Bias of the Maximum Likelihood Estimators of the Two-Parameter Gamma Distribution Revisited

We consider the quality of the maximum likelihood estimators for the parameters of the two-parameter gamma distribution in small samples. We show that the methodology suggested by Cox and Snell (1968) can be used very easily to bias-adjust these estimators. A simulation study shows that this analytic correction is frequently much more effective than bias-adjusting using the bootstrap – generally by an order of magnitude in percentage terms. The two bias-correction methods considered result in increased variability in small samples, and the original estimators and their bias-corrected counterparts all have similar percentage mean squared errors.

[1]  R. F. Drenick,et al.  Mathematical Aspects of the Reliability Problem , 1960 .

[2]  B. Efron.  The jackknife, the bootstrap, and other resampling plans , 1987 .

[3]  M. Segal,et al.  Comparing DNA Fingerprints of Infectious Organisms , 2000 .

[4]  B. Bobée,et al.  The gamma family and derived distributions applied in hydrology , 1991 .

[5]  D. Cox,et al.  A General Definition of Residuals , 1968 .

[6]  L. Shenton,et al.  Higher Moments of a Maximum‐Likelihood Estimate , 1963 .

[7]  K. Pearson.  Contributions to the Mathematical Theory of Evolution. II. Skew Variation in Homogeneous Material , 1895 .

[8]  P. McCullagh,et al.  Bias Correction in Generalized Linear Models , 1991 .

[9]  David Durand,et al.  Aids for Fitting the Gamma Distribution by Maximum Likelihood , 1960 .

[10]  Francisco Cribari-Neto,et al.  Nearly Unbiased Maximum Likelihood Estimation for the Beta Distribution , 2002 .

[11]  J. Stedinger.  Frequency analysis of extreme events , 1993 .

[12]  Francisco Cribari-Neto,et al.  Bias-corrected maximum likelihood estimation for the beta distribution , 1997 .

[13]  H. Brehm,et al.  Description and generation of spherically invariant speech-model signals , 1987 .

[14]  B. Efron,et al.  The Jackknife: The Bootstrap and Other Resampling Plans. , 1983 .

[15]  Rainer Martin,et al.  Speech enhancement using MMSE short time spectral estimation with gamma distributed speech priors , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[16]  W. D. Ray.  Maximum likelihood estimation in small samples , 1977 .

[17]  M. Bartlett,et al.  APPROXIMATE CONFIDENCE INTERVALSMORE THAN ONE UNKNOWN PARAMETER , 1953 .

[18]  D. G. Chapman,et al.  Estimating the Parameters of a Truncated Gamma Distribution , 1956 .

[19]  Lawrence M Wein,et al.  Using fingerprint image quality to improve the identification performance of the U.S. Visitor and Immigrant Status Indicator Technology Program. , 2005, Proceedings of the National Academy of Sciences of the United States of America.

[20]  D. Firth.  Bias reduction of maximum likelihood estimates , 1993 .

[21]  S. C.,et al.  A NOTE ON THE GAMMA DISTRIBUTION , 1958 .

[22]  S. C. Choi,et al.  Maximum Likelihood Estimation of the Parameters of the Gamma Distribution and Their Bias , 1969 .

[23]  M. Bartlett,et al.  APPROXIMATE CONFIDENCE INTERVALS , 1953 .

[24]  D. Stoney.  Distribution of epidermal ridge minutiae , 1988 .

[25]  P. K. Bhunya,et al.  Suitability of Gamma, Chi-square, Weibull, and Beta distributions as synthetic unit hydrographs , 2007 .

[26]  R. Fisher,et al.  On the Mathematical Foundations of Theoretical Statistics , 1922 .

[27]  K. Pearson.  Contributions to the Mathematical Theory of Evolution , 1894 .

[28]  L. R. Shenton,et al.  Properties of Estimators for the Gamma Distribution , 1987 .

[29]  Des Raj.  Estimation of the Parameters of Type III Populations from Truncated Samples , 1953 .

[30]  Richard Heusdens,et al.  A STUDY OF THE DISTRIBUTION OF TIME-DOMAIN SPEECH SAMPLES AND DISCRETE FOURIER COEFFICIENTS , 2005 .

[31]  S. Gupta.  Gamma Distribution in Acceptance Sampling Based on Life Tests , 1961 .

[32]  Albert H. Moore,et al.  Maximum-Likelihood Estimation of the Parameters of Gamma and Weibull Populations from Complete and from Censored Samples , 1965 .

[33]  J. Haldane,et al.  THE SAMPLING DISTRIBUTION OF A MAXIMUM-LIKELIHOOD ESTIMATE , 1956 .

[34]  Richard M. Stern,et al.  Robust signal-to-noise ratio estimation based on waveform amplitude distribution analysis , 2008, INTERSPEECH.

[35]  L. Shenton,et al.  REMARKS ON THOM'S ESTIMATORS FOR THE GAMMA DISTRIBUTION , 1970 .

[36]  SMALL SAMPLE PROPERTIES OF ESTIMATORS FOR THE GAMMA DISTRIBUTION. , 1970 .

[37]  H. Aksoy.  Use of Gamma Distribution in Hydrological Analysis , 2000 .

[38]  Joanne Simpson,et al.  USE OF THE GAMMA DISTRIBUTION IN SINGLE-CLOUD RAINFALL ANALYSIS , 1972 .

[39]  Gauss M. Cordeiro,et al.  Bias correction in ARMA models , 1994 .

[40]  L. R. Shenton,et al.  The bias of moment estimators with an application to the negative binomial distribution , 1962 .

[41]  S. C. Saunders,et al.  A Statistical Model for Life-Length of Materials , 1958 .

[42]  A. C. Cohen.  Estimating Parameters of Pearson Type Iii Populations from Truncated Samples , 1950 .

[43]  L. R. Shenton,et al.  Further Remarks on Maximum Likelihood Estimators for the Gamma Distribution , 1972 .

[44]  The maximum likelihood estimators of the parameters of the gamma distribution are always positively biased , 1981 .

[45]  Ashutosh Kumar Singh,et al.  Properties of Estimators for the Gamma Distribution , 1990 .

[46]  S. Yue,et al.  A review of bivariate gamma distributions for hydrological application , 2001 .