= Linear regression model
{title2=$Y=X\beta+\varepsilon$}
A <statistical model> specifying a response as a linear combination of known regressor columns and an error. Common assumptions are $\mathbb E[\varepsilon]=0$ and $\operatorname{Cov}(\varepsilon)=\sigma^2I$, although a <normal distribution> is an additional assumption, not part of the displayed equation alone. Full <column rank> of the <design matrix> makes the coefficients identifiable. Statistical association does not by itself give a <causal effect>.
Back to article page
