A reader recently inquired about using the Theil-Sen slope to estimate trends in temperature data, rather than the more usual least-squares regression. The Theil-Sen estimator is a non-parametric method to estimate a slope (perhaps more properly, a “distribution-free” method) which is robust, i.e., it is resistant to the presence of outliers (extremely variant data values) which can wreak havoc with least-squares regression. It also doesn’t rely on the noise following the normal distribution, it’s truly a distribution-free method. Even when the data are normally distributed and outliers are absent, it’s still competitive with least-squares regression.
Support Your Global Climate Blog
Recent Comments
Bob Loblaw on COVID-19: Failure Doc Snow on COVID-19: Failure snarkrates on COVID-19: Failure Susan Anderson on COVID-19: Failure Susan Anderson on COVID-19: Failure Kevin Donald McKinne… on COVID-19: Failure Kevin Donald McKinne… on COVID-19: Failure Kevin Donald McKinne… on COVID-19: Failure Kevin Donald McKinne… on COVID-19: Failure Kevin Donald McKinne… on Trump’s Wall Susan Anderson on COVID-19: Failure snarkrates on COVID-19: Failure snarkrates on COVID-19: Failure Wookey on COVID-19: Failure Bob Loblaw on COVID-19: Failure -
Recent Posts
Buy the book
astronomy
Blogroll
Global Warming
- Climate Change
- ClimateSight
- Goddard Institute for Space Studies
- GreenFyre’s
- Hadley Center for Climate Change
- History of Global Warming (Spencer Weart)
- IPCC (Intergovernmental Panel on Climate Change)
- James’s Empty Blog
- Maribo
- Old Man in a Cave
- Open Mind Archive on Skeptical Science
- Rabett Run
- RealClimate
mathematics