lpm {LPM}

Linear Parametric Model

Description

Estimate ARMA and FARMA models, make simulations and ed eventually apply a corrective procedure to rainfall synthetic series. Besides you can remove seasonal components with STL modified method.

Usage

lpm(x, p, q, n, smean, svar, outer=0, prob = 0.95, fre = 365, 
fractional = F, Plag = 20, lsign=0.05, n1 = 399, trasfo = F, des = T, rain = F, graph = F)

Arguments

x

Univariate series

p

AR order

q

MA order

n

Number of series to simulate

outer

Number of outer loops for STL modified method. Default outer = 0

smean, svar

Mean and Variance smoothing windows of STL modified method

prob

Parameter confidence interval. Default prob = 0.95

fre

Series frequency. Default fre = 365 (for daily series)

fractional

Logical variable: T to apply FARMA model. Default fractional = F

Plag

Maximum lag of ACF used in the Portmanteau test. Default Plag = 20

lsign

Portmanteau Test significance level. Default lsign = 0.05

n1

Number of parameters of infinite MA model . Default n1 = 399

trasfo

Logical variable: T for preventive logarithmical trasformation. Default trasfo = F

des

Logical variable: T to remove seasonal components. Default des = T

rain

Logical variable: T to apply the corrective procedure to daily rainfall simulated series. Default rain = F

graph

Logical variable: T to receive some graphics. Default graph = F

Details

Need integer periodical dataset. Function to complete modelling univariate series.

Value

para

List of estimated parameters

res

Residual series

simdes

List of simulated series without application of corrective procedure

sim

List of simulated series

BIC

Bayesian Information criterion index of estimated model

Note

Portmonteau test and BIC index are displaied during application. Portmonteau Test is positive if Q < chi square

Author(s)

Salvatore Grimaldi

References

Grimaldi, S., 'Linear parametric models applied on daily hydrological series', Journal of Hydrologic Engineering, Vol.9, No 5, September 2004.

Grimaldi S., F. Napolitano, L. Ubertini, 'A procedure to use linear parametric models for daily rainfall series simulation'

Brockwell, P.J and Davis, R.A. (1990) Time Series: Theory and Methods 2nd edition, Springer, NY.

Hipel, K.W. and McLeod, A.I., (1994) Time Series Modelling of Water Resources and Enviromental Systems, Reading, UK.

See Also

rain.adapt

Examples

##---  lpm(series.runoff,1,1,0,30,30,fractional=T,trasfo=T)
##--   Apply a FARMA(1,d,1) model to series.runoff after e preventive 
##     logarithmical trasformation and deseasonalization with smoothing 30.