Estimating monotonic rates from biological data using local linear regression

Colin Olito, Craig White, Dustin Marshall, Diego Barneche Rosado

Research output: Contribution to journalArticleResearchpeer-review

5 Citations (Scopus)

Abstract

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-linearand noisy timeseries data using linear regression and adhoc manual truncation of non-linearities. Here, we introduce the R package LoLinR, aflexible 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.

Original languageEnglish
Pages (from-to)759-764
Number of pages6
JournalJournal of Experimental Biology
Volume220
Issue number5
DOIs
Publication statusPublished - 1 Mar 2017

Keywords

  • Autocorrelation
  • Biological rates
  • Linearity
  • Local linear regression
  • Reproducible research
  • Time series

Cite this