office become a vector of management excellence by the company. To achieve the idealized goal, there was (a) Bibliographic survey to conceptualize project management and PMOs, (b) identified the factors that influence the PMO acting success, (c) identify the theoretical approaches of the factors direct that contribute most to the PMO Eletrobras can act as a vector management par excellence, optimizing the increased efficiency of its operations and success in project management. It was found that theoretical approaches, from the PMO acting success, bringing benefits to the Project management in the Eletrobras System. Thus, to perform statistical work for the evaluation of the adequacy of the model, SPSS Statistics software was used, for the implementation of EFA (Exploratory Factor Analysis), seeking to test the model based on the theory presented previously. 116 valid responses were obtained filled by employees with involvement in project management in the Eletrobras System. Earlier the theoretical model was composed of twenty theoretical approaches and three independent factors. After the stages of SEM, seventeen approaches was obtained and two independent factors, other than this model. With this, the H1 and H2 hypotheses were not rejected because they presented with significant factor (P <0.05). The hypothesis H3 had to be excluded, as their theoretical approaches the AFE comprised a single set with the hypothesis H2, whereas Matrix Total Variance Explained proved to be the most adjusted model with only two factors. All analyzes were validated by Cronbach's alpha.
|
59 |
Towards establishing the equivalence of the English version of the verbal analogies scale of the Woodcock Munuz Language Survey across English and Xhosa first language speakersIsmail, Ghouwa January 2010 (has links)
Magister Artium - MA / In the majority of the schools in South Africa (SA), learners commence education in English. This English milieu poses a considerable challenge for English second-language speakers. In an attempt to bridge the gap between English as the main medium of instruction and the nine indigenous languages of the country and assist with the implementation of mother-tongue based bilingual education, this study focuses on the cross-validation of a monolingual English test used in the assessment of multilingual or bilingual learners in the South African context. This test, namely the Woodcock Muñoz Language Survey (WMLS), is extensively used in the United States in Additive Bilingual Education in the country. The present study is a substudy of a broader study, in which the original WMLS (American-English version) was adapted into SA English and Xhosa. For this specific sub-study, the researcher was interested in investigating the scalar equivalence of the adapted English version of the Verbal Analogies (VA) subscale of the WMLS across English first-language speakers and Xhosa first-language speakers. This was achieved by utilising differential item functioning (DIF) and construct bias statistical techniques. The Mantel-Haenszel DIF detection method was employed to detect DIF, while construct equivalence was examined by means of exploratory factor analysis (EFA) utilising an a priori two-factor structure. The Tucker's phi coefficient was used to assess the congruence of the construct across the two language groups / South Africa
|
60 |
Exploring the scalar equivalence of the picture vocabulary scale of the Woodcock Munoz language survey across rural and urban isiXhosa-speaking learnersBrown, Qunita January 2012 (has links)
Magister Artium (Psychology) - MA(Psych) / The fall of apartheid and the rise of democracy have brought assessment issues in multicultural societies to the forefront in South Africa. The rise of multicultural assessment demands the development of tests that are culturally relevant to enhance fair testing practices, and issues of bias and equivalence of tests become increasingly important. This study forms part of a larger project titled the Additive Bilingual Education Project (ABLE). The Woodcock Munoz Language Survey (WMLS) was specifically selected to evaluate the
language aims in the project, and was adapted from English to isiXhosa. Previous research has indicated that one of the scales in the adapted isiXhosa version of the WMLS, namely the Picture Vocabulary Scale (PV), displays some item bias, or differential item functioning (DIF), across rural and urban isiXhosa learners. Research has also indicated that differences in dialects can have an impact on test takers’ scores. It is therefore essential to explore the
structural equivalence of the adapted isiXhosa version of the WMLS on the PV scale across rural and urban isiXhosa learners, and to ascertain whether DIF is affecting the extent to which the same construct is measured across both groups. The results contribute to establishing the scalar equivalence of the adapted isiXhosa version of the WMLS across rural and urban isiXhosa-speaking learners. Secondary Data Analysis (SDA) was employed because this allowed the researcher to re-analyse the existing data in order to further evaluate construct equivalence. The sample of the larger study consisted of 260 learners, both male and female, selected from a population of Grade 6 and 7 learners attending schools in the Eastern Cape. The data was analysed by using the statistical programme Comprehensive Exploratory Factor Analysis (CEFA) and the Statistical Package for Social Sciences (SPSS). Exploratory factor analysis and the Tucker’s phi coefficient were used. The results indicated distinct factor loadings for both groups, but slight differences were observed which raised concerns about construct equivalence. Scatter plots were employed to investigate further, which also gave cause for concern. It was therefore concluded that construct equivalence was only partially attained. In addition, the Cronbach’s Alpha per factor was calculated, showing that internal consistency was displayed only for Factor 1 and not for Factor 2 for the rural group, or both factors for the urban group. Scalar equivalence across the two groups must therefore be explored further.
|
Page generated in 0.1101 seconds