oos_realized_forc_general: Out-of-sample general model forecast conditioned on realized...

In lmForc: Linear Model Forecasting

Out-of-sample general model forecast conditioned on realized values

Description

oos_realized_forc takes a model function, a prediction function, input data for estimating the model, realized values of the dependent variable, an integer number of periods ahead to forecast, a period to end the initial coefficient estimation and begin forecasting, a vector of time data associated with the model, and an optional integer number of past periods to estimate the model over. The model is originally estimated using the input data and model function with data up to estimation_end minus the the number of periods specified in estimation_window. If estimation_window is left NULL then the model is estimated with all available data up to estimation_end. Model parameters are then combined with realized values of the input data h_ahead periods ahead to generate an h_ahead period ahead forecast. This process is iteratively repeated for each period after estimation_end with model parameters updating in each period. Returns an out-of-sample forecast conditional on realized values that would not have been available at the forecast origin. Tests the out-of-sample performance of a model had it been conditioned on perfect information.

Usage

oos_realized_forc_general(
  model_function,
  prediction_function,
  data,
  realized,
  h_ahead,
  estimation_end,
  time_vec,
  estimation_window = NULL
)

Arguments

model_function	Function that estimates a model using the data input.
prediction_function	Function that generates model predictions using model_function and data as inputs.
data	Input data for estimating the model.
realized	Vector of realized values of the dependent variable equal in length to the data in data.
h_ahead	Integer representing the number of periods ahead that is being forecasted.
estimation_end	Value of any class representing when to end the initial coefficient estimation period and begin forecasting.
time_vec	Vector of any class that represents time and is equal in length to the length of realized and data.
estimation_window	Integer representing the number of past periods that the linear model should be estimated over in each period.

Value

Forecast object that contains the out-of-sample forecast.

See Also

For a detailed example see the help vignette: vignette("lmForc", package = "lmForc")

Examples

date <- as.Date(c("2010-03-31", "2010-06-30", "2010-09-30", "2010-12-31",
                  "2011-03-31", "2011-06-30", "2011-09-30", "2011-12-31", 
                  "2012-03-31", "2012-06-30", "2012-09-30", "2012-12-31",
                  "2013-03-31", "2013-06-30", "2013-09-30", "2013-12-31"))
y  <- c(1, 0, 0, 0, 1, 1, 0, 0, 0, 1, 0, 0, 0, 1, 1, 0)
x1 <- c(8.22, 3.86, 4.27, 3.37, 5.88, 3.34, 2.92, 1.80, 3.30, 7.17, 3.22, 3.86, 
    4.27, 3.37, 5.88, 3.34)
x2 <- c(4.03, 2.46, 2.04, 2.44, 6.09, 2.91, 1.68, 2.91, 3.87, 1.63, 4.03, 2.46, 
    2.04, 2.44, 6.09, 2.91)
dataLogit <- data.frame(date, y, x1, x2)

forc <- oos_realized_forc_general(
    model_function = function(data) {glm(y ~ x1 + x2, data = data, family = binomial)},
    prediction_function = function(model_function, data) {
        as.vector(predict(model_function, data, type = "response"))
    }, 
    data = dataLogit,
    realized = dataLogit$y,
    h_ahead = 2L,
    estimation_end = as.Date("2012-06-30"),
    time_vec = dataLogit$date,
    estimation_window = NULL
)

lmForc documentation built on Sept. 11, 2024, 8:14 p.m.