| Title: | Familial Recurrence Risk |
|---|---|
| Description: | Given vectors of family sizes and number of affecteds per family, calculates the risk of disease recurrence in an unaffected person, conditional on a family having at least k affected members. Methods also model heterogeneity of disease risk across families by fitting a mixture model, allowing for high and low risk families. |
| Authors: | Schaid Daniel [aut], Jason Sinnwell [aut, cre] |
| Maintainer: | Jason Sinnwell <[email protected]> |
| License: | GPL (>= 2) |
| Version: | 0.1 |
| Built: | 2024-09-11 03:20:41 UTC |
| Source: | https://github.com/cran/fam.recrisk |
Given vectors of family sizes and number of affecteds per family, calculates the risk of disease recurrence
fam.recrisk(s, a, k)fam.recrisk(s, a, k)
s |
vector of sizes of families |
a |
vector of number of affected members per family; same length as vector s |
k |
number of affecteds to condition on; the ascertainment criterion, e.g., at least k affecteds |
Estimate risk of disease for a person with at least k affected relatives, where k can be specified in order to determine how risk varies with k. Estimates are based on a truncated binomial distribution where families with less than k affected relatives are truncated from the sample. If the sample of families in not a random sample from a population, the prevalence will be biased, and merely represent the frequency of disease in the sample.
A list with the following values
phat |
disease recurrence risk |
prev |
estimate of disease prevalence |
var.phat |
variance of phat |
var.prev |
variance of prev |
covar |
covariance between phat and prev |
Schaid DJ, Sinnwell JP.
Schaid DJ, McDonnell SK, Thibodeau SN. Familial recurrence risk with varying amount of family history. Under review at Genetic Epidemiology, 2018.
s <- c(4, 8, 6, 6, 10, 8, 7, 8, 5, 6, 10, 4, 4, 8, 6, 8, 4, 5, 9, 9, 5, 4, 4, 7, 3, 3, 9, 5, 3, 3, 4, 6, 8, 3, 5, 8, 6, 8, 9, 3) a <- c(3, 4, 2, 5, 4, 5, 3, 4, 3, 3, 8, 2, 0, 3, 4, 5, 2, 3, 4, 2, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 1, 0, 2, 0, 0, 1, 0, 2, 3, 0) fam.recrisk(s,a,1)s <- c(4, 8, 6, 6, 10, 8, 7, 8, 5, 6, 10, 4, 4, 8, 6, 8, 4, 5, 9, 9, 5, 4, 4, 7, 3, 3, 9, 5, 3, 3, 4, 6, 8, 3, 5, 8, 6, 8, 9, 3) a <- c(3, 4, 2, 5, 4, 5, 3, 4, 3, 3, 8, 2, 0, 3, 4, 5, 2, 3, 4, 2, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 1, 0, 2, 0, 0, 1, 0, 2, 3, 0) fam.recrisk(s,a,1)
Recurrence risk assuming a mixture of low and high risk families based on a mixture of truncated binomial densities
recrisk.mixture(s, a, k, max.iter=1e4, eps=1e-6)recrisk.mixture(s, a, k, max.iter=1e4, eps=1e-6)
s |
vector of sizes of families |
a |
vector of number of affected members per family; same length as vector s |
k |
number of affecteds to condition on; the ascertainment criterion, e.g., at least k affecteds |
max.iter |
maximum number of EM iterations |
eps |
EM stop criterion value |
Model heterogeneity of risk across families by a mixture of truncated binomial distributions, assuming two groups: high and low risk.
A list with the following values
recrisk.high |
disease recurrence risk for high-risk group |
recrisk.low |
disease recurrence risk for low-risk group |
prob.high.group |
the mixture probability that a familiy is in the high-risk group (a scalar value) |
prob.fam.high |
a vector of posterior probabilities that families are in the high-risk group (same length as vector s) |
iter |
Number of EM iterations |
Schaid DJ, Sinnwell JP.
Schaid DJ, McDonnell SK, Thibodeau SN. Familial recurrence risk with varying amount of family history. Under review at Genetic Epidemiology, 2018.
s <- c(4, 8, 6, 6, 10, 8, 7, 8, 5, 6, 10, 4, 4, 8, 6, 8, 4, 5, 9, 9, 5, 4, 4, 7, 3, 3, 9, 5, 3, 3, 4, 6, 8, 3, 5, 8, 6, 8, 9, 3) a <- c(3, 4, 2, 5, 4, 5, 3, 4, 3, 3, 8, 2, 0, 3, 4, 5, 2, 3, 4, 2, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 1, 0, 2, 0, 0, 1, 0, 2, 3, 0) recrisk.mixture(s,a,k=1)s <- c(4, 8, 6, 6, 10, 8, 7, 8, 5, 6, 10, 4, 4, 8, 6, 8, 4, 5, 9, 9, 5, 4, 4, 7, 3, 3, 9, 5, 3, 3, 4, 6, 8, 3, 5, 8, 6, 8, 9, 3) a <- c(3, 4, 2, 5, 4, 5, 3, 4, 3, 3, 8, 2, 0, 3, 4, 5, 2, 3, 4, 2, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 1, 0, 2, 0, 0, 1, 0, 2, 3, 0) recrisk.mixture(s,a,k=1)
Estimate the recurrence risk ratio of familial recurrence risk divided by population prevalence, based on results returned from fam.recrisk
recrisk.ratio(fit)recrisk.ratio(fit)
fit |
list returned from fam.recrisk |
The recurrence risk is based on a truncated binomial density, and the prevalence is the frequency of disease in the sample. If the sample of families in not a random sample from a population, the prevalence will be biased, and merely represent the frequency of disease in the sample.
A list with the following values
rr |
ratio of recurrence risk divided by population prevalence |
var.rr |
variance of rr |
Schaid DJ, Sinnwell JP.
Schaid DJ, McDonnell SK, Thibodeau SN. Familial recurrence risk with varying amount of family history. Under review at Genetic Epidemiology, 2018.
s <- c(4, 8, 6, 6, 10, 8, 7, 8, 5, 6, 10, 4, 4, 8, 6, 8, 4, 5, 9, 9, 5, 4, 4, 7, 3, 3, 9, 5, 3, 3, 4, 6, 8, 3, 5, 8, 6, 8, 9, 3) a <- c(3, 4, 2, 5, 4, 5, 3, 4, 3, 3, 8, 2, 0, 3, 4, 5, 2, 3, 4, 2, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 1, 0, 2, 0, 0, 1, 0, 2, 3, 0) fit <- fam.recrisk(s,a,1) recrisk.ratio(fit)s <- c(4, 8, 6, 6, 10, 8, 7, 8, 5, 6, 10, 4, 4, 8, 6, 8, 4, 5, 9, 9, 5, 4, 4, 7, 3, 3, 9, 5, 3, 3, 4, 6, 8, 3, 5, 8, 6, 8, 9, 3) a <- c(3, 4, 2, 5, 4, 5, 3, 4, 3, 3, 8, 2, 0, 3, 4, 5, 2, 3, 4, 2, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 1, 0, 2, 0, 0, 1, 0, 2, 3, 0) fit <- fam.recrisk(s,a,1) recrisk.ratio(fit)
Estimate familial recurrence risk, assuming there is a single identified proband in a family
recrisk.single.ascertain(s, a)recrisk.single.ascertain(s, a)
s |
vector of sizes of families |
a |
vector of number of affected members |
When affected subjects (i.e., probands) attend a clinic independent of their family size and independent of their family history, and if the family history provided by probands is complete (i.e., reporting of family history does not depend on the number of affected members), then we can view the probands and their families as sampled under complete ascertainment. This function estimates the disease recurrence risk when there is a single identified proband per family.
A list with the following values
phat |
disease recurrence risk |
var.phat |
variance of phat |
Schaid DJ, Sinnwell JP.
Schaid DJ, McDonnell SK, Thibodeau SN. Familial recurrence risk with varying amount of family history. Under review at Genetic Epidemiology, 2018.
s <- c(4, 8, 6, 6, 10, 8, 7, 8, 5, 6, 10, 4, 4, 8, 6, 8, 4, 5, 9, 9, 5, 4, 4, 7, 3, 3, 9, 5, 3, 3, 4, 6, 8, 3, 5, 8, 6, 8, 9, 3) a <- c(3, 4, 2, 5, 4, 5, 3, 4, 3, 3, 8, 2, 0, 3, 4, 5, 2, 3, 4, 2, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 1, 0, 2, 0, 0, 1, 0, 2, 3, 0) recrisk.single.ascertain(s,a)s <- c(4, 8, 6, 6, 10, 8, 7, 8, 5, 6, 10, 4, 4, 8, 6, 8, 4, 5, 9, 9, 5, 4, 4, 7, 3, 3, 9, 5, 3, 3, 4, 6, 8, 3, 5, 8, 6, 8, 9, 3) a <- c(3, 4, 2, 5, 4, 5, 3, 4, 3, 3, 8, 2, 0, 3, 4, 5, 2, 3, 4, 2, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 1, 0, 2, 0, 0, 1, 0, 2, 3, 0) recrisk.single.ascertain(s,a)