march.mc.thompson {march}

Thompson Confidence Intervals for a Markov chain model.

Description

Compute the confidence intervals using Thompson's formula on a march.Mc object. See Thompson SK (1987) Sample size for estimating multinomial proportions, American Statistician 41:42-46, for details.

Usage

march.mc.thompson(object, alpha)

Arguments

object

the march.Model object on which compute the confidence intervals.

alpha

the significance level among : 0.5, 0.4, 0.3, 0.2, 0.1, 0.05, 0.025, 0.02, 0.01, 0.005, 0.001, 0.0005, 0.0001.

Value

A list of half-length confidence intervals for each probability distribution of the Markov chain.

Author(s)

Ogier Maitre, Kevin Emery

Examples

# Compute a first-order homogeneous Markov Chain for the pewee data.
MC1 <- march.mc.construct(pewee,1)
# Display the transition matrix
print(MC1@RC)
# Compute the half-length 95% confidence interval for each row of the transition matrix.
march.mc.thompson(MC1,alpha=0.05)

# Compute a third-order MTD model for the pewee data.
MTD3 <- march.mtd.construct(pewee,3)
# Display the model
print(MTD3)
# Compute the half-length 95% confidence interval for the vector of lags
# and for each row of the transition matrix.
march.mtd.thompson(MTD3,alpha=0.05)