Linear Models in Statistics

By Debasis Sengupta. 2001

254 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

RUDDER: Return Decomposition for Delayed Rewards (2018, background): “=1 ^T 1 x i = y sT yx S 1 xx x + sT yx S 1 xx x = y: •The vector of standardized coefﬁcients ^ 1 are ^ 1= 1 s y D x^ = R 1 xx r yx: (A288) The next theorem is Theorem 10.6 in Rencher and Schaalje [91] and gives a breakdown of the factors that determine how much each variable adds to R2 [91, Chapter ”
Classification Accuracy as a Proxy for Two Sample Testing (2016, unknown): “2 in Rencher and Schaalje (2008)).”
Temperature models for pricing weather derivatives (2012, methodology): “With this assumption we can use the well-known theory of linear models (Rencher 2008 ) to estimate the variance of the error of the prediction Ŷ n +1 : where is the unbiased estimate for the variance σ 2 of the errors.”
Fungible Weights in Multiple Regression (2008, methodology): “Stated otherwise, if �a denotes a linear combination of x using alternate weights a, a �= b (�ya = a � x) then, for any a, SSEb r y�a in the sample from which b has been calculated ( Rencher, 2000, p. 238 ).”
Departing from Lectures: An Evaluation of a Peer-Led Guided Inquiry Alternative (2005, background): “To decide which significant parameter had the greatest impact on student performance, the standardized regression weights (!) can be compared within each model (12).”
Performance of the CMS muon detector and muon reconstruction with proton-proton collisions at √s=13 TeV (2018, methodology): “These residuals are approximately Gaussian and the residual widths are converted to position resolution by using standard analytical factors [26].”