rpt_rhythmicity_new: Likelihood-based Test for Detecting Circadian Pattern with...

In RepeatedCircadian/RepeatedCircadian: An R package for circadian and differential circadian analysis with repeated measurement

Likelihood-based Test for Detecting Circadian Pattern with Repeated Measurement.

Description

Likelihood-based test for circadian pattern detection with repeated measurement.

Usage

rpt_rhythmicity_new(data, period = 24, type = "int", method = "LR", cov = NULL)

Arguments

data	A data set with columns: y (gene expression value), t (circadian time), id (subjects IDs) and optional additional covariates.
period	Period of the since curve. Default is 24.
type	Types of testing model. 'lm' for linear model, 'int' for mixed model with random intercept only and 'slope' for mixed model with random slope. Default is 'int'.
method	Testing methods can be "LR" or "F". Default is "LR".
cov	Optional vector of additional covariates adding to model fitting (e.g. cov=c('age','gender')). Default is NULL.

Details

Test the significance of circadian curve fitting using mixed model with random intercept and likelihood-based test.

Value

A list of test statistic, pvalue and parameter estimates. Formula 1: yy = amp * sin(2π/period * (phase + tt)) + offset Formula 2: yy = A * sin(2π/period * tt) + B * cos(2*π/period * tt) + offset

stat	Test statistic.
pvalue	P-value from the test.
A	Amplitude estimate.
phi	Phase estimate.
basal	Basal level estimate.
sigma_null	Standard deviation for the null model under linear model setting (type='lm').
sigma_alt	Standard deviation for the alternative model unde linear model setting (type='lm').
sigma_0	Standard deviation for the fixed part of intercept under random intercept or random slope setting (type='int' or 'slope').
sigma_alpha	Standard deviation for the random part of intercept under random intercept or random slope setting (type='int' or 'slope').
coefficients	Coefficient table of fitted model.

Author(s)

Haocheng Ding, Zhiguang Huo

Examples

Example 1

library(MASS)
set.seed(32611)
m <- 10
n <- 12
id <- rep(1:n,each=m)
rho <- 0.2
offset <- runif(1,0,3)
sigmaMat <- ifelse(diag(m)==1,1,rho)
tt <- rep(runif(m,0,24),n)
yy <- as.vector(t(mvrnorm(n,rep(offset,m),sigmaMat)))
group <- factor(rep(c('A','B'),each=60),levels = c('A','B'))
age <- rep(sample(20:80,n,replace = T),each=m)
data <- data.frame(y=yy,t=tt,id=id,group=group,age=age)
rpt_rhythmicity_new(data, period=24, type='int', method="LR", cov=NULL)

Example 2

library(MASS)
set.seed(32611)
m <- 10
n <- 12
id <- rep(1:n,each=m)
rho <- 0.2
amp <- 1
phase <- 3
offset <- runif(1,0,3)
sigmaMat <- ifelse(diag(m)==1,1,rho)
t <- runif(m,0,24)
tt <- rep(t,n)
yy <- as.vector(t(mvrnorm(n,amp*sin(2*pi/24*(phase+t))+offset,sigmaMat)))
group <- factor(rep(c('A','B'),each=60),levels = c('A','B'))
age <- rep(sample(20:80,n,replace = T),each=m)
data <- data.frame(y=yy,t=tt,id=id,group=group,age=age)
rpt_rhythmicity_new(data, type='int', period=24, method="LR",cov=c('group','age'))

RepeatedCircadian/RepeatedCircadian documentation built on Jan. 4, 2023, 11:11 p.m.