The Observation Theory EncyclopediaFrom TSKAboutBy kindBy chapterBy Lean fileLedgerProvenance

bagging instrument

DefinitionFitting the same model on bootstrap resamples and averaging. The average's squared error is at most the members' mean squared error, which is how it reduces variance. Chapter 7. Also bootstrap aggregat.
ExampleTen trees fit on ten bootstrap resamples and averaged have at most the mean squared error of the ten members.
BookData Mining as Observation, draft 0.2, commit f3914f0; entry id bagging, kind instrument.
Statusno ledger row names this entry. Corrections: none recorded.
Defining equationnone
Assumptions and scope
  • Fitting the same model on bootstrap resamples of the rows and averaging. The average’s squared error is at most the mean of the members’ squared errors, which is the arithmetic by which bagging reduces variance, and the reduction is largest when the members covary least.
  • Bagging reduces variance and boosting reduces bias, and neither changes what the base model reads.
Prior artnone recorded
Evidencelean/DataMiningAsObservation/Ensemble.lean, lean/DataMiningAsObservation/Bootstrap.lean
Reviewednot yet reviewed; generated 2026-09-10 from records at the commits on the provenance page.
00.51estimateresamples of the same rows
Resamples of the same rows, each fit and then averaged.

Equation

none

Conditions

Conditions are curated in entries.toml rather than read from a record.

Ledger

none

First stated

Breiman, bagging predictors, 1996, as chapter 7 section 7.1 of Data Mining as Observation reads it.

Measurements

Where the book states it Numbers, as the book’s sources table records them Source
chapter 7 section 7.1 bagging variance, out-of-bag estimation, random forests, importances, AdaBoost Hastie, Tibshirani, Friedman, ESL 2e chapters 15 and 10.1; TSK 2e 4.10

Failures and corrections

none

Invariance envelope

none declared

Machine checked

lean/DataMiningAsObservation/Ensemble.lean, theorems average_between, sq_average_le, average_const, at observation-data-mining f3914f0; what the check covers is stated in the book’s appendix C.

lean/DataMiningAsObservation/Bootstrap.lean, theorems mean_sub, var_sub, paired_lt_iff, cov_comm, at observation-data-mining f3914f0; what the check covers is stated in the book’s appendix C.

Used in

Data Mining as Observation chapters 7.

Related

ensemble; bootstrap; random forest; standard error; variance.

See also

Book equations stated beside the entry’s terms, not defining it: 0.18, 8.2.

Status

Generated 2026-09-10 by encyclopedia/generate.py; book at observation-data-mining f3914f0; the commit of every record is listed in the encyclopedia’s provenance.

← AUROCbag of words →