Premium
Contrasting approaches to statistical regression in ecology and economics
Author(s) -
Armsworth P. R.,
Gaston K. J.,
Hanley N. D.,
Ruffell R. J.
Publication year - 2009
Publication title -
journal of applied ecology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 2.503
H-Index - 181
eISSN - 1365-2664
pISSN - 0021-8901
DOI - 10.1111/j.1365-2664.2009.01628.x
Subject(s) - endogeneity , discipline , ecology , process (computing) , regression , range (aeronautics) , regression analysis , econometrics , data science , computer science , management science , economics , sociology , statistics , machine learning , mathematics , social science , biology , engineering , aerospace engineering , operating system
Summary1 Conservation and natural resource management challenges are as much social problems as biological ones. In recognition of this fact, ecologists and economists work increasingly closely together. We discuss one barrier to effective integration of the two disciplines: put simply, many ecologists and economists approach statistical regression differently. 2 Regression techniques provide the most commonly used approach for empirical analyses of land management decisions. Researchers from each discipline attribute differing importance to a range of possibly conflicting design criteria when formulating regression analyses. 3 Ecologists commonly attribute greater importance to spatial autocorrelation and parsimony than do economists when designing regressions. Economists often attribute greater importance than ecologists to concerns about endogeneity and conformance with a priori theoretical expectations. 4 Synthesis and applications . The differing importance attributed to different design characteristics may reflect a process of cultural drift within each discipline. Greater interdisciplinary collaboration can counteract this process by stimulating the flow of ideas and techniques across disciplinary boundaries.