Description Usage Arguments Value Author(s) References
Computes the Approximate Bayes Factor proposed by Wakefield (2009) for test statistics theta / sqrt(V)
that under the null hypothesis are assumed to follow an asymptotic standard normal distribution.
1 |
theta |
a vector of numeric values, e.g., the maximum likelihood estimates for the parameter of
a logistic regression model computed by separately applying this simple logistic regression to several SNPs.
It is thus assumed that under the null hypothesis |
V |
a vector of the same length as |
W |
the prior variance. Must be either a positive value or a vector of the same length as |
numerator |
either 0 or 1, specifying whether the numerator of the approximate Bayes factor comprises the probability for the null hypothesis or the probability for the alternative hypothesis. |
pi1 |
either a numeric value between 0 and 1 specifying the prior probability of association or a vector of the
same length as |
If pi1 = NA
, a vector of the same length as theta
containing the values of the approximate Bayes factor.
If pi1
is specified, a list consisting of
ABF |
a numeric vector containing the values of the approximate Bayes factors, |
priorOdds |
either a numeric value or a numeric vector comprising the prior odds of association (if |
postOdds |
a numeric vector containing the posterior odds of association (if |
and either
BFDP |
a numeric vector containing the Bayesian False Discovery Probabilities for the SNPs (if |
or
PPA |
a numeric vector comprising the posterior probabilities of association (if |
Holger Schwender, holger.schw@gmx.de
Wakefield, J. (2007). A Bayesian Measure of Probability of False Discovery in Genetic Epidemiology Studies. American Journal of Human Genetics, 81, 208-227.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.