excess: Excess from a baseline
In PierreMasselot/hhws: Functions for heat-health warning systems

Description Usage Arguments Details Value References See Also Examples

View source: R/excess.R

excess computes the relative excesses of x relatively to a baseline. excess_inverse reverts the process.

1
2
3

excess(x, expected, fact = 100, ...)

excess_inverse(excess, expected, fact)

`x`	Numeric vector. Contains original data.
`expected`	Numeric vector the same length as `x`. The baseline used in the computation of excesses. If missing in `excess`, the function `baseline` is called with the additional arguments passed in `...`. If missing in `excess_inverse`, the attribute `baseline` is used if present.
`fact`	Numeric. A factor to apply to the relative excess. Default to 100 to express excesses in percentage.
`...`	Arguments to be passed to `baseline` if `expected` is missing. See `?baseline`.
`excess`	Numeric vector. A series of excesses to be reverted to the original scale of `x`.

Compute relative excesses from a baseline. Excesses are computed as:

excess = (x - expected) / expected * fact

excess: A numeric vector of class excess the same length as x.In addition, contains the attributes baseline and fact to keep track of the computation.

excess_inverse: A numeric vector the same length as excess.

Chebana F., Martel B., Gosselin P., Giroux J.X., Ouarda T.B.M.J., 2013. A general and flexible methodology to define thresholds for heat health watch and warning systems, applied to the province of Quebec (Canada). International journal of biometeorology 57, 631-644.

baseline for computing expected values.

  library(dlnm)
  data(chicagoNMMAPS)
  x <- chicagoNMMAPS$death
  dates <- as.POSIXlt(chicagoNMMAPS$date)

  om <- excess(x, dates = dates, order = 15)
  xrec <- excess_inverse(om)

  plot(dates, x)
  lines(dates, xrec, col = "red")