« Théorème central limite » : différence entre les versions
(Page créée avec « ==en construction== == Définition == XXXXXXXXX == Français == ''' XXXXXXXXX ''' == Anglais == ''' Central Limit Theorem''' The Central Limit Theorem states that the... ») |
m (Remplacement de texte — « DeepAI.org ] » par « DeepAI.org ] Catégorie:DeepAI.org ») |
||
| Ligne 23 : | Ligne 23 : | ||
[https://deepai.org/machine-learning-glossary-and-terms/central-limit-theorem Source : DeepAI.org ] | [https://deepai.org/machine-learning-glossary-and-terms/central-limit-theorem Source : DeepAI.org ] | ||
[[Catégorie:DeepAI.org]] | |||
[[Catégorie:vocabulary]] | [[Catégorie:vocabulary]] | ||
Version du 15 décembre 2020 à 18:10
en construction
Définition
XXXXXXXXX
Français
XXXXXXXXX
Anglais
Central Limit Theorem
The Central Limit Theorem states that the distribution of various independent observation means approaches a normal distribution model as the sample size gets larger, regardless of the population distribution’s statistical shape.
Moreover, the theory demonstrates that as the sample size increase, even across multiple unrelated datasets, so increases the accuracy of the population mean estimate.
For example, calculating the mean of a sample is only an estimate of the mean of the population distribution. So there will always be some margin of error. However, if you draw multiple independent samples and then graph all of their means, the distribution of those sample means will form a Normal, or Gaussian distribution.
On the same token, if you take the average of every standard deviation observation in your sample, then you’ll find the exact standard deviation for your entire population.
Contributeurs: Isaline Hodecent, wiki
