21
Exploring Lagged Effects in Time
Series
Andréa Puzzi Nicolau , Karen Dyson , David Saah ,
and Nicholas Clinton
Overview
In this chapter, we will introduce lagged effects to build on the previous work in mod-
eling time series data. Time-lagged effects occur when an event at one point in time
impacts dependent variables at a later point in time. You will be introduced to con-
cepts of autocovariance and autocorrelation, cross-covariance and cross-correlation,
and auto-regressive models. At the end of this chapter, you will be able to examine
how variables relate to one another across time and to fit time series models that take
into account lagged events.
A. P. Nicolau · K. Dyson · D. Saah
Spatial Informatics Group, Pleasanton, CA, USA
e-mail: apnicolau@sig-gis.com
K. Dyson
e-mail: kdyson@sig-gis.com
A. P. Nicolau · K. Dyson
SERVIR-Amazonia, Cali, Colombia
D. Saah (B)
University of San Francisco, San Francisco, CA, USA
e-mail: dssaah@usfca.edu
N. Clinton
Google LLC, Mountain View, CA, USA
e-mail: nclinton@google.com
K. Dyson
Dendrolytics, Seattle, WA, USA
© The Author(s) 2024
J. A. Cardille et al. (eds.), Cloud-Based Remote Sensing with Google Earth Engine,
https://doi.org/10.1007/978-3-031-26588-4_21
403