Nearly Unbiased Maximum Likelihood Estimation for the Beta Distribution

By Francisco Cribari‐Neto, Klaus L. P. Vasconcellos. 2002

75 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/b664db287c1b5dd6a58af5d807360ec6befa39d9

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

General results for the Marshall and Olkin's family of distributions (2013, unknown): “We obtain what we call the integrated relative bias squared norm (Cribari-Neto and Vasconcellos 2002).”
Improved maximum-likelihood estimators for the parameters of the unit-gamma distribution (2018, methodology): “Finally, we assess the overall performance of each estimators with respect to the bias and root mean-squared error through two measures proposed by Cribari-Neto and Vasconcellos (2002).”
Bias-corrected maximum likelihood estimation of the parameters of the generalized Pareto distribution (2016, unknown): “Interestingly, Cribari-Neto and Vasconcellos (2002) found that these two approaches are equally successful with respect to (finite sample) bias reduction without loss of efficiency in the context of the MLE for the parameters of the beta distribution.”
Improved point estimation for the Kumaraswamy distribution (2011, methodology): “We obtain what we call the integrated relative bias squared norm [12].”
Beta autoregressive moving average models (2009, background): “For a detailed discussion of information criteria and their properties, see Choi (1992) .”
On the Bias of the Maximum Likelihood Estimator for the Two-Parameter Lomax Distribution (2013, result): “This “over-correction” has been reported in similar studies involving the Cox-Snell methodology, including those of Cribari-Neto and Vasconcellos (2002) for the beta distribution, Giles (2012) for the half-logistic distribution, and Giles et al.”
Improved estimators for a general class of beta regression models (2008, methodology): “ζ, ζ) defined in equation ( 13 ), ˆ BFˆ ( ˆ”
A better lemon squeezer? Maximum-likelihood regression with beta-distributed dependent variables. (2006, background): “It should be borne in mind that maximum-likelihood estimates are not necessarily unbiased, and the degree of bias will be greater for small samples (see Cribari-Neto & Vasconcellos, 2002, for an exploration of bias in such models).”