Uncertainty bounds for parameter identification with small sample sizes

Consider the problem of determining uncertainty bounds for an M-estimate of a parameter vector from (generally) non-i.i.d. data (M-estimates are those obtained as the solution of a set of equations; maximum likelihood estimates are perhaps the most common type). Calculating uncertainty bounds requires information about the distribution of the estimate. It is well known that M-estimates typically have an asymptotic normal distribution. However, because of their generally complex nonlinear (and implicitly defined) structure, very little is usually known about the finite-sample distribution. This paper presents a method for characterizing the distribution of an M-estimate when the sample size is small. The approach works by comparing the actual (unknown) distribution of the estimate with a closely related known distribution. Some discussion and analysis are included that compare the approach here with the well-known bootstrap and saddlepoint methods. Theoretical justification and an illustration of the approach in a signal-plus-noise estimation problem are presented. This illustrative problem arises in many contexts, including random effects modeling ("unbalanced" case), the problem of combining several independent estimates, Kalman filter-based modeling, small area survey analysis, and quantile calculation for projectile accuracy analysis.

[1]  W. G. Cochran.  The combination of estimates from different experiments. , 1954 .

[2]  H. Daniels.  Saddlepoint Approximations in Statistics , 1954 .

[3]  Calyampudi R. Rao,et al.  Linear statistical inference and its applications , 1965 .

[4]  Calyampudi R. Rao,et al.  Linear Statistical Inference and Its Applications. , 1975 .

[5]  R. Laha.  Probability Theory , 1979 .

[6]  S. Rice,et al.  Saddle point approximation for the distribution of the sum of independent random variables , 1980, Advances in Applied Probability.

[7]  R. Shumway,et al.  Estimation and tests of hypotheses for the initial mean and covariance in the kalman filter model , 1981 .

[8]  Jack Kaplan,et al.  Estimators for the One-Way Random Effects Model with Unequal Error Variances , 1981 .

[9]  Fang-Kuo Sun,et al.  A maximum likelihood algorithm for the mean and covariance of nonidentically distributed observations , 1982 .

[10]  J. Berger,et al.  Empirical Bayes Estimation of Rates in Longitudinal Studies , 1983 .

[11]  F. Graybill,et al.  Matrices with Applications in Statistics. , 1984 .

[12]  Richard H. Smith.  Maximum likelihood mean and covariance matrix estimation constrained to general positive semi-definiteness , 1985 .

[13]  Robert Tibshirani,et al.  Bootstrap Methods for Standard Errors, Confidence Intervals, and Other Measures of Statistical Accuracy , 1986 .

[14]  Nancy Reid,et al.  Saddlepoint Methods and Statistical Inference , 1988 .

[15]  Chris Field,et al.  Small sample confidence intervals , 1990 .

[16]  Elvezio Ronchetti,et al.  Small Sample Asymptotics , 1990 .

[17]  James C. Spall,et al.  First-order data sensitivity measures with applications to a multivariate signal-plus-noise problem , 1990 .

[18]  Saddlepoint Approximations in the Case of Intractable Cumulant Generating Functions , 1991 .

[19]  J. Ghosh.  Higher order asymptotics for the likelihood ratio, Rao's and Wald's tests , 1991 .

[20]  P. Hall.  The Bootstrap and Edgeworth Expansion , 1992 .

[21]  J. L. Maryak,et al.  A Feasible Bayesian Estimator of Quantiles for Projectile Accuracy From Non-iid Data , 1992 .

[22]  Matrix Weighting of Several Regression Coefficient Vectors , 1993 .

[23]  Ronald W. Butler,et al.  Saddlepoint Approximations to the CDF of Some Statistics with Nonnormal Limit Distributions , 1993 .

[24]  Jayanta K. Ghosh,et al.  Higher Order Asymptotics , 1994 .

[25]  Malay Ghosh,et al.  Small Area Estimation: An Appraisal , 1994 .

[26]  Elvezio Ronchetti,et al.  Empirical Saddlepoint Approximations for Multivariate M-estimators , 1994 .