View source: R/simulate_ptglmm.R
simulate_ptglmm | R Documentation |
Simulates a dataset comprising t repeated measurements for n subjects from a Poisson-Tweedie GLMM. Subjects are assumed to belong to two different groups. The linear predictor comprises an intercept, main effects of group and of time, and the interaction between time and group; a random intercept; and, optionally, a normally-distributed offset term.
simulate_ptglmm(n = 20, t = 5, seed = 1, beta = c(3, 0, 0, 0.4), D = 1.5, a = -1, sigma2 = 0.8^2, offset = F)
n |
number of subjects |
t |
number of time points (0, 1, ..., t-1) |
seed |
seed for random number generation |
beta |
vector of regression coefficients, to be specified in this order: intercept, group main effect, time main effect, group*time interaction |
D |
dispersion parameter of the Poisson-Tweedie distribution (D > 1) |
a |
power parameter of the Poisson-Tweedie distribution (a < 1) |
sigma2 |
Variance of the subject-specific random intercept |
offset |
Logical value. If |
A list containing the following elements: a dataframe (data
)
containing the response y, the subject id, the group indicator and time;
a vector with the true random intercept values (true.randint
).
Mirko Signorelli
Signorelli, M., Spitali, P., Tsonaka, R. (2021). Poisson-Tweedie mixed-effects model: a flexible approach for the analysis of longitudinal RNA-seq data. Statistical Modelling, 21 (6), 520-545. URL: https://doi.org/10.1177/1471082X20936017
# simulate a simple, small dataset example1 = simulate_ptglmm(n = 5, t = 2) example1$data # the function allows to set several different parameters example2 = simulate_ptglmm(n = 20, t = 5, seed = 1, beta = c(2.2, 1.2, 0.3, -0.5), D = 1.8, a = 0.5, sigma2 = 0.7, offset = TRUE) # view the distribution of the response variable: pmf(example2$data$y) # visualize the data with a trajectory plot: make.spaghetti(x = time, y = y, id = id, group = group, data = example2$data)
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.