Articles | Volume 26, issue 2
https://doi.org/10.5194/npg-26-91-2019
https://doi.org/10.5194/npg-26-91-2019
Research article
 | 
14 Jun 2019
Research article |  | 14 Jun 2019

Statistical hypothesis testing in wavelet analysis: theoretical developments and applications to Indian rainfall

Justin A. Schulte

Data sets

Meteorological Data Sets for Downloading Indian Institute of Tropical Meteorology https://www.tropmet.res.in/Data Archival-51-Page

Climate Timeseries NOAA/OAR/ESRL PSD https://www.esrl.noaa.gov/psd/gcos_wgsp/Timeseries/

Download
Short summary
Statistical hypothesis tests in wavelet analysis are used to asses the likelihood that time series features are noise. The choice of test will determine which features emerge as a signal. Tests based on area do poorly at distinguishing abrupt fluctuations from periodic behavior, unlike tests based on arclength that do better. The application of the tests suggests that there are features in Indian rainfall time series that emerge from background noise.