Calculate correlation difference between a forecast and a reference forecast, and assess uncertainty
CorrDiff(
fcst,
fcst.ref,
obs,
N.eff = NA,
conf.level = 0.95,
handle.na = "na.fail"
)
vector of forecasts
vector of reference forecasts
vector of observations
user-defined effective sample size to be used in hypothesis test and for confidence bounds; if NA, the length of `obs` is used after removing missing values; default: NA
confidence level for the confidence interval; default = 0.95
how should missing values in forecasts and observations be handled; possible values are 'na.fail' and 'only.complete.triplets'; default: 'na.fail'
vector with correlation difference, one-sided p-value, and central confidence interval at the user-defined confidence level
Steiger (1980): Tests for comparing elements of a correlation matrix. Psychological Bulletin. 10.1037/0033-2909.87.2.245 Zou (2007): Toward using confidence intervals to compare correlations. Psychological Methods. 10.1037/1082-989X.12.4.399
Corr
# NOT RUN { data(eurotempforecast) CorrDiff(rowMeans(ens), ens[, 1], obs) # }