The Dependability of Behavioral Measurements: Theory of Generalizability for Scores and Profiles.

Rubin, Donald B.; Cronbach, Lee J.; Gleser, Goldine C.; Nanda, Harinder; Rajaratnam, Nageswari

doi:10.2307/2286194

Cited by 71 publications

(108 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Still, to determine how much the proposed classification scheme discriminates between subjects and contexts, the results need to be examined through a generalizability analysis (Rubin et al, 1974). Also, as a limitation, it must be noted that a corpus based on a different genre might result in different findings.…”

Section: Discussionmentioning

confidence: 99%

Understanding conversational interaction in multiparty conversations: the EVA Corpus

Mlakar

Verdonik

Majhenič

et al. 2022

Lang Resources & Evaluation

View full text Add to dashboard Cite

This paper focuses on gaining new knowledge through observation, qualitative analytics, and cross-modal fusion of rich multi-layered conversational features expressed during multiparty discourse. The outlined research stems from the theory that speech and co-speech gestures originate from the same representation; however, the representation is not solely limited to the speech production process. Thus, the nature of how information is conveyed by synchronously fusing speech and gestures must be investigated in detail. Therefore, this paper introduces an integrated annotation scheme and methodology which opens the opportunity to study verbal (i.e., speech) and non-verbal (i.e., visual cues with a communicative intent) components independently, however, still interconnected over a common timeline. To analyse this interaction between linguistic, paralinguistic, and non-verbal components in multiparty discourse and to help improve natural language generation in embodied conversational agents, a high-quality multimodal corpus, consisting of several annotation layers spanning syntax, POS, dialogue acts, discourse markers, sentiment, emotions, non-verbal behaviour, and gesture units was built and is represented in detail. It is the first of its kind for the Slovenian language. Moreover, detailed case studies show the tendency of metadiscourse to coincide with non-verbal behaviour of non-propositional origin. The case analysis further highlights how the newly created conversational model and the corresponding information-rich consistent corpus can be exploited to deepen the understanding of multiparty discourse.

show abstract

Section: Discussionmentioning

confidence: 99%

Understanding conversational interaction in multiparty conversations: the EVA Corpus

Mlakar

Verdonik

Majhenič

et al. 2022

Lang Resources & Evaluation

View full text Add to dashboard Cite

show abstract

“…For validation purposes, the questionnaire was administered to a sample of N = 500 (320 females and 180 males), undergraduate and graduate university students with a mean age of 25 (range = 18−37). The sample size was based on Cohen’s rule of thumb of larger sample size (Cohen, 1992, 1990), following the notion that larger samples more precisely characterize the characteristics of the populations from which they are selected (Marcoulides, 1993; Rubin et al , 1974; VanVoorhis and Morgan, 2007). Similarly, a student’s sample was selected because it has the most diverse population of individuals from different backgrounds (Wu et al , 2012).…”

Section: Methodsmentioning

confidence: 99%

Psychometric development and validation of attitude rating scale towards women empowerment: across male and female university population in Pakistan

Shuja

Aqeel

Khan

2020

IJHRH

View full text Add to dashboard Cite

Purpose Attaining equality between women and men and eliminating all forms of discrimination are fundamental human rights and United Nations values. Nevertheless, women globally suffer violations of their human rights throughout their lives. This necessitates investigation of the attitude that people hold towards women empowerment, which is defined as their ability to practice their rights, freedom and attain resources within a framework of gender inequality. The purpose of this study is to develop an instrument to measure attitudes regarding women’s empowerment, which can develop better understanding and future interventions to counter these negative attitudes for better social and health care, including mental and physical health. Design/methodology/approach The factorial structure, reliability, content validity and impact of gender on factor structure of scale were examined among university students (N = 500) in study with male (n = 180) and female (n = 320) population. Findings Exploratory factor analysis using direct oblimin method based on principal component analysis indicated a three-factor, 16-item scale including subscales of personal freedom; equal rights and women empowerment-related fears. Instrument exhibited decent reliability (0.80) and content validity in both male and female university students with a t = −7.64, p = 0.00, suggesting a highly significant difference between the two genders on the developed scale. Research limitations/implications The major limitation was that the sample was obtained from student population; therefore, it will not be entirely correct to generalize it to the whole population of Pakistan. Similarly, there are issues regarding the availability of students because of a busy schedule or not having interest to take part in the study that led to variance in the sample. Lastly, the current scale is developed based on exploratory factor analysis (EFA) and it should be further enhanced using item response theory in future. Future studies need to include samples from different populations in Pakistan to bring out a more generalized view and try to minimize the variances in sample as much as possible for better results. Practical implications The scale is constructed using the basic features of women empowerment at its core and is applicable in various settings to measure the attitude towards women empowerment. It will be a helpful tool to be used in various health, employment and educational settings. Moreover, this instrument can be applied for research purpose of measuring attitude as a predictor in combination with other variables such as domestic violence and harassment. Social implications Empowering of women is one of the main agendas of 2019 of United Nations for Asian countries where women are not given equal rights, because of which suffer socially and economically from various problems along with issues regarding physical and mental health. By identifying the attitudes of general population, their causes for their attitudes can help in betterment of the women empowerment process. Originality/value This paper in discussion is an original work and has been performed with the purpose of assessing attitudes of males and females regarding women empowerment as the previous measures are either not psychometric valid or are in interview or survey form. The current developed scale is an attempt to develop an instrument that can be globally used.

show abstract

“…Al finalizar este análisis, se procedió a realizar un Análisis de Generalizabilidad mediante el programa informático SAGT (Hernández-Mendo et al, 2016; Hernández-Mendo et al, 2012). La Teoría de Generalizabilidad (Cardinet et al, 1976(Cardinet et al, , 1981Cronbach et al, 1972) unifica las definiciones de fiabilidad, validez y precisión (Blanco-Villaseñor et al, 2014) y comprende cuatro etapas: la definición de las facetas de estudio, el análisis de varianza de las puntuaciones obtenidas sobre las facetas de estudio, el cálculo de los componentes de error y la optimización de los coeficientes de Generalizabilidad (Blanco-Villaseñor et al, 2014). Con el objetivo de complementar el análisis de calidad del dato, se estimó el acuerdo intraobservador e interobservador, la homogeneidad de las categorías y el número mínimo de sesiones necesarias para generalizar con precisión.…”

Section: Nivel De Plasticidad O Grado De Aperturaunclassified

Sistema de observación para la evaluación técnica en la danza clásica: ejercicio del battement tendu

Izquierdo

Baro

Rabaneda

et al. 2023

Cuad. psicol. deporte

View full text Add to dashboard Cite

The battement tendu, in its different forms of execution and each of them with its own work objective, is essential from the first training courses in academic dance, since it provides the basis for the learning of dancers and dancers. The present study shows an observation tool designed ad hoc for this exercise, composed of a combination of field format and category systems, exhaustive and mutually exclusive (E/ME), with the aim of being able to validate, codify and evaluate said exercise. of classical dance at a ballet barre. The instrument is made up of 5 criteria and a total of 54 categories distributed as follows: 23 in lower body, 9 in upper body, 10 for head/gaze, 3 in spatial direction and 9 for musical counts. The sample selected in the study was made up of 10 dancers, eight women and two men, all with a professional level in classical dance. A Data Quality analysis and a Generalizability analysis were performed with the HOISAN and SAGT v1.0 programs, respectively. The reliability of the observers was carried out by calculating the Pearson, Spearman and Kendall's Tau b correlation coefficients, and through Cohen's Kappa concordance index and Krippendorf's canonical concordance. The results showed adequate correlation coefficients and concordance indexes, as well as excellent Generalizability results with a relative G and absolute G value of .99 in the interobserver agreement and 1.00 for the intraobserver agreement, revealing that the observation tool for the exercise of the battement tendu in classical dance presents optimal precision, reliability and validity. El battement tendu, en sus diferentes formas de ejecución y cada una de ellas con su propio objetivo de trabajo, se hace indispensable desde los primeros cursos de formación en la danza académica, ya que proporciona la base para el aprendizaje de los bailarines y las bailarinas. El presente estudio muestra una herramienta de observación diseñada ad hoc para este ejercicio, compuesta por una combinación de formato de campo y sistemas de categorías, exhaustivas y mutuamente excluyentes (E/ME),con el objetivo de poder validar, codificar y evaluar dicho ejercicio de danza clásica en una barra de ballet. El instrumento se compone de 5 criterios y un total de 54 categorías distribuidas de la siguiente forma: 23 en tren inferior, 9 en tren superior, 10 para cabeza/mirada, 3 en dirección espacial y 9 para las cuentas musicales. La muestra seleccionada en el estudio estaba formaba por 10 bailarines/as, ocho mujeres y dos hombres, todos con un nivel profesional en danza clásica. Se realizó un análisis de Calidad del Dato y un análisis de Generalizabilidad con los programas HOISAN y SAGT v1.0 respectivamente. La fiabilidad de los observadores se llevó a cabo mediante el cálculo de los coeficientes de correlación Pearson, Spearman y Tau b de Kendall; y mediante el índice de concordancia Kappa de Cohen y concordancia canónica de Krippendorf. Los resultados mostraron adecuados coeficientes de correlación e índices concordancia, así como excelentes resultados de la Generalizabilidad con un valor G relativo y G absoluto de .99 en el acuerdo interobservador y 1.00 para el acuerdo intraobservador, revelando que la herramienta de observación para el ejercicio del battement tendu en la danza clásica presenta una óptima precisión, fiabilidad y validez. O battement tendu, em suas diferentes formas de execução e cada uma de las com seu próprio objetivo de trabalho, é essencial desde os primeiros cursos de formação em dança acadêmica, pois fornece a base para o aprendizado de bailarinos e bailarinas. O presente estudo apresenta um instrumento de observação concebido ad hoc para este exercício, composto por uma combinação de formato de campo e sistemas de categorias, exaustivos e mutuamente exclusivos (E/ME), com o objectivo de poder validar, codificar e avaliar o referido exercício. de dança clássica em uma barra de balé. O instrumento é composto por 5 critérios e um total de 54 categorias distribuídas da seguinte forma: 23 na parte inferior do corpo, 9 na parte superior do corpo, 10 na cabeça/olhar, 3 na direção espacial e 9 na contagem musical. A amostra selecionada no estudo foi composta por 10 bailarinos, sendo oito mulheres e dois homens, todos com nível profissional em dança clássica. Uma análise de qualidade de dados e uma análise de generalização foram realizadas com os programas HOISAN e SAGT v1.0, respectivamente. A confiabilidade dos observadores foi realizada por meio do cálculo dos coeficientes de correlação Tau b de Pearson, Spearman e Kendall; e através do índice de concordância Kappa de Cohen e concordância canônica de Krippendorf. Os resultados mostraram coeficientes de correlação e índices de concordância adequados, bem como excelentes resultados de Generalizabilidade com um valor de G relativo e G absoluto de 0,99 na concordância interobservador e 1,00 na concordância intraobservador, revelando que a ferramenta de observação para o exercício do battement tendu na dança clássica apresenta ótima precisão, confiabilidade e validade.

show abstract

The Dependability of Behavioral Measurements: Theory of Generalizability for Scores and Profiles.

Cited by 71 publications

References 0 publications

Understanding conversational interaction in multiparty conversations: the EVA Corpus

Understanding conversational interaction in multiparty conversations: the EVA Corpus

Psychometric development and validation of attitude rating scale towards women empowerment: across male and female university population in Pakistan

Sistema de observación para la evaluación técnica en la danza clásica: ejercicio del battement tendu

Contact Info

Product

Resources

About