Latent growth mixture modeling: an application in the aeronautic training environment

• Autor(a) principal: Gomes, Ana Patrícia Correia
• Data de Publicação: 2009
• Tipo de documento: Dissertação
• Idioma: eng
• Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
• Texto Completo: http://hdl.handle.net/10071/2009
• topic: Latent change models; Growth mixture modeling; Aeronautic training; Unobserved heterogeneity; Modelos com mudança latente; Modelo de mistura com crescimento latente; Treino aeronáutico; Heterogeneidade não observada

The application of growth mixture modeling to longitudinal data offers an important extension of conventional modeling tools, enabling the identification of different patterns in growth, by accounting for population heterogeneity. The main goal of this study is to analyze the shape of the learning process in pilot training (Latent Growth Modeling), as well as to recognize different patterns in growth due to population heterogeneity (Growth Mixture Modeling). Moreover, the research intends to identify predictors that explain that variability and the pattern of growth. The object of study is the performance in flight training of ab-initio pilot applicants (n=297) to the Portuguese Air Force Academy (evaluated through six repeated measures). The results showed the existence of unobserved heterogeneity in the population and the best fitting model is a 2-class mixture model. Psychomotor coordination (SMA) showed a significant effect on the intercept (initial status) and the prognostic of General Adaptability (Personality and Motivation dimension) depicted a significant effect on the intercept (initial status) and on slope (development). The latent class 1 (66% of the sample) presents the highest initial flight performance, a positive significant effect of the General Adaptation on the intercept and the best results in the tests performed in the psychological phase. The latent class 2 (34% of the sample) presents the worst initial flight performance, and a positive significant effect of General Adaptation on the slope.