Authors: Colin Olito, Craig R White, Dustin J Marshall and Diego R Barneche
Published in: Journal of Experimental Biology, volume 220, number 5 (March 2017)
Accessing many fundamental questions in biology begins with empirical estimation of simple monotonic rates of underlying biological processes. Across a variety of disciplines, ranging from physiology to biogeochemistry, these rates are routinely estimated from non-linear and noisy time series data using linear regression and ad hoc manual truncation of non-linearities.
Here, we introduce the R package LoLinR, a flexible toolkit to implement local linear regression techniques to objectively and reproducibly estimate monotonic biological rates from non-linear time series data, and demonstrate possible applications using metabolic rate data.
LoLinR provides methods to easily and reliably estimate monotonic rates from time series data in a way that is statistically robust, facilitates reproducible research and is applicable to a wide variety of research disciplines in the biological sciences.
Olito C, White CR, Marshall DJ, Barneche DR (2017) Estimating monotonic rates from biological data using local linear regression, Journal of Experimental Biology, 220: 759‒764 PDF 617 KB doi: 10.1242/jeb.148775