Nearest Neighbor Classification Rule for Mixtures of Discrete and Continuous Random Variables

In this paper very simple nonparametric classification rule for mixtures of discrete and continuous random variables is described. It is based on the method of nearest neighbor proposed by Cover and Hart (1967). The bounds on the limit of the nearest neighbor rule risks are given. Both lower and upper bound depend on the Bayes risk and the loss function. Finally the method is compared with other existing methods on some practical data set.     

Fire history of an isolated subalpine mountain range of the Intermountain Region,United States

Fire has historically been an important ecological component of forests in the Intermountain Region of the northwestern United States. This study is set in a small biogeographically disjunct mountain range. Our research objectives were to (1) investigate the historical frequency, severity, size, and spatial pattern of fire; (2) determine if and how fire regimes have changed since Euro-American settlement; and (3) compare how fire regimes of a small isolated range compare to nearby, but considerably larger, mountain agglomerations. Our findings suggest that this mountain range has historically supported fires typified by small size and high frequency, resulting in a high degree of spatial pattern complexity compared to mountain agglomerations. We also found disparity in size and burn severity solely within the study area based on the bisecting Continental Divide. Since the advent of Euro-American settlement in the 1870s, fire frequency and sizes of individual fires in the West Big Hole Range have significantly decreased resulting in an estimated 87% reduction in area burned. We discuss potential relationships of mountain range isolation and fire regimes in the Intermountain Region. Furthermore, we suggest that the relative small size of this mountain range predisposes it to greater anthropogenic effects upon fire occurrence.     

Behaviour, natural history, and annual cycle of the Henderson Island rail Porzana atra (Aves: Rallidae)

The little known endemic Henderson Island rail (or Henderson rail) Porzflna atra , inhabits forest on the coastal plain and upraised plateau of Henderson Island. Rails were studied for 15 months from January 1991 to March 1992. The population was estimated at c. 6200 individuals living in pairs or cooperative groups of 3–4 adults on territories averaging about 1 ha. Two or three eggs were laid in covered or open nests near the ground from mid-July to mid-February. Up to five consecutive nesting attempts were made in cases where eggs or young chicks were lost. Adults laid a second clutch when chicks were fully feathered at about one month of age. Both sexes incubated and helped rear the young. Older chicks sometimes helped feed younger siblings. Dispersal of juveniles from the natal territory took place in April. Adult birds underwent a rapid, simultaneous post-nuptial moult of the remiges in February-April; the post-juvenile moult involved body feathers only. Data on morphometries, breeding ecology, courtship behaviour and voice are compared with available information for the spotless crake P. tabuensis , the Henderson rail's closest relative and probable ancestor. These comparisons provide some information on how these two taxa have differentiated since rails arrived on Henderson Island some time in the last 380000 years.     

Area and the rapid radiation of Hawaiian Bidens (Asteraceae)

Aim To estimate the rate of adaptive radiation of endemic Hawaiian Bidens and to compare their diversification rates with those of other plants in Hawaii and elsewhere with rapid rates of radiation. Location Hawaii. Methods Fifty‐nine samples representing all 19 Hawaiian species, six Hawaiian subspecies, two Hawaiian hybrids and an additional two Central American and two African Bidens species had their DNA extracted, amplified by polymerase chain reaction and sequenced for four chloroplast and two nuclear loci, resulting in a total of approximately 5400 base pairs per individual. Internal transcribed spacer sequences for additional outgroup taxa, including 13 non‐Hawaiian Bidens, were obtained from GenBank. Phylogenetic relationships were assessed by maximum likelihood and Bayesian inference. The age of the most recent common ancestor and diversification rates of Hawaiian Bidens were estimated using the methods of previously published studies to allow for direct comparison with other studies. Calculations were made on a per‐unit‐area basis. Results We estimate the age of the Hawaiian clade to be 1.3–3.1 million years old, with an estimated diversification rate of 0.3–2.3 species/million years and 4.8 × 10^?5 to 1.3 × 10^?4 species Myr^?1 km^?2. Bidens species are found in Europe, Africa, Asia and North and South America, but the Hawaiian species have greater diversity of growth form, floral morphology, dispersal mode and habitat type than observed in the rest of the genus world‐wide. Despite this diversity, we found little genetic differentiation among the Hawaiian species. This is similar to the results from other molecular studies on Hawaiian plant taxa, including others with great morphological variability (e.g. silverswords, lobeliads and mints). Main conclusions On a per‐unit‐area basis, Hawaiian Bidens have among the highest rates of speciation for plant radiations documented to date. The rapid diversification within such a small area was probably facilitated by the habitat diversity of the Hawaiian Islands and the adaptive loss of dispersal potential. Our findings point to the need to consider the spatial context of diversification – specifically, the relative scale of habitable area, environmental heterogeneity and dispersal ability – to understand the rate and extent of adaptive radiation.     

Evolutionary history of Scinax treefrogs on land‐bridge islands in south‐eastern Brazil

Aim We investigated how Pleistocene refugia and recent (c. 12,000 years ago) sea level incursions shaped genetic differentiation in mainland and island populations of the Scinax perpusillus treefrog group. Location Brazilian Atlantic Forest, São Paulo state, south‐eastern Brazil. Methods Using mitochondrial and microsatellite loci, we examined population structure and genetic diversity in three species from the S. perpusillus group, sampled from three land‐bridge islands and five mainland populations, in order to understand the roles of Pleistocene forest fragmentation and sea level incursions on genetic differentiation. We calculated metrics of relatedness and genetic diversity to assess whether island populations exhibit signatures of genetic drift and isolation. Two of the three island populations in this study have previously been described as new species based on a combination of distinct morphological and behavioural characters, thus we used the molecular datasets to determine whether phenotypic change is consistent with genetic differentiation. Results Our analyses recovered three distinct lineages or demes composed of northern mainland São Paulo populations, southern mainland São Paulo populations, and one divergent island population. The two remaining island populations clustered with samples from adjacent mainland populations. Estimates of allelic richness were significantly lower, and estimates of relatedness were significantly higher, in island populations relative to their mainland counterparts. Main conclusions Fine‐scale genetic structure across mainland populations indicates the possible existence of local refugia within São Paulo state, underscoring the small geographic scale at which populations diverge in this species‐rich region of the Atlantic Coastal Forest. Variation in genetic signatures across the three islands indicates that the populations experienced different demographic processes after marine incursions fragmented the distribution of the S. perpusillus group. Genetic signatures of inbreeding and drift in some island populations indicate that small population sizes, coupled with strong ecological selection, may be important evolutionary forces driving speciation on land‐bridge islands.     

Phylogenetic analyses of primate size evolution: the consequences of sexual selection

We have analysed the relationship between primate mating system, size and size dimorphism by utilizing several phylogenetically based methods. An independent contrast analysis of male and female size (log weight) showed that these are tightly correlated and that size dimorphism is not a simple allometric function of size. We found no relationship between mating system and sexual dimorphism in strepsirhines but a strong relationship in haplorhines. By matched-pairs analysis, where sister groups were matched according to whether the mating system predicted higher or lower intrasexual selection for male size, haplorhine species in more polygynous clades (with a predicted higher sexual selection) were significantly more dimorphic, had larger males, and also, but to a lesser degree, larger females. Both independent contrast and matched-pairs analyses are non-directional and correlational. By using a directional test we investigated how a transition in mating system affects size and dimorphism. Here, each observation is the sum of changes in dimorphism or size in a clade that is defined by a common origin of a mating system. Generally, dimorphism, as well as male and female size, increased after an expected increase in sexual selection, and decreased after an expected decrease in sexual selection. The pattern was, however, not significant for all of the alternative character reconstructions. In clades with an expected increase in sexual selection, male size increased more than female size. This pattern was significant for all character reconstructions. The directional investigation indicates that the magnitude of change in haplorhine dimorphism is larger after an increase in sexual selection than after a decrease, and, for some reconstructions, that the magnitude of size increase is larger than the magnitude of size decrease for both sexes. Possible reasons for these patterns are discussed, as well as their implications as being one possible mechanism behind Cope's rule, i.e. general size increase in many phylogenetic lineages.     

Genetic and morphometric differentiation among island populations of two Norops lizards (Reptilia: Sauria: Polychrotidae) on independently colonized islands of the Islas de Bahia (Honduras)

Aim Anole lizards (Reptilia: Sauria: Polychrotidae) display remarkable morphological and genetic differentiation between island populations. Morphological differences between islands are probably due to both adaptive (e.g. differential resource exploitation and intra‐ or interspecific competition) and non‐adaptive differentiation in allopatry. Anoles are well known for their extreme diversity and rapid adaptive speciation on islands. The main aim of this study was to use tests of morphological and genetic differentiation to investigate the population structure and colonization history of islands of the Islas de Bahia, off the coast of Honduras. Location Five populations of Norops bicaorum and Norops lemurinus were sampled, four from islands of the Islas de Bahia and one from the mainland of Honduras. Methods Body size and weight differentiation were measured in order to test for significant differences between sexes and populations. In addition, individuals were genotyped using the amplified fragment length polymorphism technique. Bayesian model‐based and assignment/exclusion methods were used to study genetic differentiation between island and mainland populations and to test colonization hypotheses. Results Assignment tests suggested migration from the mainland to the Cayos Cochinos, and from there independently to both Utila and Roatán, whereas migration between Utila and Roatán was lacking. Migration from the mainland to Utila was inferred, but was much less frequent. Morphologically, individuals from Utila appeared to be significantly different in comparison with all other localities. Significant differentiation between males of Roatán and the mainland was found in body size, whereas no significant difference was detected between the mainland and the Cayos Cochinos. Main conclusions Significant genetic and morphological differentiation was found among populations. A stepping‐stone model for colonization, in combination with an independent migration to Utila and Roatán, was suggested by assignment tests and was compatible with the observed morphological differentiation.