Content uploaded by Paula Elosua
Author content
All content in this area was uploaded by Paula Elosua on Apr 08, 2020
Content may be subject to copyright.
A preview of the PDF is not available
Psicometría aplicada. Guía para el análisis de datos y escalas con jamovi
Supplementary resource (1)
... However, the change is insignificant if a modification is made, and there would be a risk of losing some information. This result indicates that the items in the instrument, from the results obtained in the sample, have a high correlation and favorable internal consistency [90]. ...
This study aims to describe the analysis of the validity and reliability of an instrument that determines the self-perception of natural science teachers using the STEAM approach regarding the planning, development, and evaluation of their pedagogical activities. For its design, empirical studies were obtained from a bibliographic review, theoretical criteria on self-perception and STEAM approach, and population characteristics. For the instrument quality assessment, content validity parameters were analyzed by experts, and construct validity and reliability were assessed with the help of the SPSS statistical package. Ten educational doctors served as expert judges and 143 teachers (pre-service and in-service) participated in the pilot test. As the main finding, the instrument applied to a sample presents a high reliability coefficient (Cronbach’s alpha = 0.920) and validity (KMO = 0.903) in three factors after performing a factor analysis. Thus, it is concluded that the instrument has structure and coherence both in its internal consistency and meaning grid, which facilitates progress in understanding the self-perception of using the STEAM approach in didactic practices in natural sciences.
... The objective of this study was to test the usefulness of the QIHVC tool to explore the empirical relationship between perception and behavioral intention in the face of violent behavior, and other theoretically related variables (type of violence and number of bystanders present at the scene). The relationship between the scores obtained with a measuring tool and other external variables is one of the sources of information traditionally used in the process of validating measuring tools (Elosúa and Egaña, 2000). Its usefulness has been corroborated by different theoretical perspectives such as external focus of validity (Messick, 1989), the nomological validity focus (Campbell, 1960), and the nomothetic amplitude focus (Whitely, 1983). ...
Introduction
Violence against women (VAW) is a worldwide social and health problem of epidemic proportions. This violence is preventable, and bystander programs are one of the possible preventative strategies. The main purpose of this research was to develop a tool that, by applying a contrastive methodology for its application in different forms of violence (forms of gender-based violence, such as intimate partner VAW, sexual harassment at work, and street harassment, and common violence, such as a robbery), would allow measuring the probability of occurrence of bystander response in the face of these types of violence with good evidence of content validity.
Method
Firstly (Study 1), an initial version of a measure tool, the Questionnaire of Intention to Help in VAW Cases (QIHVC), was developed; secondly (Study 2), a Delphi (modified) study was carried out to obtain valid, content-based evidence; and finally (Study 3), a pilot study was carried out to evaluate the appropriate functioning of the QIHVC and, if required, to make any necessary adjustments.
Results and discussion
The main result is the development of a set of case scenarios and a questionnaire related to its content which constitutes the QIHVC and, in its initial approximation, seems to constitute an adequate and sensible tool to capture the differences between the characterizations of common violence and VAW and in the possible response of bystanders in the face of such violence.
... Con base en estos criterios, se tomó la decisión de eliminar el ítem eWti3 de la escala de confianza y de los ítems eWnv1 y eWnv2 de la escala de e-WoM. A pesar de que los ítems de valencia negativa del e-WoM de la escala de Goyette et al. (2010) sirven para controlar la deseabilidad social y la aquiescencia de las respuestas (Elosua & Egaña, 2020), el hecho de que esta incluya también ítems de valencia positiva hacen que su fiabilidad se deteriore (Suárez-Álvarez et al., 2018). Es así como, al eliminar estos ítems, se obtuvo un Alfa de Cronbach de 0,946 para la escala de e-WoM, mientras que para la escala de confianza se obtuvo un Alfa de Cronbach de 0,948 (tabla 4), lo que quiere decir que los índices de fiabilidad de las escalas son muy elevados (Hernández et al., 2014) y, por lo tanto, la correlación entre los ítems de cada una de estas escalas es alta (Cortina, 1993). ...
Las restricciones impuestas para contener la pandemia por covid-19 durante el 2020 ocasionaron un gran crecimiento del e-commerce, que no fue uniforme en todas las categorías de productos. Las categorías con comportamientos menos favorables requieren de herramientas para estimular las ventas por el canal digital y los productos más favorecidos necesitan fidelizar a sus clientes. La generación de boca-oído electrónico o e-WoM es una de estas herramientas de las estrategias de marketing que incentivan el e-commerce, por lo que es importante analizar las variables que lo afectan. Una de ellas es la confianza del consumidor en las tiendas en línea, que en el contexto internacional se ha demostrado que promueve el e-WoM. Se realizó un estudio transversal con base en un modelo de ecuaciones estructurales planteado a partir de las escalas de confianza y e-WoM encontradas en la literatura, y comprobado mediante la técnica de regresión de mínimos cuadrados parciales en el software SmartPLS3. Para ello, se encuestó a clientes de tiendas de e-commerce b2c de Bogotá, Medellín y Cali. Los resultados demuestran que los expertos en mercadeo en Colombia deben buscar mecanismos para fortalecer la confianza en las tiendas en línea, porque con ello se contribuye a la difusión de boca-oído electrónico.
... En la utilización de cualquiera de los procedimientos elegidos es importante hacer comprender al alumno el objetivo de la evaluación. En el trabajo de Ruiz-Primo y Furtak [14] se recoge información sobre métodos de evaluación informal, y sobre el proceso de construcción de instrumentos de evaluación estandarizados puede consultarse literatura especializada [6,[15][16][17]. ...
... En la utilización de cualquiera de los procedimientos elegidos es importante hacer comprender al alumno el objetivo de la evaluación. En el trabajo de Ruiz-Primo y Furtak [14] se recoge información sobre métodos de evaluación informal, y sobre el proceso de construcción de instrumentos de evaluación estandarizados puede consultarse literatura especializada [6,[15][16][17]. ...
La evaluación para el aprendizaje en contraposición a la evaluación del aprendizaje se encuadra dentro del tipo de evaluación formativa que permea la educación superior desde la adopción del modelo competencial. Los docentes somos conscientes de la relevancia de las buenas prácticas evaluativas, y conceptos como rúbrica, portafolios, evaluación por pares o evaluación continua, hasta hace poco tiempo relegados a especialistas en evaluación, son parte ya de la jerga universitaria. Sin embargo, la consideración de la evaluación como piedra angular de
la organización y ejecución docentes, colisiona en muchas ocasiones con una alfabetización deficiente, y una estructura académica que limitan el espacio y el tiempo dedicados a implementar programas evaluativos. En este trabajo repasamos algunos de los conceptos clave en evaluación formativa aplicados a la educación superior.
... As none of the tested options provided a good fit, we decided to switch to an empirically guided strategy to select the best items, using the information of the complete sample (n = 528) and taking as exigency criteria to keep an item in the model if (1) the corrected itemtotal correlation was greater than 0.4 [102], (2) the factor loadings were greater than 0.4 [103], and (3) the correlation of the item with the related constructs (validity index of the item) was significant and at least of a small intensity, either positive or negative (r > |0.1|; [101]). There were seven criteria (see Table 5), and items were gradually eliminated. ...
Moral disengagement is a process of cognitive restructuring that allows individuals to disassociate from their internal moral standards and behave unethically without feeling distressed. It has been described as a key predictor of maladaptive behaviors (e.g., delinquency, aggression, and cyberbullying) and as a mediator between individual variables and unethical outcomes (e.g., empathy and aggression). We aimed to provide evidence of validity based on the internal structure, reliability, and correlations with other constructs of the most used instrument to measure disengagement from moral self-sanctions: Bandura’s Mechanisms of Moral Disengagement Scale (MMDS). A nonprobabilistic national sample of 528 Chilean adolescents from 14 to 18 years participated in the study. The results showed that the 10-item version of the MMDS had a unidimensional structure and good internal consistency. As expected, the MMDS-10 showed positive and medium correlations with abusive, violent antisocial, and delinquent behaviors and negative and medium associations with prosocial behavior and empathy. Additionally, moral disengagement fully mediated the relationship between empathy and violent antisocial behavior, supporting the hypothesis on moral disengagement as a self-regulatory cognitive process. The results confirm previous research, and the findings are discussed in terms of their implications for reducing the use of moral disengagement strategies in adolescence.
... The value of Kaiser-Meyer-Olkin (KMO = 0.863) and Bartlett's test (Bartlett's statistic (435) = 5597.2; p < 0.001) obtained indicated that the correlation matrix was adequate for the factor analysis [24]. The exploratory factor analysis classified the items in two subscales: 1) compassion satisfaction (CS), and 2) compassion fatigue (CF). ...
Many workers contribute to the success of animal welfare and study outcomes in biomedical research. However, the professional quality of life (ProQoL) of those who work with laboratory animals has not been explored in Spain. To this end, we adapted the ProQoL scale to the Spanish population working with laboratory animals. Participants were contacted by email and asked to complete an anonymous on-line questionnaire. The study comprised a total of 498 participants, 12.4% welfare officers/veterinarians, 19.5% caretaker/technicians, 13.9% principal investigators, 20.7% investigators, 13.6% research technicians, and 19.9% PhD students. The adapted scale revealed very good reliability and internal validity, providing information about two different sub-scales, compassion satisfaction and compassion fatigue. Animal facility personnel showed higher total ProQoL and compassion satisfaction scores than researchers; PhD students showed the lowest scores. Thus, our results indicate that job category is a contributing factor in perceived professional quality of life. We observed that compassion satisfaction is negatively associated with the perceived animal stress/pain. Participants reporting poorer compassion satisfaction also reported lower social-support scores. Overall, our ProQoL scale is a useful tool for analyzing the professional quality of life in the Spanish population, and may help to design future interventions to improve workplace wellbeing in Spain and other Spanish-speaking populations.
La estigmatización ha acompañado la pandemia del VIH desde sus orígenes, lo cual ha tenido consecuencias negativas en la salud de las personas con VIH y ha desalentado el testeo regular en la población general. Cualquier diseño, monitoreo y reade-cuación de políticas dirigidas a reducir la estigmatización hacia el VIH requiere contar con instrumentos rigurosos para su medición. El objetivo del trabajo fue construir y validar una Breve Escala sobre Estigmatización hacia el VIH (BESE-VIH) en una muestra representativa de la Ciudad Autónoma de Buenos Aires (CABA), respetando sus particularidades lingüísticas. Se encuestó en la vía pública a 400 participantes de entre 18 y 60 años en un diseño muestral por cuotas y se logró la representatividad de género, edad, nivel educativo y nivel socioeconómico. La BESE-VIH quedó compuesta por nueve reactivos y mostró muy buenos niveles de confiabilidad y evidencias de validez interna y externa adecuadas, por lo que la escala resulta un instrumento prometedor.
The presence of people with disabilities in a family can modify family functioning and relationships. This study aimed to verify the initial evidence of internal structure validity and convergence of the Brazilian version of the Family APGAR Scale, in order to evaluate the perception of family functionality in family members of people with disabilities, users of Social Assistance services. Participated in this study 185 family members of people with disabilities, users of a service of a non-governmental entity providing assistance to people with disabilities in a capital of southeastern Brazil. The results from exploratory factorial procedures demonstrated the internal one-dimensional structure of the adapted measure, composed of five items, with good precision indicators of the Alpha (α = 0,96) and Omega (ω = 0.96). Evidence of convergent validity between the adapted measure in this study and the Total Social Support Scale of the Medical Outcomes Study (MOS) was also observed. Thus, the results indicate that the adapted Brazilian version of the measure had adequate psychometric properties and can be used in this context and population.
Ten steps for test development.
Background:
Tests are the measurement instruments most used by psychologists to obtain data about people, both in professional and research contexts. The main goal of this paper is to synthesize in ten steps the fundamental aspects that must be taken into account when building a test in a rigorous way.
Method:
For the elaboration of the ten proposed phases, the specialized psychometric literature was revised, and previous works by the authors on the subject were updated.
Results:
Ten steps are proposed for the objective development of a test: delimitation of the general framework, definition of the variable to be measured, specifications, items development, edition of the test, pilot studies, selection of other measurement instruments, test administration, psychometric properties, and development of the final version.
Conclusion:
Following the ten proposed steps, objective tests can be developed with adequate psychometric properties based on empirical evidence.
Background:
The use of positively worded items and reversed forms aims to reduce response bias and is a commonly used practice nowadays. The main goal of this research is to analyze the psychometric implications of the use of positive and reversed items in measurement instruments.
Method:
A sample of 374 participants was tested aged between 18 and 73 (M=33.98; SD=14.12), 62.60% were women. A repeated measures design was used, evaluating the participants with positive, reversed, and combined forms of a self-efficacy test.
Results:
When combinations of positive and reversed items are used in the same test the reliability of the test is flawed and the unidimensionality of the test is jeopardized by secondary sources of variance. In addition, the variance of the scores is reduced, and the means differ significantly from those in tests in which all items are either positive or reversed, but not combined.
Conclusions:
The results of this study present a trade-off between a potential acquiescence bias when items are positively worded and a potential different understanding when combining regular and reversed items in the same test. The specialized literature recommends combining regular and reversed items for controlling for response style bias, but these results caution researchers in using them as well after accounting for the potential effect of linguistic skills and the findings presented in this study.
Conventional methods for producing test norms are often plagued with “jumps” or “gaps” (i.e., discontinuities) in norm tables and low confidence for assessing extreme scores. We propose a new approach for producing continuous test norms to address these problems that also has the added advantage of not requiring assumptions about the distribution of the raw data: Norm values are established from raw data by modeling the latter ones as a function of both percentile scores and an explanatory variable (e.g., age). The proposed method appears to minimize bias arising from sampling and measurement error, while handling marked deviations from normality – such as are commonplace in clinical samples. In addition to step-by-step instructions in how to apply this method, we demonstrate its advantages over conventional discrete norming procedures using norming data from two different psychometric tests, employing either age norms (N = 3.555) or grade norms (N = 1.400).
An R package for applying the procedure is available via https://www.psychometrica.de/cNorm_en.html
The Cronbach's alpha is the most widely used method for estimating internal consistency reliability. This procedure has proved very resistant to the passage of time, even if its limitations are well documented and although there are better options as omega coefficient or the different versions of glb, with obvious advantages especially for applied research in which the ítems differ in quality or have skewed distributions. In this paper, using Monte Carlo simulation, the performance of these reliability coefficients under a one-dimensional model is evaluated in terms of skewness and no tau-equivalence. The results show that omega coefficient is always better choice than alpha and in the presence of skew items is preferable to use omega glb coefficients even in small samples.
http://journal.frontiersin.org/article/10.3389/fpsyg.2016.00769/abstract
A must-have resource for researchers, practitioners, and advanced students interested or involved in psychometric testing. Over the past hundred years, psychometric testing has proved to be a valuable tool for measuring personality, mental ability, attitudes, and much more. The word 'psychometrics' can be translated as 'mental measurement'; however, the implication that psychometrics as a field is confined to psychology is highly misleading. Scientists and practitioners from virtually every conceivable discipline now use and analyze data collected from questionnaires, scales, and tests developed from psychometric principles, and the field is vibrant with new and useful methods and approaches. This handbook brings together contributions from leading psychometricians in a diverse array of fields around the globe. Each provides accessible and practical information about their specialist area in a three-step format covering historical and standard approaches, innovative issues and techniques, and practical guidance on how to apply the methods discussed. Throughout, real-world examples help to illustrate and clarify key aspects of the topics covered. The aim is to fill a gap for information about psychometric testing that is neither too basic nor too technical and specialized, and will enable researchers, practitioners, and graduate students to expand their knowledge and skills in the area. Provides comprehensive coverage of the field of psychometric testing, from designing a test through writing items to constructing and evaluating scales. Takes a practical approach, addressing real issues faced by practitioners and researchers. Provides basic and accessible mathematical and statistical foundations of all psychometric techniques discussed. Provides example software code to help readers implement the analyses discussed.
