mhar1 function

mhar1

Run Bayesian estimation of a balanced longitudinal model with AR(1) structure

mhar1(Data, Matriz, individuos, tiempos, betai, rhoi, beta1i, beta2i,
  iteraciones, burn)

Arguments

• Data: A vector with the observations of the response variable
• Matriz: The model design matrix
• individuos: A numerical value indicating the number of individuals in the study
• tiempos: A numerical value indicating the number of times observations were repeated
• betai: A vector with the initial values of the vector of regressors
• rhoi: A numerical value with the initial value of the correlation
• beta1i: A numerical value with the shape parameter of a beta apriori distribution of rho
• beta2i: A numerical value with the scaling parameter of a beta apriori distribution of rho
• iteraciones: A numerical value with the number of iterations that will be applied the algorithm MCMC
• burn: Number of iterations that are discarded from the chain

Returns

A dataframe with the mean, median and standard deviation of each parameter, A graph with the histograms and chains for the parameters that make up the variance matrix, as well as the selection criteria AIC, BIC and DIC

Examples

attach(Dental)
Y=as.vector(distance)
X=as.matrix(cbind(1,age))
mhar1(Y,X,27,4,c(1,1),0.5,1,1,500,50)

References

Gamerman, D. 1997. Sampling from the posterior distribution in generalized linear mixed models. Statistics and Computing, 7, 57-68

Cepeda, C and Gamerman, D. 2004. Bayesian modeling of joint regressions for the mean and covariance matrix. Biometrical journal, 46, 430-440.

Cepeda, C and Nuñez, A. 2007. Bayesian joint modelling of the mean and covariance structures for normal longitudinal data. SORT. 31, 181-200.

Nuñez A. and Zimmerman D. 2001. Modelación de datos longitudinales con estructuras de covarianza no estacionarias: Modelo de coeficientes aleatorios frente a modelos alternativos. Questio. 2001. 25.