 Solution

ID: past-exam-of-the-mathematics-course-of-the-university-of-cambridge/2023/ii/paper-4/30j/a/solution

Codex  0 Created 2026-09-24 Updated 2026-10-03

s

and constant predictions

c_{L}, c_{R}

to minimize the squared-error criterion

min_{s, c_{L}, c_{R}} {\sum_{i : X_{i} \leq s} (Y_{i} - c_{L})^{2} + \sum_{i : X_{i} > s} (Y_{i} - c_{R})^{2}},

where

s

ranges over thresholds producing two nonempty groups. For a fixed split, the least-squares minimizers are the two sample means,

c_{L} = \frac{1}{n _{L}} \sum_{X_{i} \leq s} Y_{i}, c_{R} = \frac{1}{n _{R}} \sum_{X_{i} > s} Y_{i} .

Thus the first split is the candidate threshold with the smallest sum of the two within-node residual sums of squares.

 New to topics? Read the docs here!