Prior distribution elicitation for generalized linear and piecewise-linear models

An elicitation method is proposed for quantifying subjective opinion about the regression coefficients of a generalized linear model. Opinion between a continuous predictor variable and the dependent variable is modelled by a piecewise-linear function, giving a flexible model that can represent a wide variety of opinion. To quantify his or her opinions, the expert uses an interactive computer program, performing assessment tasks that involve drawing graphs and bar-charts to specify medians and other quantiles. Opinion about the regression coefficients is represented by a multivariate normal distribution whose parameters are determined from the assessments. It is practical to use the procedure with models containing a large number of parameters. This is illustrated through practical examples and the benefit from using prior knowledge is examined through cross-validation.

[1]  A. O'Hagan,et al.  Statistical Methods for Eliciting Probability Distributions , 2005 .

[2]  J. Kadane,et al.  Using Statistical Regressions to Identify Factors Influencing PM2.5 Concentrations: The Pittsburgh Supersite as a Case Study , 2010 .

[3]  Wayne S. Smith,et al.  Interactive Elicitation of Opinion for a Normal Linear Model , 1980 .

[4]  Anthony O'Hagan,et al.  Eliciting expert beliefs in substantial practical applications , 1998 .

[5]  Mary Kynn,et al.  Eliciting Expert Knowledge for Bayesian Logistic Regression in Species Habitat Modelling , 2005 .

[6]  N. Bingham,et al.  Generalised Linear Models , 2010 .

[7]  Paul H. Garthwaite,et al.  Elicitation of Prior Distributions for Variable-Selection Problems in Regression , 1992 .

[8]  R. Christensen,et al.  A New Perspective on Priors for Generalized Linear Models , 1996 .

[9]  R. Cooke.  Experts in Uncertainty: Opinion and Subjective Probability in Science , 1991 .

[10]  Robert K. Tsutakawa,et al.  Estimation of Two-Parameter Logistic Item Response Curves , 1984 .

[11]  Fadlalla Ghaly Hassan Mohamed Elfadaly,et al.  Elicitation of Subjective Probability Distributions , 2012 .

[12]  Paul Tappenden,et al.  Use of expert knowledge in evaluating costs and benefits of alternative service provisions: A case study , 2008, International Journal of Technology Assessment in Health Care.

[13]  Michael Goldstein,et al.  Constructing partial prior specifications for models of complex physical systems , 1998 .

[14]  Kerrie Mengersen,et al.  Geographically Assisted Elicitation of Expert Opinion for Regression Models , 2007 .

[15]  Paul H. Garthwaite,et al.  Double- and single-bisection methods for subjective probability assessment in a location-scale family , 1985 .

[16]  Veronica Czitrom,et al.  One-Factor-at-a-Time versus Designed Experiments , 1999 .

[17]  Samuel D. Oman,et al.  Specifying a Prior Distribution in Structured Regression Problems , 1985 .

[18]  Paul H. Garthwaite,et al.  Quantifying expert opinion for modelling fauna habitat distributions , 2006, Comput. Stat..

[19]  B. Fischhoff,et al.  Calibration of probabilities: the state of the art to 1980 , 1982 .

[20]  J. Kadane,et al.  Experiences in elicitation , 1998 .

[21]  J. Ibrahim,et al.  Prior elicitation, variable selection and Bayesian computation for logistic regression models , 1999 .

[22]  George P. Huber,et al.  METHODS FOR QUANTIFYING SUBJECTIVE PROBABILITIES AND MULTI‐ATTRIBUTE UTILITIES*† , 1974 .

[23]  Paul H. Garthwaite,et al.  Quantifying Expert Opinion in Linear Regression Problems , 1988 .

[24]  Jeremy E. Oakley,et al.  Uncertain Judgements: Eliciting Experts' Probabilities , 2006 .