haplo.score.podds: Compute Haplotype Score Statistics for Ordinal Traits with
Proportional Odds Model
Description
This function is used by haplo.score when analyzing ordinal traits
by a proportional odds model score statistic.Usage
haplo.score.podds(y, alpha, beta=NA, x.adj=NA, nreps, x.post, post, x)
Arguments
y
Vector of ordinal trait values.
alpha
Intercept parameters for ordinal logistic regression model.
beta
Regression parameters for adjusted covariates (x.adj).
x.adj
Matrix of non-genetic covariates used to adjust the
score statistics. Note that intercept should NOT be included
in this matrix.
nreps
Vector for the count of haplotype pairs that map to
each subject's marker genotypes (see haplo.em).
x.post
Matrix for posterior mean of x per subject.
post
Vector of posterior probabilities of pairs of
haplotypes for a person, given thier marker phenotypes
(see haplo.em).
x
Matrix of scores for enumerated haplotypes for each
subject, with elements 0, 1, 2 (counts of specific
haplotypes).
Value
- List with components:
- u.scoreVector of scores for the chosen haplotypes
- v.scoreCovariance matrix for u.score
Warning
To analyze an ordinal trait with adjustment for x.adj
covariates, the user will need to have Frank Harrell's librarys
(Design and Hmisc). However, the unadjusted ordinal trait works fine
without these libraries.References
Schaid DJ, Rowland CM, Tines DE, Jacobson RM, Poland GA.
Score tests for association of traits with haplotypes when
linkage phase is ambiguous. Submitted to Amer J Hum Genet.Details
Using posterior probabilities of pairs of haplotypes, the
"design" matrix for the haplotype effects, and the proportional odds model, compute the score vector and its variance
matrix, adjusted for the non-genetic covariates.