bootstrap_month: Implements a monthly bootstrap
View source: R/bootstrap_month.R
| bootstrap_month | R Documentation |
Implements a monthly bootstrap
Description
Months in which at least one variable exceeds the user-specified minimum proportion of non-missing values are sampled with replacement. February of leap years are treated as a 13th month.
Usage
bootstrap_month(data, boot_prop = 0.8)
Arguments
data |
Data frame of raw data detrended if necessary. First column should be of the |
block_prop |
Numeric vector of length one specifying the minimum proportion of non-missing values of at least one of the variables for a month to be included in the bootstrap. Default is |
Value
Dataframe containing a bootstrap undertaken with replacement that accounts for monthly-scale seasonality.
Examples
#Let's assess the sampling variability in kendall's tau
#correlation coefficient between rainfall and OsWL at S-22.
#Data starts on first day of 1948
head(S22.Detrend.Declustered.df)
#Dataframe ends on 1948-02-03
tail(S22.Detrend.Declustered.df)
#Adding dates to complete final month of combined records
final.month = data.frame(seq(as.Date("2019-02-04"),as.Date("2019-02-28"),by="day"),NA,NA,NA)
colnames(final.month) = c("Date","Rainfall","OsWL","Groundwater")
S22.Detrend.Declustered.df = rbind(S22.Detrend.Declustered.df,final.month)
#Generate 100 monthly bootstrap samples of rainfall and OsWL
cor = rep(NA,100)
for(i in 1:100){
boot_df = bootstrap_month(S22.Detrend.df[,c(1:3)], boot_prop=0.8)
boot_df = na.omit(boot_df)
cor[i] = cor(boot_df$Rainfall, boot_df$OsWL, method="kendall")
}
#Compare means of bootstrap samples with the mean of the observed data
hist(cor)
df = na.omit(S22.Detrend.df[,1:3])
abline(v=cor(df$Rainfall,df$OsWL, method="kendall"),col=2,lwd=2)
