= Solution
\b[TODO: directions, magnitudes and inferential conclusions require the unavailable coefficient table, coding and model specification.] For illustration of interpretation only, let $D$ and $S$ be binary indicators whose reference levels are explicitly defined. If an ordinary linear model includes both factors and their <interaction>, its conditional mean has the form
$$
\operatorname E(Y\mid D,S)=\beta_0+\beta_DD+\beta_SS+\beta_{DS}DS.
$$
Then the distance difference is $\beta_D$ at the reference size and $\beta_D+\beta_{DS}$ at the other size; the <interaction> is the difference between those differences. If the <interaction> is omitted, the model assumes a common distance difference across sizes. These are conditional model meanings, not a claim that the missing analysis used this model or that either predictor had an observed effect. The uncertainty of a coefficient sum also involves their <covariance>, not merely their separate <p-values>.
Back to article page
