Is Correcting for Acquiescence Increasing the External Validity of Personality Test Scores? / ¿La Corrección por Aquiescencia Aumenta la Validez Externa de las Puntuaciones en Personalidad?

Background: Balanced scales control for acquiescence (ACQ) because the tendency of the respondent to agree with the positive items is cancelled out by the tendency to agree with opposite-pole items. When full balance is achieved, ACQ is not expected to affect external validity. Otherwise, attenuated estimates are expected to appear if no control methods such as Lorenzo-Seva & Ferrando’s (2009) are used. Method: Expected results were derived analytically. Subsequently, a simulation was carried out to assess (a) how ACQ impacted external validity and (b) how validity estimates behaved when ACQ was corrected. Two illustrative examples are provided. Results: A sizable number of items and/or high content loadings tended to decrease ACQ’s impact on validity estimates, making the empirical coefficient closer to its structural value. Furthermore, when scales were well balanced, the controlled and uncorrected scores were close to each other, and led to unbiased validity estimates. When the scales were unbalanced and no corrections were used, attenuated empirical validity coefficients inevitably appeared. Conclusions: Designing a well-balanced test or correcting for ACQ are the best ways to minimize attenuation in external validity estimation. (AU)

Antecedentes: construir escalas balanceadas permite controlar la aquiescencia (ACQ), haciendo que la tendencia del encuestado a estar de acuerdo con los ítems positivos se cancele con la tendencia a estar de acuerdo con los ítems del polo opuesto. En caso contrario, se esperarán estimaciones atenuadas de los coeficientes de validez externa en caso de no utilizar algún método de control (Lorenzo-Seva & Ferrando, 2009). Método: se llevó a cabo (a) un desarrollo analítico (b) una simulación para evaluar (a) el impacto de ACQ en la validez externa y (b) el comportamiento de las estimaciones de validez cuando se corrige por ACQ. Incluyendo finalmente dos ejemplos ilustrativos. Resultados: número alto de ítems y/o cargas altas en el factor de contenido tienden a disminuir el impacto de ACQ en las estimaciones de validez. Además, con escalas balanceadas por diseño, las diferencias entre las puntuaciones corregidas y no corregidas son menores, llevando a estimaciones de validez insesgadas. En escalas no balanceadas ni corregidas aparece una atenuación en el coeficiente de validez empírico. Conclusiones: diseñar pruebas balanceadas o corregir ACQ son las mejores maneras de minimizar la atenuación en la estimación de la validez externa. (AU)

Optimization of Machine Learning in Various Situations Using ICT-Based TVOC Sensors.

A computational framework using artificial intelligence (AI) has been suggested in numerous fields, such as medicine, robotics, meteorology, and chemistry. The specificity of each AI model and the relationship between data characteristics and ground truth, allowing their guidance according to each situation, has not been given. Since TVOCs (total volatile organic compounds) cause serious harm to human health and plants, the prevention of such damages with a reduction in their occurrence frequency becomes not an optional process but an essential one in manufacturing, as well as for chemical industries and laboratories. In this study, with consideration of the characteristics of the machine learning technique and ICT (information and communications technology), TVOC sensors are explored as a function of grounded data analysis and the selection of machine learning models, determining their performance in real situations. For representative scenarios, considering features from an ICT semiconductor sensor and one targeting TVOC gas, we investigated suitable analysis methods and machine learning models such as LSTM (long short-term memory), GRU (gated recurrent unit), and RNN (recurrent neural network). Detailed factors for these machine learning models with respect to the concentration of TVOC gas in the atmosphere are compared with original sensory data to obtain their accuracy. From this work, we expect to significantly minimize risk in empirical applications, i.e., maintaining homeostasis or predicting abnormal situations to construct an opportune response.