Modeling lake-chemistry distributions: approximate Bayesian methods for estimating a finite-mixture model

A modification of the Laplace method is presented and applied to estimation of posterior functions in a Bayesian analysis of finite-mixture distributions. The technique is nonsequential yet relatively fast and provides estimates of mixture-model parameters and classification probabilities. The method is applied to a regional distribution of lake-chemistry data for north central Wisconsin. A mixture density of two lognormal populations is estimated for the acid-neutralizing capacity of lakes in the region, using several other lake characteristics as explanatory variables for classification into lake subpopulations. The fitted mixture model provides a good representation of the observed distribution. Separation into subpopulations based solely on the other lake characteristics matches the mixture-model classification relatively well.

[1]  L. Tierney,et al.  The validity of posterior expansions based on Laplace''s method , 1990 .

[2]  G J McLachlan,et al.  Mixture models for partially unclassified data: a case study of renal venous renin in hypertension. , 1989, Statistics in medicine.

[3]  L. Tierney,et al.  Fully Exponential Laplace Approximations to Expectations and Variances of Nonpositive Functions , 1989 .

[4]  W. J. Rose,et al.  Interrelationships among hydrologic-budget components of a northern Wisconsin seepage lake and implications for acid-deposition modeling , 1989 .

[5]  M J Small,et al.  Parametric distributions of regional lake chemistry: fitted and derived. , 1988, Environmental science & technology.

[6]  D. Landers,et al.  Eastern lake survey, regional estimates of lake chemistry. , 1988, Environmental science & technology.

[7]  J. Eilers,et al.  Chemical and physical characteristics of lakes in the upper Midwest, United States. , 1988, Environmental science & technology.

[8]  J. Eilers,et al.  Chemical and physical characteristics of lakes in the northeastern United States. , 1988, Environmental science & technology.

[9]  J. Bernardo,et al.  A Bayesian approach to cluster analysis , 1988 .

[10]  M. Small,et al.  A direct distribution model for regional aquatic acidification , 1986 .

[11]  A. F. Smith,et al.  Statistical analysis of finite mixture distributions , 1986 .

[12]  L. Tierney,et al.  Accurate Approximations for Posterior Moments and Marginal Densities , 1986 .

[13]  Jerald L. Schnoor,et al.  Lake resources at risk to acidic deposition in the Upper Midwest , 1986 .

[14]  Nikolaos Nikolaidis,et al.  Lake resources at risk to acidic deposition in the eastern United States , 1986 .

[15]  R. Newton,et al.  Chemical characteristics of Adirondack lakes. , 1985, Environmental science & technology.

[16]  Maximum Likelihood Estimates for the Parameters of Mixture Distributions , 1984 .

[17]  K. Webster,et al.  Hydrologic Control of Lake Susceptibility to Acidification , 1983 .

[18]  A. Cohen,et al.  Finite Mixture Distributions , 1982 .

[19]  Jery R. Stedinger,et al.  Fitting log normal distributions to hydrologic data , 1980 .

[20]  O. Barndorff-Nielsen,et al.  Models for non-Gaussian variation, with applications to turbulence , 1979, Proceedings of the Royal Society of London. A. Mathematical and Physical Sciences.

[21]  A. F. Smith,et al.  A Quasi‐Bayes Sequential Procedure for Mixtures , 1978 .

[22]  Ramanathan Gnanadesikan,et al.  Methods for statistical data analysis of multivariate observations , 1977, A Wiley publication in applied statistics.

[23]  M. Degroot,et al.  Probability and Statistics , 1977 .

[24]  O. Barndorff-Nielsen.  Exponentially decreasing distributions for the logarithm of particle size , 1977, Proceedings of the Royal Society of London. A. Mathematical and Physical Sciences.

[25]  D. M. Titterington,et al.  Updating a Diagnostic System using Unconfirmed Cases , 1976 .

[26]  Tzay Y. Young,et al.  Classification, Estimation and Pattern Recognition , 1974 .

[27]  S. Goldfeld,et al.  A Markov model for switching regressions , 1973 .

[28]  Stuart C. Schwartz,et al.  Analysis of a decision-directed receiver with unknown priors , 1970, IEEE Trans. Inf. Theory.

[29]  Claude Lepeltier.  A simplified statistical treatment of geochemical data by graphical representation , 1969 .

[30]  Bhattacharya Cg.  A simple method of resolution of a distribution into gaussian components. , 1967 .

[31]  C G Bhattacharya,et al.  A simple method of resolution of a distribution into gaussian components. , 1967, Biometrics.

[32]  Bruce M. Hill,et al.  The Three-Parameter Lognormal Distribution and Bayesian Analysis of a Point-Source Epidemic , 1963 .

[33]  H. Hartley.  Maximum Likelihood Estimation from Incomplete Data , 1958 .