smooth (version 2.4.7)

viss: Vector Intermittent State Space

Description

Function calculates the probability for vector intermittent state space model. This is needed in order to forecast intermittent demand using other functions.

Usage

viss(data, intermittent = c("logistic", "none", "fixed"),
  ic = c("AICc", "AIC", "BIC", "BICc"), h = 10, holdout = FALSE,
  probability = c("dependent", "independent"), model = "ANN",
  persistence = NULL, transition = NULL, phi = NULL,
  initial = NULL, initialSeason = NULL, xreg = NULL)

Arguments

data

The matrix with data, where series are in columns and observations are in rows.

intermittent

Type of method used in probability estimation. Can be "none" - none, "fixed" - constant probability or "logistic" - probability based on logit model.

ic

Information criteria to use in case of model selection.

h

Forecast horizon.

holdout

If TRUE, holdout sample of size h is taken from the end of the data.

probability

Type of probability assumed in the model. If "dependent", then it is assumed that occurrence of one variable is connected with the occurrence with another one. In case of "independent" the occurrence of the variables is assumed to happen independent of each other.

model

Type of ETS model used for the estimation. Normally this should be either "ANN" or "MNN". If you assume that there are some tendencies in occurrence, then you can use more complicated models. Model selection is not yet available.

persistence

Persistence matrix type. If NULL, then it is estimated. See ves for the details.

transition

Transition matrix type. If NULL, then it is estimated. See ves for the details.

phi

Damping parameter type. If NULL, then it is estimated. See ves for the details.

initial

Initial vector type. If NULL, then it is estimated. See ves for the details.

initialSeason

Type of the initial vector of seasonal components. If NULL, then it is estimated. See ves for the details.

xreg

Vector of matrix of exogenous variables, explaining some parts of occurrence variable (probability).

Value

The object of class "iss" is returned. It contains following list of values:

• model - the type of the estimated ETS model;

• fitted - fitted values of the constructed model;

• forecast - forecast for h observations ahead;

• states - values of states (currently level only);

• variance - conditional variance of the forecast;

• logLik - likelihood value for the model

• nParam - number of parameters used in the model;

• residuals - residuals of the model;

• actuals - actual values of probabilities (zeros and ones).

• persistence - the vector of smoothing parameters;

• initial - initial values of the state vector;

• initialSeason - the matrix of initials seasonal states;

• intermittent - type of intermittent model used;

• probability - type of probability used;

• issModel - intermittent state-space model used for calculations. Useful only in the case of intermittent="l" and probability="d".

Details

The function estimates probability of demand occurrence, using one of the VES state-space models.

References

• Svetunkov Ivan and Boylan John E. (2017). Multiplicative State-Space Models for Intermittent Time Series. Working Paper of Department of Management Science, Lancaster University, 2017:4 , 1-43.

• Teunter R., Syntetos A., Babai Z. (2011). Intermittent demand: Linking forecasting to inventory obsolescence. European Journal of Operational Research, 214, 606-615.

• Croston, J. (1972) Forecasting and stock control for intermittent demands. Operational Research Quarterly, 23(3), 289-303.

• Syntetos, A., Boylan J. (2005) The accuracy of intermittent demand estimates. International Journal of Forecasting, 21(2), 303-314.

See Also

ets, forecast, es

Examples

# NOT RUN {
    Y <- cbind(c(rpois(25,0.1),rpois(25,0.5),rpois(25,1),rpois(25,5)),
               c(rpois(25,0.1),rpois(25,0.5),rpois(25,1),rpois(25,5)))

    viss(Y, intermittent="l")
    viss(Y, intermittent="l", probability="i")

# }