summary.CausalMBSTS function

Summary of causal effect estimation results obtained with CausalMBSTS

The method extracts and computes various summaries of the causal analysis with CausalMBSTS.

## S3 method for class 'CausalMBSTS'
summary(object, ...)

Arguments

• object: An object of class 'CausalMBSTS', a result of a call to CausalMBSTS.
• ...: further arguments passed to or from other methods (currently not used).

Returns

Returns an object of class summary.CausalMBSTS, which is a list of data frames corresponding to each date provided in horizon (or its default value) with the following columns: - mean: Estimated average causal effect

• lower: Lower bound of the two-sided (1-alpha)% credible interval. Note that alpha parameter is inherited from the object object.

• upper: Upper bound of the two-sided (1-alpha)% credible interval

• cum.sum: Pointwise effect

• cum.lower: Lower bound of a (1-alpha)% credible interval of the pointwise effect

• cum.upper: Upper bound of a (1-alpha)% credible interval of the pointwise effect

• bayes.pval: Bayesian p-value for the average causal effect

• pct.causal.eff: Probability of a causal effect (%)

Examples

set.seed(1)
t <- seq(from = 0,to = 4*pi, length.out=300)
y <- cbind(3*sin(2*t)+rnorm(300), 2*cos(2*t) + rnorm(300))
dates <- seq.Date(from = as.Date("2015-01-01"), by = "week", length.out=300)
int.date <- as.Date("2020-02-27")
y[dates >= int.date,] <- y[dates >= int.date,]+2

# Causal effect estimation
causal.2 <- CausalMBSTS(y, components = c("trend", "cycle"), cycle.period = 75,
                        dates = dates, int.date = int.date, s0.r = 0.01*diag(2),
                        s0.eps = 0.1*diag(2), niter = 100, burn = 10)

sum.causal.2 <- summary(causal.2)
print(sum.causal.2, digits = 2)
sum.causal.2$horizon_default