adehabitatLT (version 0.3.7)

acfdist.ltraj: Compute correlogram for angular and linear descriptors of a movement path

Description

The functions acfdist.ltraj and acfang.ltraj compute (and by default plot) a correlogram-like function .

Usage

acfdist.ltraj(x, which = c("dist", "dx", "dy"), nrep = 999, lag = 1,
              plot = TRUE, xlab = "Lag", ylab = "autocorrelation")
acfang.ltraj(x, which = c("absolute", "relative"), nrep = 999, lag = 1,
             plot = TRUE, xlab = "Lag", ylab = "autocorrelation")

Arguments

x

an object of the class ltraj

which

to select on which parameter the autocorrelation should be computed (see details).

nrep

the number of repetitions used to test the significance of autocorrelation for each lag value.

lag

maximum lag at which to calculate the autocorrelation. Default is 1.

plot

logical. If 'TRUE' (the default) the autocorrelation is plotted.

xlab

a title for the x axis

ylab

a title for the y axis

Value

• A list of matrices. Each matrix corresponds to a 'burst'. The matrix contains for each lag value (column), the values of autocorrelation (observed, and the 2.5 %, 50 % and 97.5 % quantiles of for the set of nrep permutations of values).

Details

The function acfdist.ltraj is used to compute a correlogram for linear descriptors and acfang.ltraj for angular descriptors (see as.ltraj for a description of these descriptors).

Statistics used are defined in Dray et al. (in press). They are based on squared differences between successive values. For angular descriptors, the statistic is based on the chord distance.

In the case of missing data, the computation of the correlograms is restricted to the pairs of successive observed data and only observed data are permuted (i.e. the structure of the missing data is kept constant under permutation).

The grey area represents a 95 % interval obtained after permutation of the data. If the observed data is outside this region, it is considered as significant and represetend by a black symbol. Note that no multiple-comparison adjustement is performed.

References

Dray, S., Royer-Carenzi, M. and Calenge, C. The exploratory analysis of autocorrelation in animal movement studies. Ecological Research, in press. Calenge, C., Dray, S. and Royer-Carenzi, M. (2009) The concept of animals trajectories from a data analysis perspective. Ecological Informatics, 4,34--41.

See Also

as.ltraj for additional information on the class ltraj, wawotest for a simple test of the autocorrelation of the descriptive parameters on the trajectory.

Examples

data(puechcirc)
puechcirc
acfang.ltraj(puechcirc, lag=5)
acfdist.ltraj(puechcirc, lag=5)