KLLR: Kernel Localized Linear Regression

Discussion topics for individual codes
Post Reply
Ada Coda
ASCL Robot
Posts: 1916
Joined: Thu May 08, 2014 5:37 am

KLLR: Kernel Localized Linear Regression

Post by Ada Coda » Wed Aug 12, 2020 2:09 am

KLLR: Kernel Localized Linear Regression

Abstract: KLLR (Kernel Localized Linear Regression) generates estimates of conditional statistics in terms of the local slope, normalization, and covariance. This method provides a more nuanced description of population statistics appropriate for very large samples with non-linear trends. The code uses a bootstrap re-sampling technique to estimate the uncertainties and also provides tools to seamlessly generate visualizations of the model parameters.

Credit: Farahi, Arya; Evrard, August E.; McCarthy, Ian; Barnes, David J.; Kay, Scott T.; Anbajagane, Dhayaa; Dolag, Klaus; McCarthy, Ian G.; Nelson, Dylan; Pillepich, Annalisa

Site: https://github.com/afarahi/kllr
https://ui.adsabs.harvard.edu/abs/2020MNRAS.495..686A

Bibcode: 2020ascl.soft08003F

Preferred citation method: https://ui.adsabs.harvard.edu/abs/2018MNRAS.478.2618F and https://ui.adsabs.harvard.edu/abs/2020MNRAS.495..686A

ID: ascl:2008.003

Post Reply