Assessing the effect of time series duration

Robert Schlegel

2018-05-29

Overview

The purpose of this vignette is to lay out, in detail, how one goes about testing a range of variables, and analysing the effects they have on the detection of MHWs. THis has a plurality of meanings, which will be discussed at more depth in the following sections.

Time series shortening

library(heatwaveR)

Systematically reducing time series length of the three reference time series—i.e., from 30-year to 20-year and 10-year. Bootstrapping (I have used 100 resamples, but this can be adjusted upwards if necessary).

Standard climatologies

Measurement metrics:

  • for each day-of-year (doy) in the climatology, calculate the SD of the climatological means of the 100 bootstrapped samples;
  • for each doy, calculate the RMSE of the boostrapped means relative to the true climatology (i.e. the one produced from the 30-year long time series);
  • correspondence of detected events when using climatologies calculated from reduced time series vs. when using the full duration time series climatologies.

Also assess the effect of systematic varying windowHalfWidth and smoothPercentile and studying the outcomes for the three time series lengths.

Fourier transform climatologies

Same as above