Exploratory Analysis

Abstract

This chapter describes some simple procedures that may be used to gain a preliminary understanding of a data set, often as a prelude to more sophisticated analyses. Specifically, techniques for visualising time series data are discussed, as well as some of the “classical” tests for trend. The key concepts of autocorrelation and smoothing are introduced-the former because of the need to account for it in subsequent analyses and the latter because, in one form or another, smoothing techniques underlic many of the other methods discussed. The chapter discusses some procedures that are commonly used to test for the existence of trends in environmental time series. Many techniques are well established in one or more areas of environmental science, and it is perhaps natural to ask why they have all been included under the heading “exploratory analysis”-surely, after dealing with visualisation, serial dependence, smoothing, trend and seasonality removal and testing. Controlled Vocabulary Terms autocorrelation function; exploratory factor analysis; smoothing

Cite this paper

@misc{chandler2011exploratory,
  title = {{Exploratory Analysis}},
  author = {Chandler, Richard E. and Scott, E. Marian},
  pages = {25--59},
  year = {2011},
  doi = {10.1002/9781119991571.ch2}
}

Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.

Related papers