Newer
Older
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/Corr.R
\title{Computes the correlation coefficient between an array of forecasts and their corresponding observations}
Corr(
var_exp,
var_obs,
posloop = 1,
poscor = 2,
compROW = NULL,
limits = NULL,
siglev = 0.95,
method = "pearson",
conf = TRUE,
pval = TRUE
)
.Corr(exp, obs, siglev = 0.95, method = "pearson", conf = TRUE, pval = TRUE)
\item{var_exp}{Array of experimental data.}
\item{var_obs}{Array of observational data, same dimensions as var_exp
except along posloop dimension, where the length can be nobs instead of nexp.}
\item{posloop}{Dimension nobs and nexp.}
\item{poscor}{Dimension along which correlation are to be computed (the
dimension of the start dates).}
\item{compROW}{Data taken into account only if (compROW)th row is complete.
\item{limits}{Complete between limits[1] & limits[2]. Default = NULL.}
\item{siglev}{Significance level. Default = 0.95.}
\item{method}{Type of correlation: 'pearson', 'spearman' or 'kendall'.
Default='pearson'}
\item{conf}{Whether to compute confidence intervals (default = 'TRUE') or
not (FALSE).}
\item{pval}{Whether to compute statistical significance p-value (default = 'TRUE')
or not (FALSE).}
\item{exp}{N by M matrix of N forecasts from M ensemble members.}
\item{obs}{Vector of the corresponding observations of length N.}
Corr: Array with dimensions :\cr
c(# of datasets along posloop in var_exp, # of datasets along posloop in
var_obs, 4, all other dimensions of var_exp & var_obs except poscor).\cr
The third dimension, of length 4 maximum, contains to the lower limit of
the 95\% confidence interval, the correlation, the upper limit of the 95\%
confidence interval and the 95\% significance level given by a one-sided
T-test. If the p-value is disabled via \code{pval = FALSE}, this dimension
will be of length 3. If the confidence intervals are disabled via
\code{conf = FALSE}, this dimension will be of length 2. If both are
disabled, this will be of length 2. \cr\cr
\itemize{
\item{$corr}{The correlation statistic.}
\item{$p_val}{Corresponds to the p values for the \code{siglev}\%
(only present if \code{pval = TRUE}) for the correlation.}
\item{$conf_low}{Corresponds to the upper limit of the \code{siglev}\%
(only present if \code{conf = TRUE}) for the correlation.}
\item{$conf_high}{Corresponds to the lower limit of the \code{siglev}\%
(only present if \code{conf = TRUE}) for the correlation.}
}
}
\description{
Calculates the correlation coefficient (Pearson, Kendall or Spearman) for
an array of forecasts and observations. The input should be an array with
dimensions c(no. of datasets, no. of start dates, no. of forecast times,
no. of lons, no. of lats.), where the longitude and latitude dimensions are
optional. The correlations are computed along the poscor dimension which
should correspond to the startdate dimension. If compROW is given, the
correlations are computed only if rows along the compROW dimension are
complete between limits[1] and limits[2], i.e. there are no NAs between
limits[1] and limits[2]. This option can be activated if the user wishes to
account only for the forecasts for which observations are available at all
leadtimes. \cr
Default: limits[1] = 1 and limits[2] = length(compROW dimension).\cr
The confidence interval is computed by a Fisher transformation.\cr
The significance level relies on a one-sided student-T distribution.\cr
We can modifiy the treshold of the test modifying siglev (default value=0.95).\cr\cr
.Corr calculates the correlation between the ensemble mean and the
observations, using an N by M matrix (exp) of forecasts and a vector of
observations (obs) as input.
}
\examples{
# Load sample data as in Load() example:
clim <- Clim(sampleData$mod, sampleData$obs)
ano_exp <- Ano(sampleData$mod, clim$clim_exp)
ano_obs <- Ano(sampleData$obs, clim$clim_obs)
runmean_months <- 12
dim_to_smooth <- 4
# Smooth along lead-times
smooth_ano_exp <- Smoothing(ano_exp, runmean_months, dim_to_smooth)
smooth_ano_obs <- Smoothing(ano_obs, runmean_months, dim_to_smooth)
dim_to_mean <- 2 # Mean along members
required_complete_row <- 3 # Discard start dates which contain any NA lead-times
leadtimes_per_startdate <- 60
corr <- Corr(Mean1Dim(smooth_ano_exp, dim_to_mean),
Mean1Dim(smooth_ano_obs, dim_to_mean),
compROW = required_complete_row,
limits = c(ceiling((runmean_months + 1) / 2),
leadtimes_per_startdate - floor(runmean_months / 2)))
PlotVsLTime(corr, toptitle = "correlations", ytitle = "correlation",
monini = 11, limits = c(-1, 2), listexp = c('CMIP5 IC3'),
listobs = c('ERSST'), biglab = FALSE, hlines = c(-1, 0, 1),
fileout = 'tos_cor.eps')
# The following example uses veriApply combined with .Corr instead of Corr
require(easyVerification)
Corr2 <- s2dverification:::.Corr
corr2 <- veriApply("Corr2",
smooth_ano_exp,
# see ?veriApply for how to use the 'parallel' option
Mean1Dim(smooth_ano_obs, dim_to_mean),
tdim = 3, ensdim = 2)
}
0.1 - 2011-04 (V. Guemas) - Original code\cr
1.0 - 2013-09 (N. Manubens) - Formatting to R CRAN\cr
1.1 - 2014-10 (M. Menegoz) - Adding siglev argument\cr
1.2 - 2015-03 (L.P. Caron) - Adding method argument\cr
1.3 - 2017-02 (A. Hunter) - Adapted to veriApply()