Shrinkage (statistics)In statistics, shrinkage is the reduction in the effects of sampling variation. In regression analysis, a fitted relationship appears to perform less well on a new data set than on the data set used for fitting. In particular the value of the coefficient of determination 'shrinks'. This idea is complementary to overfitting and, separately, to the standard adjustment made in the coefficient of determination to compensate for the subjunctive effects of further sampling, like controlling for the potential of new explanatory terms improving the model by chance: that is, the adjustment formula itself provides "shrinkage.
Strain (chemistry)In chemistry, a molecule experiences strain when its chemical structure undergoes some stress which raises its internal energy in comparison to a strain-free reference compound. The internal energy of a molecule consists of all the energy stored within it. A strained molecule has an additional amount of internal energy which an unstrained molecule does not. This extra internal energy, or strain energy, can be likened to a compressed spring.
Tension de cycleEn chimie organique, la tension de cycle ou contrainte cyclique désigne la déstabilisation d'une molécule cyclique, telle un cycloalcane, causée par l'orientation spatiale des atomes qui la composent. Cette tension provient d'une combinaison (1) de contrainte d'angle, (2) de contrainte de torsion (ou tension de Pitzer) et (3) de la tension trans-annulaire (ou contrainte de van der Waals).
Reduced chi-squared statisticIn statistics, the reduced chi-square statistic is used extensively in goodness of fit testing. It is also known as mean squared weighted deviation (MSWD) in isotopic dating and variance of unit weight in the context of weighted least squares. Its square root is called regression standard error, standard error of the regression, or standard error of the equation (see ) It is defined as chi-square per degree of freedom: where the chi-squared is a weighted sum of squared deviations: with inputs: variance , observations O, and calculated data C.
Generalized least squaresIn statistics, generalized least squares (GLS) is a method used to estimate the unknown parameters in a linear regression model when there is a certain degree of correlation between the residuals in the regression model. Least squares and weighted least squares may need to be more statistically efficient and prevent misleading inferences. GLS was first described by Alexander Aitken in 1935. In standard linear regression models one observes data on n statistical units.
Série temporellethumb|Exemple de visualisation de données montrant une tendances à moyen et long terme au réchauffement, à partir des séries temporelles de températures par pays (ici regroupés par continents, du nord au sud) pour les années 1901 à 2018. Une série temporelle, ou série chronologique, est une suite de valeurs numériques représentant l'évolution d'une quantité spécifique au cours du temps. De telles suites de variables aléatoires peuvent être exprimées mathématiquement afin d'en analyser le comportement, généralement pour comprendre son évolution passée et pour en prévoir le comportement futur.
