Information Analysis of Vegetation Data

ISBN-13: 9789400965775 / Angielski / Miękka / 2011 / 153 str.

E. Feoli;M. Lagonegro;L. Orloci

Opis

Information analysis, a popular subject among vegetation ecologists not too many years ago, is revisited in this short monograph. The overview provided and the systematic presentation of ideas and algorithms should interest data analysts with backgrounds in this or other fields of natural science where the question of classifi cation is addressed. The text gives the detailed descriptions and the listings of the computer programs. The authors were recipients of grant support from the Italian Consiglio Nazionale delle Ricerche "Gruppo Biologia Naturalistica" (E. Feoli) and the Canadian Na tional Science and Engineering Research Council (L. Orl6ci) during completion of the project. The respective institutions of the University of Western Ontario and the University of Trieste provided facilities and computer time. Mrs. Stefani Tichbourne (London) typed the manuscript, Mr. Aulo Zampar (Trieste) gave computing assis tance and Mr. Furio Poropat (Trieste) translated some programs. We are most grateful to them. E. Feoli M. Lagonegro L."

Spis treści

1. Introduction.- 2. Definitions of entropy and divergence.- 3. Arrays of vegetation data.- R-dispersion arrays.- Q-dispersion arrays.- Diversity arrays.- Predictive arrays.- Notes on symbols.- 4. Measurements on the arrays.- Entropy measures and multiples.- Components of entropy.- A. A single array.- B. Several arrays.- Divergence measures.- A. A single su x sz array.- B. Several arrays.- Information measures on diversity arrays.- Hierarchically nested model of divergence.- Redundancy.- Equivocation.- 5. Application to community analysis.- Ecological connections.- Classification.- A. Weighting of variables and individuals.- B. Data reduction.- C. Measurement of resemblance.- D. Cluster-seeking algorithms.- Predictivity analysis.- Comparison of classifications.- Identification.- 6. Computer programs and examples of application.- A. Characterization of programs.- B. Ranking species.- C. Computation of resemblance matrices.- D. Cluster analysis.- E. Predictivity analysis.- F. Nested model.- G. Identification.- H. Structuring data tables.- 7. Program listings.- 8. References.