bootstrap_lm_cov_latent_cont: Parametric bootstrap for LM models for continuous outcomes...

In LMest: Generalized Latent Markov Models

Parametric bootstrap for LM models for continuous outcomes with individual covariates in the latent model

Description

Function that performs bootstrap parametric resampling to compute standard errors for the parameter estimates.

The function is no longer maintained. Please look at bootstrap function.

Usage

bootstrap_lm_cov_latent_cont(X1, X2, param = "multilogit", Mu, Si, Be, Ga, B = 100)

Arguments

X1	matrix of covariates affecting the initial probabilities (n x nc1)
X2	array of covariates affecting the transition probabilities (n x TT-1 x nc2)
param	type of parametrization for the transition probabilities ("multilogit" = standard multinomial logit for every row of the transition matrix, "difflogit" = multinomial logit based on the difference between two sets of parameters)
Mu	matrix of conditional means for the response variables (r x k)
Si	var-cov matrix common to all states (r x r)
Be	parameters affecting the logit for the initial probabilities
Ga	parametes affecting the logit for the transition probabilities
B	number of bootstrap samples

Value

mMu	average of bootstrap estimates of the conditional means for the response variables
mSi	average of bootstrap estimates of the var-cov matrix
mBe	average of bootstrap estimates of the parameters affecting the logit for the initial probabilities
mGa	average of bootstrap estimates of the parameters affecting the logit for the transition probabilities
seMu	standard errors for the conditional means
seSi	standard errors for the var-cov matrix
seBe	standard errors for the parameters in Be
seGa	standard errors for the parameters in Ga

Author(s)

Francesco Bartolucci, Silvia Pandolfi - University of Perugia (IT)

Examples

## Not run: 
# Example based on multivariate longitudinal continuous data

data(data_long_cont)
TT <- 5
res <- long2matrices(data_long_cont$id, X = cbind(data_long_cont$X1, data_long_cont$X2),
                    Y = cbind(data_long_cont$Y1, data_long_cont$Y2,data_long_cont$Y3))
Y <- res$YY
X1 <- res$XX[,1,]
X2 <- res$XX[,2:TT,]

# estimate the model
est <- est_lm_cov_latent_cont(Y, X1, X2, k = 3, output = TRUE)
out <- bootstrap_lm_cov_latent_cont(X1, X2, Mu = est$Mu, Si = est$Si,
                                    Be = est$Be, Ga = est$Ga, B = 1000)


## End(Not run)

LMest documentation built on Aug. 27, 2023, 5:06 p.m.