RESUMEN
Resumen La actitud positiva hacia la estadística promueve el estudio y uso de esta disciplina fundamental para analizar datos; de ahí la relevancia de evaluar el nivel actitudinal y desarrollar estrategias que lo potencien. La Escala de Actitud hacia la Estadística (EAE-25) de Auzmendi es uno de los instrumentos más usados en español para medir esta actitud, pero no se ha validado en México, lo que es importante para su uso en este país y para aportar evidencias de validez. Los objetivos del estudio fueron contrastar el modelo propuesto originariamente, comprobar su consistencia interna, describir su distribución, comparar los promedios entre sexos y verificar su validez concurrente. Este estudio instrumental usó un muestreo no probabilístico. Se analizó una muestra de 383 estudiantes de psicología mexicanos (73.6 % mujeres y 26.4 % hombres) que respondieron a dos escalas de actitud. El modelo de cinco factores (confianza, ansiedad, agrado, utilidad y motivación) mostró buen ajuste a los datos. Sus factores presentaron confiabilidad y validez discriminante. La distribución de las puntuaciones en EAE-25 fue normal. La actitud se polarizó, aproximadamente, en cuatro de cada diez estudiantes hacia la aceptación y en uno de cada diez hacia el rechazo. No hubo diferencias de medias entre sexos. La EAE-25 tuvo correlación alta con actitud hacia la investigación y baja con la calificación en la materia de investigación del semestre anterior. Se concluye que la EAE-25 presenta consistencia interna y validez de constructo.
Abstract The positive attitude towards statistics promotes the study and use of this fundamental discipline to analyze data, hence the relevance of evaluating the attitudinal level and developing strategies that promote a positive attitude. The Auzmendi's Scale of Attitude towards Statistics (EAE-25) is one of the most used instruments in Spanish language to assess this attitude; however, it has not been validated in Mexico, which is important for its use in this country and to provide evidence of validity. The objectives of the study were to test the originally proposed model, to verify its reliability, to describe its distribution, to compare the averages between both sexes, and to verify its concurrent validity. A non-probabilistic sampling was used in this instrumental study. A sample of 383 Mexican psychology students was analyzed (73.6 % women and 26.4 % men). The EAE-25 and a scale assessing attitude towards research were applied. Confirmatory factor analysis was used to test the Auzmendi's five-factor model. The parameter estimation was performed by unweighted least squares, using polychoric correlation matrix. The internal consistency was estimated by the McDonald's omega coefficient (ω), the convergent validity by the average variance extracted (AVE), and the discriminant validity by the heterotrait-monotrait ratio of correlations (HTMT). The mean differences between both sexes were tested through the t-test and concurrent validity through Pearson's correlation coefficients. The model of five correlated factors (confidence, anxiety, pleasure, usefulness, and motivation) showed good fit (χ./df =1.79, GFI = .98, AGFI = .97, NFI = .97, CFI =.99, RMSEA = .04, and SRMR = .07). The five factors showed reliability (ω > .80 in confidence, anxiety, pleasure, and usefulness, and ω = .72 in motivation) and discriminant validity (HTMT < .85 in nine out of ten factor pairs, and < .90 in the pair of the anxiety and confidence factors). The values of AVE were higher than .50 in the factors of confidence, anxiety and pleasure, which shows convergent validity in these three factors. A value of AVE very close to .50 in utility (AVE = .49) was compensated by an omega coefficient of .82, which suggests an acceptable convergent validity. However, the value of AVE was lower than .50 in motivation (AVE = .34). The EAE-25 and its factors presented normal distribution, with the exception of the motivation factor. The scores in the scale and its factors were obtained through the quotient between the sum of the items scored in the sense of acceptance attitude and the number of items added. These scores were interpreted in an absolute sense, by dividing the continuum from 1 to 5 into five intervals in correspondence with the five ordered categories of response to the items: [1, 1.8) y [1.8, 2.6) rejection, [2.6, 3.4) neutral, and [3.4, 4.2) y [4.2, 5] acceptance. The average attitude was positive in confidence (. = 3.53) and utility (. = 3.52), and neutral in the EAE-25 total score and its other three factors. The EAE-25 total scores were polarized towards acceptance in approximately four out of ten students and towards the rejected in approximately one out of ten; in the rest, they were neutral. There were no differences of means between both sexes. The EAE-25 total score had a high correlation with the total score in the scale of attitude towards research (. = .52, . < .001) and low with the qualification in the research subject of the previous semester (. = .13, . < .001). It is concluded that EAE-25 presents internal consistency and construct validity. It is suggested to use this scale in applied research in the field of university education and upper secondary education.
RESUMEN
Abstract The scientific method is indispensable for the consolidation of evidence-based Psychology. However, Psychology is a discipline permeated by doubts about its scientific nature, and there are resistances to the scientific method by its students and professionals. The aim of this study was to verify relations between Attitude towards Science in Psychology's scores (ATSP) and sociodemographic characteristics. Participants were 611 people, students or professionals of Psychology, from all regions of Brazil, with 18 to 75 years, 64.2% women. Participants answered a sociodemographic questionnaire and the Attitude towards Science in Psychology Scale. Men presented ATSP more favorable than women, as did students from private universities compared to public universities and people who work in relation to those who do not work. Rio de Janeiro presented lower rates of ATSP compared to other states in the South and Southeast. The results promote preliminary findings of variables involved in the difficulty of constructing a scientific psychology in Brazil.
Resumo O método científico é importante para a consolidação da Psicologia baseada em evidências. Entretanto, a Psicologia é uma disciplina permeada por dúvidas em relação à sua cientificidade, e há resistências à pesquisa científica por parte de seus estudantes e profissionais. O objetivo deste estudo foi verificar relações entre escores de atitude em relação à ciência na Psicologia (ARCP) e características sociodemográficas. Participaram 611 pessoas, estudantes ou profissionais da Psicologia, de todas as regiões brasileiras, com 18 a 75 anos, sendo 64,2% mulheres. Os participantes responderam um questionário sociodemográfico e à Escala de Atitude em Relação à Ciência na Psicologia. Homens apresentaram ARCP mais favorável do que mulheres, assim como os alunos de instituições privadas em relação aos de instituições públicas e pessoas que trabalham em relação às que não trabalham. O Rio de Janeiro apresentou menores índices de ARCP em comparação com os outros estados do Sul e Sudeste. Os resultados promovem apontamentos preliminares sobre as variáveis envolvidas na dificuldade de se construir uma Psicologia científica no Brasil.
Resúmen El método científico es importante para la consolidación de la Psicología basada en evidencias. Sin embargo, la Psicología es una disciplina permeada por dudas en relación a su cientificidad, existiendo resistencia en el uso del la investigación científica por parte de estudiantes y profesionales del área. El objetivo de este estudio fue verificar relaciones entre las puntuaciones de actitud en relación a la ciencia en la Psicología (ARCP) y características sociodemográficas. Participaron 611 personas, entre estudiantes o profesionales de Psicología de todas las regiones brasileñas, de 18 a 75 años, siendo 64,2% mujeres. Los participantes respondieron un cuestionario sociodemográfico y la Escala de Actitud en relación a la Ciencia en Psicología. Los hombres presentaron ARCP más favorable que las mujeres, así como los alumnos de instituciones privadas en relación a los de instituciones públicas y personas que trabajan en relación a las que no trabajan. Río de Janeiro presentó menores índices de ARCP en comparación con los otros estados del Sur y Sudeste. Los resultados promueven apuntes preliminares sobre las variables involucradas en la dificultad de construir una Psicología científica en Brasil.