Esta apostila resume o Capítulo 4 de An Introduction to Generalized Linear Models (Dobson & Barnett, 4ª ed., 2018). O capítulo desenvolve a teoria de estimação por máxima verossimilhança para MLGs, introduz o algoritmo de Newton–Raphson, apresenta o método de scoring e demonstra que os estimadores de MLGs são obtidos por mínimos quadrados iterativamente reponderados (IRLS). Todos os resultados são ilustrados com exemplos numéricos completos, incluindo tabelas e gráficos reproduzidos.

This code through shows how R can be used to track, analyze, and visualize language learning progress over time. Using Hungarian as an example, I created a six month dataset measuring vocabulary mastered, words read, listening hours, speaking hours, and study consistency. I compare these measurements to illustrative CEFR related benchmarks to identify strengths and areas that need improvement. I also demonstrate how R can estimate future progress, calculate the time needed to reach selected learning goals, and identify adjustments to a study plan. The goal is to show how data analysis can help self directed language learners better understand their progress and make informed decisions about their learning strategies.

project wrangling report (hopefully final)