Bootstrapping with models for count data.

Two methods of bootstrap resampling are discussed with log-linear models for count data. The first involves the resampling of observations and the second involves the resampling of Pearson residuals taking into account changes in the distribution of residuals associated with the expected values of counts. The use of both methods is illustrated on two data sets; one data set concerns the number of ear infections of swimmers related to whether they are frequent swimmers or not and three other variables, and the other data set concerns the number of visits to a doctor made in the last 2 weeks related to the age of subjects and 10 other variables. A third data set on the number of marine mammal interactions in different years and fishing areas is also used as an example. In this case only the second bootstrap method can be used because the nature of the data allows the bootstrap resampling of observations to produce sets of data that could not have occurred in practice. Simulation results indicate that the bootstrap results are slightly better than the results from a conventional analysis for the first data set, and much better than the results from a conventional analysis for the second data set, but a conventional analysis works well for the third data set while there are problems with bootstrap analyses.

Estimating habitat selection when GPS fix success is less than 100%.

Inferences about habitat selection by animals derived from sequences of relocations obtained with global positioning system (GPS) collars can be influenced by GPS fix success. Environmental factors such as dense canopy cover or rugged terrain can reduce GPS fix success, making subsequent modeling problematic if fix success depends on the selected habitat. Ignoring failed fix attempts may affect estimates of model coefficients and lead to incorrect conclusions about habitat selection. Here, we present a habitat selection model that accounts for missing locations due to habitat-induced data losses, called a resource selection function (RSF) for GPS fix success. The model's formulation is similar to adjusting estimates of probability of occupancy when detection is less than 100% in patch occupancy sampling. We demonstrate use of the model with GPS data collected from an adult female mule deer (Odocoileus hemionus) and discuss how to analyze data from multiple animals. In the simulations presented, our habitat selection model was generally unbiased for GPS data sets missing up to 50% of the locations.

Comments on A note on permutation tests of significance for multiple regression coefficients by Long, et al.

It is noted that a recent paper in the Journal may give a misleading impression of the robustness of classical regression methods. First, the authors show that p-values based on the randomization distributions of regression coefficients may be quite different from p-values based on t-distributions. However, there is no reason why these two types of p-value should be exactly the same, and p-values based on the randomization distributions of t-statistics are usually similar to p-values obtained from t-distributions. These latter p-values are perfectly valid for the purposes of randomization tests. Second, the authors imply that estimating the standard errors of regression coefficients by randomizing the order of the Y values gives better estimates of standard errors than standard theory. In fact these standard errors based on randomization will tend to be too large unless the regression equation accounts for none of the variation in the Y values.

The Fisher-Pitman permutation test when testing for differences in mean and variance.

The Fisher-Pitman permutation test can detect any type of difference between two samples: hence, a significant Fisher-Pitman permutation test does not necessarily provide evidence for a difference in means. It is possible, however, to test separately for differences in means and variances. Here, we present a recently proposed two-stage procedure to decide whether there are differences in means or variances that can be applied when samples may come from nonnormal distributions with possibly unequal variances.

Trade-offs in the vertical distribution of zooplankton: ideal free distribution with costs?

Zooplankton vertical migratory patterns are a classic example of optimal habitat choice. We hypothesize that zooplankton distribute themselves vertically in the water column according to an ideal free distribution (IFD) with costs such as to optimize their fitness. In lakes with a deep-water chlorophyll maximum, zooplankton are faced with a trade-off, either experiencing high food (high reproductive potential) but low temperature (slow development) in the hypolimnion or high temperature and low food in the epilimnion. Thus, in the absence of fish predation (e.g. at night) they should allocate the time spent in the different habitats according to fitness gain dependent on the temperature gradient and distribution of food. We tested this hypothesis with a Daphnia hyalina x galeata clone in large indoor columns (Plön Plankton Towers) and with a dynamic energy budget model. In the tower experiments, we simulated a deep-water algal maximum below the thermocline with epilimnetic/hypolimnetic temperature differences of 2, 5 and 10 degrees C. Experimental data supported the model. We found a significantly larger proportion of daphniids in the hypolimnion when the temperature difference was smaller. Our results are consistent with the concept of IFD with costs originally developed for stream fishes. This concept can be applied to predict the vertical distribution of zooplankton in habitats where fish predation is of minor importance.

Coexistence of helminth species in Lysapsus limellus (Anura: Pseudidae) from an Argentinean subtropical area: influence of biotic and abiotic factors.

The need for studies on helminth communities of South American amphibians was addressed by examining changes in composition and population dynamics of the helminth component and infracommunities in the frog Lysapsus limellus Cope, 1862, from 1994 to 1996. Two pond types were considered, one permanent and one semipermanent. The main goals of this study were (1) to investigate the relationships between pond type, season, study time, frog body size, and frog sex and the presence-absence and counts of helminth parasite species in the frog host, L. limellus, and (2) to examine the co-occurrence of the different parasite species in the frog host in terms of the structure, assembly, and dynamics of the helminth infracommunity. Parasite presence and absence were analyzed using logistic regression and parasite counts were analyzed using log-linear modeling. To examine the association between parasite species, a principal components analysis was carried out on the correlation matrix for the counts. The pattern of co-occurrences was also examined through a randomization test. The main results were as follows: (1) five parasite species were found in the infracommunity; (2) the pond type and the host size class were the principal factors related to the presence and absence of parasites for the three dominant species, while the year of study and the host sex were only important for one of the species; (3) for the parasite counts, many more factors were significant, with body size class and pond type always important factors for the three core species of the infracommunity, with season, year of study, and sex also sometimes important, and (4) strong associations were observed between some helminth species of the host from the permanent pond, but the same species did not co-occur in frogs in the semipermanent pond. The life histories of the five species can be considered as opportunistic or "r strategists."

Latitudinal patterns in European ant assemblages: variation in species richness and body size.

Using published distributions of 65 species from the British Isles and northern Europe, we show that ant assemblages change with latitude in two ways. First, as commonly found for many types of organisms, the number of ant species decreased significantly with increasing latitude. For Ireland and Great Britain, species richness also increased significantly with region area. Second, although rarely demonstrated for ectotherms, the body size of ant species, as measured by worker length, increased significantly with increasing latitude. We found that this body-size pattern existed in the subfamily Formicinae and, to a lesser extent, in the Myrmicinae, which together comprised 95% of the ant species in our study area. There was a trend for formicines to increase in size with latitude faster than myrmicines. We also show that the pattern of increasing body size was due primarily to the ranges of ant species shifting to higher latitudes as their body sizes increased, with larger formicines becoming less represented at southerly latitudes and larger myrmicines becoming more represented at northerly latitudes. We conclude by discussing five potential mechanisms for generating the observed body-size patterns: the heat-conservation hypothesis, two hypotheses concerning phylogenetic history, the migration-ability hypothesis, and the starvation-resistance hypothesis.

Comments on design and analysis of multiple-choice feeding-preference experiments.

An approach to the analysis of multiple-choice food selection experiments proposed recently is criticised on three grounds and modified methods are suggested.