crwPredict: Predict animal locations and velocities using a fitted CTCRW model and
calculate measurement error fit statistics
Description
The crwMEfilter function uses a fitted model object from
crwMLE to predict animal locations (with estimated uncertainty) at
times in the original data set and supplimented by times in predTime.
If speedEst is set to TRUE, then animal log-speed is also
estimated. In addition, the measurement error shock detection filter of de
Jong and Penzer (1998) is also calculated to provide a measure for outlier
detection.Usage
crwPredict(object.crwFit, predTime = NULL, speedEst = FALSE, flat = TRUE,
getUseAvail = FALSE)
Arguments
predTime
vector of additional prediction times (numeric or POSIXct).
speedEst
logical. Estimate animal speed or not.
flat
logical. Should the result be returned as a flat data.frame.
getUseAvail
logical. This is a test function. Not for general use yet.
Value
- List with the following elements:
- originalDataA data.frame with is
data merged with
predTime. - alpha.hat.yA data.frame with predicted state values for each time.
First column in latitude location (
mu.y), second in velocity
(nu.y or theta.y for drift models), and third is drift
velocity (gamma.y if specified). - alpha.hat.xlongitude state predictions.
- Var.hat.yarray where
Var.hat.y[,,i] is the prediction
covariance matrix for alpha.hat.y[,i]. - Var.hat.xarray or covariance matrices for
alpha.hat.x. - speed(If
speedEst=TRUE) Gives log speed estimates for each
time and standard errors based on delta method. If coordinates are polar,
units are meters/unit Time, else, units are those specified by the
coordinates. - fit.testA data.frame of chi-square fit (df=2) statistics and naive
(pointwise) p-values.
- If
flat is set to TRUE then a data set is returned with the
columns of the original data plus the state estimates, standard errors (se),
speed estimates, and the fit statistics and naive p-values.
Details
The requirements for data are the same as those for fitting the model
in crwMLE.References
de Jong, P. and Penzer, J. (1998) Diagnosing shocks in time
series. Journal of the American Statistical Association 93:796-806.