Influence diagnostics for linear models with first-order autoregressive elliptical errors

We introduce in this paper the class of linear models with first-order autoregressive elliptical errors. The score functions and the Fisher information matrices are derived for the parameters of interest and an iterative process is proposed for the parameter estimation. Some robustness aspects of the maximum likelihood estimates are discussed. The normal curvatures of local influence are also derived for some usual perturbation schemes whereas diagnostic graphics to assess the sensitivity of the maximum likelihood estimates are proposed. The methodology is applied to analyse the daily log excess return on the Microsoft whose empirical distributions appear to have AR(1) and heavy-tailed errors. (C) 2008 Elsevier B.V. All rights reserved.

Effects of selective logging on tropical forest tree growth

We combined measurements of tree growth and carbon dioxide exchange to investigate the effects of selective logging on the Aboveground Live Biomass (AGLB) of a tropical rain forest in the Amazon. Most of the measurements began at least 10 months before logging and continued at least 36 months after logging. The logging removed similar to 15% of the trees with Diameter at Breast Height (DBH) greater than 35 cm, which resulted in an instantaneous 10% reduction in AGLB. Both wood production and mortality increased following logging, while Gross Primary Production (GPP) was unchanged. The ratio of wood production to GPP (the wood Carbon Use Efficiency or wood CUE) more than doubled following logging. Small trees (10 cm < DBH < 35 cm) accounted for most of the enhanced wood production. Medium trees (35 cm < DBH < 55 cm) that were within 30 m of canopy gaps created by the logging also showed increased growth. The patterns of enhanced growth are most consistent with logging-induced increases in light availability. The AGLB continued to decline over the study, as mortality outpaced wood production. Wood CUE and mortality remained elevated throughout the 3 years of postlogging measurements. The future trajectory of AGLB and the forest`s carbon balance are uncertain, and will depend on how long it takes for heterotrophic respiration, mortality, and CUE to return to prelogging levels.