Vertaile menetelmiä

	Lasso-regressio	Paneeliaineiston kiinteiden vaikutusten malli	Poisson- ja negatiivinen binomiregressio
Tieteenala	Koneoppiminen	Ekonometria	Ekonometria
Menetelmäperhe	Machine learning	Regression model	Regression model
Syntyvuosi	1996	2014	1998
Kehittäjä	Tibshirani, R.	Hsiao (textbook treatment); within transformation of panel data	Cameron & Trivedi (textbook treatment); Hilbe (negative binomial)
Tyyppi	Regularized linear regression (L1 penalty)	Panel data regression	Generalized linear model for count data
Alkuperäislähde	Tibshirani, R. (1996). Regression Shrinkage and Selection via the Lasso. Journal of the Royal Statistical Society: Series B, 58(1), 267–288.	Hsiao, C. (2014). Analysis of Panel Data (3rd ed.). Cambridge University Press.	Cameron, A. C. & Trivedi, P. K. (1998). Regression Analysis of Count Data. Cambridge University Press.
Rinnakkaisnimet	LASSO Regresyonu, lasso, L1-regularized regression, L1 regularization	fixed effects model, within estimator, panel fixed-effects regression, Panel Veri — Sabit Etkiler Modeli	count regression, log-linear count model, negative binomial regression, Poisson / Negatif Binom Regresyon
Liittyvät	4	5	4
Tiivistelmä	Lasso regression, introduced by Robert Tibshirani in 1996, is a linear regression method that adds an L1 penalty to the loss so that it shrinks coefficients and performs variable selection at the same time, producing a sparse model. By driving some coefficients exactly to zero it keeps only the predictors that matter.	The Panel Data Fixed Effects model estimates relationships from panel data (the same units observed over several time periods) while controlling for unit- and/or time-specific effects, supporting causal inference. It is developed as the within estimator in standard treatments such as Hsiao's Analysis of Panel Data (2014).	Poisson regression is a generalized linear model for count outcomes — events tallied as non-negative integers such as hospital admissions, accidents, or article counts. It models the log of the expected count as a linear function of the predictors, and is developed in the standard count-data treatment of Cameron and Trivedi (1998); when the counts are over-dispersed, the closely related negative binomial model (Hilbe, 2011) is preferred.