Journal of Plant Ecology ›› 2017, Vol. 10 ›› Issue (1): 91-110.DOI: 10.1093/jpe/rtw107

所属专题: 生物多样性与生态系统功能

• • 上一篇    下一篇

A guide to analyzing biodiversity experiments

Bernhard Schmid, Martin Baruffol, Zhiheng Wang, Pascal A. Niklaus   

  • 收稿日期:2016-06-12 修回日期:2016-09-17 接受日期:2016-09-26 出版日期:2017-02-04 发布日期:2017-01-30
  • 基金资助:
    This study was supported by the Swiss National Science Foundation (grant number 310030B_147092 to B.S.) and the University Research Priority Program Global Change and Biodiversity of the University of Zürich.

A guide to analyzing biodiversity experiments

Bernhard Schmid1,*, Martin Baruffol1, Zhiheng Wang1,2 and Pascal A. Niklaus1   

  1. 1 Department of Evolutionary Biology and Environmental Studies and Zürich–Basel Plant Science Center, University of Zürich, Winterthurerstrasse 190, CH-8057 Zürich, Switzerland; 2 Department of Ecology and Key Laboratory for Earth Surface Processes of the Ministry of Education, College of Urban and Environmental Sciences, Peking University, Beijing 100871, China
  • Received:2016-06-12 Revised:2016-09-17 Accepted:2016-09-26 Online:2017-02-04 Published:2017-01-30
  • Contact: Schmid, Bernhard
  • Supported by:
    This study was supported by the Swiss National Science Foundation (grant number 310030B_147092 to B.S.) and the University Research Priority Program Global Change and Biodiversity of the University of Zürich.

摘要: Aims The aim of this guide is to provide practical help for ecologists who analyze data from biodiversity–ecosystem functioning experiments. Our approach differs from others in the use of least squares-based linear models (LMs) together with restricted maximum likelihood-based mixed models (MMs) for the analysis of hierarchical data. An original data set containing diameter and height of young trees grown in monocultures, 2- or 4-species mixtures under ambient light or shade is used as an example.
Methods Starting with a simple LM, basic features of model fitting and the subsequent analysis of variance (ANOVA) for significance tests are summarized. From this, more complex models are developed. We use the statistical software R for model fitting and to demonstrate similarities and complementarities between LMs and MMs. The formation of contrasts and the use of error (LMs) or random-effects (MMs) terms to account for hierarchical data structure in ANOVAs are explained.
Important Findings Data from biodiversity experiments can be analyzed at the level of entire plant communities (plots) and plant individuals. The basic explanatory term is species composition, which can be divided into contrasts in many ways depending on specific biological hypotheses. Typically, these contrasts code for aspects of species richness or the presence of particular species. For significance tests in ANOVAs, contrast terms generally are compared with remaining variation of the explanatory terms from which they have been ‘carved out’. Once a final model has been selected, parameters (e.g. means or slopes for fixed-effects terms and variance components for error or random-effects terms) can be estimated to indicate the direction and size of effects.

关键词: analysis of variance, BEF-China, contrasts, linear models, mixed models, non-orthogonality, repeated measures, variance components

Abstract: Aims The aim of this guide is to provide practical help for ecologists who analyze data from biodiversity–ecosystem functioning experiments. Our approach differs from others in the use of least squares-based linear models (LMs) together with restricted maximum likelihood-based mixed models (MMs) for the analysis of hierarchical data. An original data set containing diameter and height of young trees grown in monocultures, 2- or 4-species mixtures under ambient light or shade is used as an example.
Methods Starting with a simple LM, basic features of model fitting and the subsequent analysis of variance (ANOVA) for significance tests are summarized. From this, more complex models are developed. We use the statistical software R for model fitting and to demonstrate similarities and complementarities between LMs and MMs. The formation of contrasts and the use of error (LMs) or random-effects (MMs) terms to account for hierarchical data structure in ANOVAs are explained.
Important findings Data from biodiversity experiments can be analyzed at the level of entire plant communities (plots) and plant individuals. The basic explanatory term is species composition, which can be divided into contrasts in many ways depending on specific biological hypotheses. Typically, these contrasts code for aspects of species richness or the presence of particular species. For significance tests in ANOVAs, contrast terms generally are compared with remaining variation of the explanatory terms from which they have been 'carved out'. Once a final model has been selected, parameters (e.g. means or slopes for fixed-effects terms and variance components for error or random-effects terms) can be estimated to indicate the direction and size of effects.

Key words: analysis of variance, BEF-China, contrasts, linear models, mixed models, non-orthogonality, repeated measures, variance components