nowcasting (version 0.0.90)

nowcast: Nowcasting of a quarterly time serie using a dynamic factor.

Description

Estimate nowcasting and foreacasting for a quarterly time serie. The method is based on Giannone et al. 2008

Usage

nowcast(y, regressors, q = 2, r = 2, p = 1)

Arguments

y

Stationary quarterly time-series

regressors

A time series matrix (mts) representing the regressors of interest. The series must be stationary.

q

Dynamic rank. Number of error terms. If not specified q = 2.

r

Static rank (r>=q), i.e. number of factors. If not specified r = 2.

p

AR order of factors. If not specified p = 1.

Value

A list containing two elements:

A data.frame named main contains the original serie, the estimation in the sample, the estimation out of the sample;

A list named factors contains the estimated factors and coeffients..

References

Giannone, D., Reichlin, L., & Small, D. (2008). Nowcasting: The real-time informational content of macroeconomic data. Journal of Monetary Economics, 55(4), 665-676.<doi:10.1016/j.jmoneco.2008.05.010>

See Also

base_extraction

Examples

# NOT RUN {
pib<-base_extraction(22099)
now<-nowcast(lag(pib,-2),Bpanel(vintage,rep(3,dim(vintage)[2])))
now$prev
now$factors
# }