noun
generalized linear model
A statistical model that extends ordinary linear regression to response variables with non-normal error distributions, such as binary, count, or skewed data. Common in data analysis and machine learning.
ロジスティック回帰は一般化線形モデルの一種です。
Logistic regression is a type of generalized linear model.
このデータには一般化線形モデルを適用するのが適切だ。
It is appropriate to apply a generalized linear model to this data.
Linear regression is a special case of a generalized linear model with normally distributed errors and identity link function.
General linear model (GLM) is a broader class that includes multiple linear regression and ANOVA, but assumes normal errors; generalized linear models extend to other distributions.
Calque from English 'generalized linear model'. The Japanese term is a direct translation: 一般化 (generalization) + 線形 (linear) + モデル (model).