AuthorArnold, Barry C. author
TitleConditionally Specified Distributions [electronic resource] / by Barry C. Arnold, Enrique Castillo, Josรฉ-Mariรก Sarabia
ImprintNew York, NY : Springer New York, 1992
Connect tohttp://dx.doi.org/10.1007/978-1-4612-2912-4
Descript XIV, 151 p. 1 illus. online resource

SUMMARY

The concept of conditional specification is not new. It is likely that earlier investigators in this area were deterred by computational difficulties encountered in the analysis of data following conยญ ditionally specified models. Readily available computing power has swept away that roadblock. A broad spectrum of new flexible models may now be added to the researcher's tool box. This monoยญ graph provides a preliminary guide to these models. Further development of inferential techniques, especially those involving concomitant variables, is clearly called for. We are grateful for invaluable assistance in the preparation of this monograph. In Riverside, Carole Arnold made needed changes in grammer and punctuation and Peggy Franklin miraculously transformed minute hieroglyphics into immaculate typescript. In Santander, Agustin Manrique exยญ pertly transformed rough sketches into clear diagrams. Finally, we thank the University of Cantabria for financial support which made possible Barry C. Arnold's enjoyable and productive visit to S- tander during the initial stages of the project. Barry C. Arnold Riverside, California USA Enrique Castillo Jose Maria Sarabia Santander, Cantabria Spain January, 1991 Contents 1 Conditional Specification 1 1.1 Why? ............. ........ . 1 1.2 How may one specify a bivariate distribution? 2 1.3 Early work on conditional specification 4 1.4 Organization of this monograph . . . . . . . . . . . . . . . . . . . . . . . . . . . .. 5 2 Basic Theorems 7 Compatible conditionals: The finite discrete case


CONTENT

1 Conditional Specification -- 1.1 Why? -- 1.2 How may one specify a bivariate distribution? -- 1.3 Early work on conditional specification -- 1.4 Organization of this monograph -- 2 Basic Theorems -- 2.1 Compatible conditionals: The finite discrete case -- 2.2Compatibility in more general settings -- 2.3Uniqueness -- 2.4 Conditionals in prescribed families -- 2.5 An example -- 3 Distributions with normal conditionals -- 3.1 Variations on the classical bivariate normal theme -- 3.2 Normal conditionals -- 3.3 Properties of the normal conditionals distribution -- 3.4 The centered model -- 4 Conditionals in Exponential Families -- 4.1 Introduction -- 4.2 Distributions with conditionals in given exponential families -- 4.3 Dependence in CEF distributions -- 4.4 Examples -- 5 Other conditionally specified families -- 5.1 Introduction -- 5.2 Bivariate Distributions with Pareto conditionals -- 5.3 Some extensions of the Pareto case -- 5.4 Bivariate distributions with Cauchy conditionals -- 5.5 Bivariate distributions with uniform conditionals -- 5.6 Possibly translated exponential conditionals -- 5.7 Bivariate distributions with scaled beta conditionals -- 5.8 Weibull and logistic conditionals -- 5.9 Mixtures -- 6 Impossible Models -- 6.1 Introduction -- 6.2 Logistic Regression -- 6.3 Uniform conditionals -- 6.4 Exponential and Weibull conditionals -- 6.5 Measurement error models -- 6.6 Stochastic processes and Wohler fields -- 6.6.1 The Gumbel-Gumbel model -- 6.6.2 The Wei bull-Weibull model -- 7 Characterizations involving conditional moments -- 7.1 Introduction -- 7.2 Mardiaโs bivariate Pareto distribution -- 7.3Linear regressions with conditionals in exponential families -- 7.4Linear regressions with conditionals in location families -- 7.5Specified regressions with conditionals in scale families -- 7.6 Conditionals in location-scale families with specified moments -- 8 Multivariate extensions -- 8.1 Extension by underlining -- 8.2 Compatibility in 3 dimensions -- 8.3 Conditionals in prescribed families -- 8.4 Conditionals in exponential families -- 8.5 Examples -- 8.6 Further extension by underlining -- 9 Parameter estimation in conditionally specified models -- 9.1 The ubiquitous norming constant -- 9.2 Maximum likelihood -- 9.3 Pseudolikelihood involving conditional densities -- 9.4 Marginal likelihood -- 9.5 An efficiency comparison -- 9.6 Method of moments estimates -- 9.7 Bayesian estimates -- 10 Simulations -- 10.1 Introduction -- 10.2 The rejection method -- 10.3 Application to models with conditionals in exponential families -- 10.4 Other conditionally specified models -- 10.5 A direct approach not involving rejection -- 11 Bibliographic Notes -- 11.1 Introduction -- 11.2 Basic theorems -- 11.3 Distributions with normal conditionals -- 11.4 Conditionals in exponential families -- 11.5 Other conditionally specified Families -- 11.6 Impossible models -- 11.7 Characterizations involving conditional moments -- 11.8 Multivariate extensions -- 11.9 Parameter estimation in conditionally specified models -- 11.10 Simulations


SUBJECT

  1. Mathematics
  2. Functional analysis
  3. Probabilities
  4. Statistics
  5. Mathematics
  6. Functional Analysis
  7. Statistics
  8. general
  9. Probability Theory and Stochastic Processes