TERMIUM Plus®
The Government of Canada’s terminology and linguistic data bank.
HOLDOUT SAMPLE [2 records]
Record 1 - internal organization data 2017-03-20
Record 1, English
Record 1, Subject field(s)
- Statistical Methods
Record 1, Main entry term, English
- hold-out sample
1, record 1, English, hold%2Dout%20sample
correct
Record 1, Abbreviations, English
Record 1, Synonyms, English
- test sample 2, record 1, English, test%20sample
correct
Record 1, Textual support, English
Record number: 1, Textual support number: 1 DEF
[A] set of data withheld from the end of a series [and] to be compared with the forecast values in assessing a forecasting model. 3, record 1, English, - hold%2Dout%20sample
Record 1, Key term(s)
- holdout sample
Record 1, French
Record 1, Domaine(s)
- Méthodes statistiques
Record 1, Main entry term, French
- échantillon test
1, record 1, French, %C3%A9chantillon%20test
masculine noun
Record 1, Abbreviations, French
Record 1, Synonyms, French
Record 1, Textual support, French
Record number: 1, Textual support number: 1 CONT
Une cause très fréquente réside dans la non-représentativité de l’échantillon de données utilisé pour calibrer ou évaluer le modèle, qui peut généralement être détectée par une analyse des données à disposition, et par une comparaison statistique à l’ensemble des données sur lequel est appliqué le modèle (échantillon test). 2, record 1, French, - %C3%A9chantillon%20test
Record 1, Spanish
Record 1, Textual support, Spanish
Record 2 - internal organization data 2010-06-04
Record 2, English
Record 2, Subject field(s)
- Statistical Methods
Record 2, Main entry term, English
- holdout sample
1, record 2, English, holdout%20sample
correct
Record 2, Abbreviations, English
Record 2, Synonyms, English
Record 2, Textual support, English
Record number: 2, Textual support number: 1 CONT
Utilizing standard structured interview data, we employed a holdout sample strategy to test a path model that posited three psychosocial variables as partially mediating the predictive relations of two ecological/architectural and three personal variables with mental health. 1, record 2, English, - holdout%20sample
Record number: 2, Textual support number: 1 OBS
The strategy used to develop the model involved randomly splitting the total sample of 989 subjects into two approximately equal size groups. The model was developed on one-half of the sample ("explore" group, n = 494) and subsequently tested on the other half ("confirm" group, n = 495). 1, record 2, English, - holdout%20sample
Record 2, French
Record 2, Domaine(s)
- Méthodes statistiques
Record 2, Main entry term, French
- échantillon restant
1, record 2, French, %C3%A9chantillon%20restant
proposal, masculine noun
Record 2, Abbreviations, French
Record 2, Synonyms, French
- échantillon confirmant 1, record 2, French, %C3%A9chantillon%20confirmant
proposal, masculine noun
Record 2, Textual support, French
Record 2, Spanish
Record 2, Textual support, Spanish
Copyright notice for the TERMIUM Plus® data bank
© Public Services and Procurement Canada, 2024
TERMIUM Plus®, the Government of Canada's terminology and linguistic data bank
A product of the Translation Bureau
Features
Language Portal of Canada
Access a collection of Canadian resources on all aspects of English and French, including quizzes.
Writing tools
The Language Portal’s writing tools have a new look! Easy to consult, they give you access to a wealth of information that will help you write better in English and French.
Glossaries and vocabularies
Access Translation Bureau glossaries and vocabularies.
- Date Modified: