setModel {polySegratioMM}

Set characteristics of the Bayesian mixture model for dosages

Description

Used to automatically set up Bayesian finite mixture models for dosage allocation of dominant markers in autopolyploids given the number of components and ploidy level

Usage

setModel(n.components, ploidy.level, random.effect = FALSE, seg.ratios =NULL,
 ploidy.name = NULL, equal.variances=TRUE, 
 type.parents = c("heterogeneous", "homozygous"))

Arguments

n.components

number of components for mixture model (less than or equal to maximum number of possible dosages)

ploidy.level

the number of homologous chromosomes, either as numeric or as a character string

random.effect

Logical indicating whether model contains random effect (Default: FALSE)

seg.ratios

segregation proportions for each marker provided as S3 class segRatio

ploidy.name

Can overide ploidy name here or allow it to be determined from ploidy.level

equal.variances

Logical indicating whether model contains separate or common variances for each component (Default: TRUE)

type.parents

"heterogeneous" if parental markers are 0,1 or "homogeneous" if parental markers are both 1

Value

Returns object of class modelSegratioMM with components

bugs.code

text to be used by JAGS in the .bug file but without statements pertaining to priors

n.components

number of components for mixture model

monitor.var

names of variables to be monitored in JAGS run

ploidy.level

ploidy level

random.effect

Logical indicating whether model contains random effect (Default: FALSE)

equal.variances

Logical indicating equal or separate variances for each component

E.segRatio

Expected segregation ratios

type.parents

"heterogeneous" if parental markers are 0,1 or "homogeneous" if parental markers are both 1

call

function call

Author(s)

Peter Baker [e-mail]

See Also

setPriors setInits expected.segRatio segRatio setControl dumpData dumpInits or for an easier way to run a segregation ratio mixture model see runSegratioMM

Examples

## simulate small autooctaploid data set
a1 <- sim.autoMarkers(8,c(0.7,0.2,0.1),n.markers=100,n.individuals=50)

## set up model with 3 components
x <- setModel(3,8)
print(x)