The MCMC Procedure

 
Standard Distributions

The section Univariate Distributions (Table 54.7 through Table 54.34) lists all univariate distributions that PROC MCMC recognizes. The section Multivariate Distributions (Table 54.35 through Table 54.38) lists all multivariate distributions that PROC MCMC recognizes. With the exception of the multinomial distribution, all these distributions can be used in the MODEL, PRIOR, and HYPERPRIOR statements. The multinomial distribution is supported only in the MODEL statement. The RANDOM statement supports a limited number of distributions; see Table 54.4 for the complete list.

See the section Using Density Functions in the Programming Statements for information about how to use distributions in the programming statements. To specify an arbitrary distribution, you can use the GENERAL and DGENERAL functions. See the section Specifying a New Distribution for more details. See the section Truncation and Censoring for tips about how to work with truncated distributions and censoring data.

Univariate Distributions

Table 54.7 Beta Distribution

PROC specification

beta(, )

Density

Parameter restriction

,

Range

Mean

Variance

Mode

Random number

If , see (Cheng; 1978); if , see (Atkinson and Whittaker; 1976) and (Atkinson; 1979); if and , see (Cheng; 1978); if or , use the inversion method; if , use a uniform random number generator.

Table 54.8 Binary Distribution

PROC specification

binary()

Density

Parameter restriction

Range

Mean

round

Variance

Mode

Random number

Generate . If , ; else,

Table 54.9 Binomial Distribution

PROC specification

binomial(, )

Density

Parameter restriction

Range

Mean

Variance

Mode

Table 54.10 Cauchy Distribution

PROC specification

cauchy(, )

Density

Parameter restriction

Range

Mean

Does not exist.

Variance

Does not exist.

Mode

Random number

Generate ; let . Repeat the procedure until . is a draw from the standard Cauchy, and (Ripley; 1987).

Table 54.11 Distribution

PROC specification

chisq()

Density

Parameter restriction

Range

if ; otherwise.

Mean

Variance

Mode

if ; does not exist otherwise.

Random number

is a special case of the gamma distribution: is a draw from the distribution.

Table 54.12 Exponential Distribution

PROC specification

expchisq()

Density

Parameter restriction

Range

Mode

Random number

Generate , and is a draw from the exponential distribution.

Relationship to the distribution

Table 54.13 Exponential Exponential Distribution

PROC specification

expexpon(scale = )

expexpon(iscale = )

Density

Parameter restriction

Range

Same

Mode

Random number

Generate , and is a draw from the exponential exponential distribution. Note that an exponential exponential distribution is not the same as the double exponential distribution.

Relationship to the exponential distribution

Table 54.14 Exponential Gamma Distribution

PROC specification

expgamma(, scale = )

expgamma(, iscale = )

Density

Parameter restriction

Range

Same

Mode

Random number

Generate , and is a draw from the exponential gamma distribution.

Relationship to the distribution

Table 54.15 Exponential Inverse Distribution

PROC specification

expichisq()

Density

Parameter restriction

Range

Mode

Random number

Generate , and is a draw from the exponential inverse distribution.

Relationship to the distribution

Table 54.16 Exponential Inverse-Gamma Distribution

PROC specification

expigamma(, scale = )

expigamma(, iscale = )

Density

Parameter restriction

Range

Same

Mode

Random number

Generate , and is a draw from the exponential inverse-gamma distribution.

Relationship to the distribution

Table 54.17 Exponential Scaled Inverse Distribution

PROC specification

expsichisq(, )

Density

Parameter restriction

Range

Mode

Random number

Generate , and is a draw from the exponential scaled inverse distribution.

Relationship to the distribution

Table 54.18 Exponential Distribution

PROC specification

expon(scale = )

expon(iscale = )

Density

Parameter restriction

Range

Same

Mean

Variance

Mode

Random number

The exponential distribution is a special case of the gamma distribution: is a draw from the exponential distribution.

Table 54.19 Gamma Distribution

PROC specification

gamma(, scale = )

gamma(, iscale = )

Density

Parameter restriction

Range

if otherwise.

Same

Mean

Variance

Mode

if

if

Random number

See (McGrath and Irving; 1973).

Table 54.20 Geometric Distribution

PROC specification

geo()

Density 1

Parameter restriction

Range

Mean

round()

Variance

Mode

Random number

Based on samples obtained from a Bernoulli distribution with probability until the first success.

Table 54.21 Inverse Distribution

PROC specification

ichisq()

Density

Parameter restriction

Range

Mean

if

Variance

if

Mode

Random number

Inverse is a special case of the inverse-gamma distribution: is a draw from the inverse distribution.

Table 54.22 Inverse-Gamma Distribution

PROC specification

igamma(, scale = )

igamma(, iscale = )

Density

Parameter restriction

Range

Same

Mean

if

if

Variance

Mode

Random number

Generate , and is a draw from the distribution.

Relationship to the gamma distribution

Table 54.23 Laplace (Double Exponential) Distribution

PROC specification

laplace(, scale = )

laplace(, iscale = )

Density

Parameter restriction

Range

Same

Mean

Variance

Mode

Random number

Inverse CDF.
Generate . If else . is a draw from the Laplace distribution.

Table 54.24 Logistic Distribution

PROC specification

logistic(, )

Density

Parameter restriction

Range

Mean

Variance

Mode

Random number

Inverse CDF method with . Generate , and is a draw from the logistic distribution.

Table 54.25 Lognormal Distribution

PROC specification

lognormal(, sd = )

lognormal(, var = )

lognormal(, prec = )

Density

Parameter restriction

Range

Same

Same

Mean

Variance

Mode

Random number

Generate , and is a draw from the lognormal distribution.

Table 54.26 Negative Binomial Distribution

PROC specification

negbin(, )

Density

Parameter restriction

Range

Mean

round

Variance

Mode

Random number

Generate , and (Fishman; 1996).

Table 54.27 Normal Distribution

PROC specification

normal(, sd = )

normal(, var = )

normal(, prec = )

Density

Parameter restriction

Range

Same

Same

Mean

Same

Same

Variance

Mode

Same

Same

Table 54.28 Pareto Distribution

PROC specification

pareto(, )

Density

Parameter restriction

Range

Mean

if

Variance

if

Mode

Random number

Inverse CDF method with . Generate , and is a draw from the Pareto distribution.

Useful transformation

is Beta(, 1)I{}.

Table 54.29 Poisson Distribution

PROC specification

poisson()

Density

Parameter restriction

Range

Mean

Variance

, if

Mode

round

Table 54.30 Scaled Inverse Distribution

PROC specification

sichisq()

Density

Parameter restriction

Range

Mean

if

Variance

if

Mode

Random number

Scaled inverse is a special case of the inverse-gamma distribution: is a draw from the scaled inverse distribution.

Table 54.31 t Distribution

PROC specification

t(, sd = , )

t(, var = , )

t(, prec = , )

Density

Parm restriction

,

,

,

Range

Same

Same

Mean

if

Same

Same

Variance

if

if

if

Mode

Same

Same

Random number

is a draw from the t distribution.

Table 54.32 Uniform Distribution

PROC specification

uniform(, )

Density

Parameter restriction

none

Range

Mean

Variance

Mode

Does not exist

Random number

Mersenne Twister (Matsumoto and Kurita; 1992, 1994; Matsumoto and Nishimura; 1998)

Table 54.33 Wald Distribution

PROC specification

wald(, )

Density

Parameter restriction

Range

Mean

Variance

Mode

Random number

Generate . Let and . Perform a Bernoulli trial, . If , choose ; otherwise, choose (Michael, Schucany, and Haas; 1976).

Table 54.34 Weibull Distribution

PROC specification

weibull(, , )

Density

Parameter restriction

Range

if otherwise

Mean

Variance

Mode

if

Random number

Inverse CDF method with . Generate , and is a draw from the Weibull distribution.

Multivariate Distributions

Table 54.35 Dirichlet Distribution

PROC specification

dirich(), where , for

Density

, where

Parameter restriction

Range

,

Mean

Mode

Table 54.36 Inverse Wishart Distribution

PROC specification

iwishart(, ), both and are matrics

Density

Parameter restriction

must be symmetric and positive definte;

Range

is symmetric and positive definite

Mean

Mode

Table 54.37 Multivariate Normal Distribution

PROC specification

mvn(, ), where , for , and is a variance matrix

Density

Parameter restriction

must be symmetric and positive definite

Range

Mean

Mode

Table 54.38 Multinomial Distribution

PROC specification

multinom(), where and , for

Density

, where

Parameter restriction

with all

Range

, nonnegative integers

Mean