Canonical correspondence analysis in social science research

The use of simple and multiple correspondence analysis is well-established in socialscience research for understanding relationships between two or more categorical variables.By contrast, canonical correspondence analysis, which is a correspondence analysis with linearrestrictions on the solution, has become one of the most popular multivariate techniques inecological research. Multivariate ecological data typically consist of frequencies of observedspecies across a set of sampling locations, as well as a set of observed environmental variablesat the same locations. In this context the principal dimensions of the biological variables aresought in a space that is constrained to be related to the environmental variables. Thisrestricted form of correspondence analysis has many uses in social science research as well,as is demonstrated in this paper. We first illustrate the result that canonical correspondenceanalysis of an indicator matrix, restricted to be related an external categorical variable, reducesto a simple correspondence analysis of a set of concatenated (or stacked ) tables. Then weshow how canonical correspondence analysis can be used to focus on, or partial out, aparticular set of response categories in sample survey data. For example, the method can beused to partial out the influence of missing responses, which usually dominate the results of amultiple correspondence analysis.

The use of canonical correlation analysis to assess the relationship between executive functioning and verbal memory in older adults

Executive functioning (EF), which is considered to govern complex cognition, and verbal memory (VM) are constructs assumed to be related. However, it is not known the magnitude of the association between EF and VM, and how sociodemographic and psychological factors may affect this relationship, including in normal aging. In this study, we assessed different EF and VM parameters, via a battery of neurocognitive/psychological tests, and performed a Canonical Correlation Analysis (CCA) to explore the connection between these constructs, in a sample of middle- aged and older healthy individuals without cognitive impairment (N = 563, 50+ years of age). The analysis revealed a positive and moderate association between EF and VM independently of gender, age, education, global cognitive performance level, and mood. These results confirm that EF presents a significant association with VM performance.

The contributions of rare objects in correspondence analysis

Correspondence analysis, when used to visualize relationships in a table of counts(for example, abundance data in ecology), has been frequently criticized as being too sensitiveto objects (for example, species) that occur with very low frequency or in very few samples. Inthis statistical report we show that this criticism is generally unfounded. We demonstrate this inseveral data sets by calculating the actual contributions of rare objects to the results ofcorrespondence analysis and canonical correspondence analysis, both to the determination ofthe principal axes and to the chi-square distance. It is a fact that rare objects are oftenpositioned as outliers in correspondence analysis maps, which gives the impression that theyare highly influential, but their low weight offsets their distant positions and reduces their effecton the results. An alternative scaling of the correspondence analysis solution, the contributionbiplot, is proposed as a way of mapping the results in order to avoid the problem of outlying andlow contributing rare objects.

Diversity and microdistribution of black fly (Diptera: Simuliidae) assemblages in the tropical savanna streams of the Brazilian cerrado

We describe the abiotic factors affecting the distribution of black flies at a microhabitat scale, rather than at the regional scale usually present in the literature on the Neotropics. Black fly larvae were sampled from the Tocantins River and three tributaries, located in the Brazilian savanna (state of Tocantins, Brazil) during six bi-monthly sampling periods from October 2004-August 2005. At each sampling site, 15 random quadrats (30 x 30 cm) were sampled each period and for each quadrat were determined mean water velocity, predominant substrate type (rocks, riffle litter or riparian vegetation) and depth detrended correspondence analysis (DCA) was used to determine associations with current velocity, whereas correspondence analysis (CA) was used to estimate site specific current velocity associations. Canonical correspondence analysis (CCA) was used to identify general microhabitat associations. The CCA showed that most species had a trend towards riffle litter, except for Simulium nigrimanum associated with rocky substrate and Simulium cuasiexiguum associated with riparian vegetation. The DCA showed a well defined pattern of water velocity associations. The CA revealed that the species showed different speed associations from one site to another, suggesting different competitive pressures resulting in the occurrence of different realized niches.

Soil and phytosociological characterization of an area with predominance of arnica (Lychnophora pohlii sch. bip.)

Lychnophora pohlii Sch. Bip. (Asteraceae), known as "Arnica mineira", is widely used in folk medicine and very abundant in the altitude vegetation of rocky grassland. The aim of this work was to study the density of this species and its relationship with soil parameters in rocky grassland in Diamantina, in the Upper Jequitinhonha region, Minas Gerais. Ten contiguous 20 x 50 m plots were marked (total sampled area 10,000 m²) on the campus Juscelino Kubitschek of the Federal University of Jequitinhonha and Mucuri Valleys (UFVJM). The plants in these plots were evaluated for frequency, dominance and density. The relationship between the density of this species with nine soil physical and chemical properties was analyzed by means of canonical correspondence analysis (CCA). The highest plant abundance (I) of the species Lychnophora pohlii Sch. Bip. was found in the vegetation sampling areas: plot 6 with 255 plants, plot 7 with 173, plot 8 with 189, plot 9 with 159, and plot 1 with 151 plants. In these areas, the floristic soil characteristics were similar, resulting in spatial proximity in the ACC diagrams. The density of Lychnophora pohlii was higher in plots with higher pH, P-rem and base saturation, the variables most strongly correlated with the first axis of canonical correspondence analysis.

Relationship Between Edaphic Factors and Vegetation in Savannas of the Brazilian Midwest Region

The Brazilian savanna is a mosaic of phytophysiognomies influenced by edaphic and topographic factors that range from the occurrence of fires to anthropic disturbance. The goal of this study was a comparative analysis between two cerrado areas in southeastern Goiás, relating the floristic composition and structure of the vegetation to soil properties to better understand the physiognomic characteristics of the region. Twenty-five 20 × 20 m plots were used. All plants with circumference at breast height of more than 15 cm were measured. Soil samples collected at a depth of 0-20 cm were subjected to physical and chemical analyses. Canonical correspondence analysis (CCA) was used to detect possible correlations between the soil properties and species abundance and distribution. The density and total basal area were 1,647 ind/ha and 15.57 m2/ha, respectively, in Ouroana. At this site, 107 species were sampled. In Montes Claros de Goiás, the density and total basal area were 781 ind/ha and 17.62 m2/ha, and 120 species were sampled. The soil texture of Ouroana was sandy and significantly different from the medium to clayey texture of Montes Claros. The soils of both areas are dystrophic, however, more fertile in Montes Claros and aluminum-toxic in Ouroana. The species of vegetation were distributed according to soil fertility levels. The CCAs grouped species according to soil properties that defined location and abundance as well as the phytophysiognomies of the studied areas.

Biogeochemistry of the shelf sediments of south eastern Arabian sea: Effect on benthic bacterial heterotrophs

The composition and variability of heterotrophic bacteria along the shelf sediments of south west coast of India and its relationship with the sediment biogeochemistry was investigated. The bacterial abundance ranged from 1.12 x 103 – 1.88 x 106 CFU g-1 dry wt. of sediment. The population showed significant positive correlation with silt (r = 0.529, p< 0.05), organic carbon (OC) (r = 0.679, p< 0.05), total nitrogen (TN) (r = 0.638, p< 0.05), total protein (TPRT) (r = 0.615, p< 0.05) and total carbohydrate (TCHO) (r = 0.675, p< 0.05) and significant negative correlation with sand (r = -0.488, p< 0.05). Community was mainly composed of Bacillus, Alteromonas, Vibrio, Coryneforms, Micrococcus, Planococcus, Staphylococcus, Moraxella, Alcaligenes, Enterobacteriaceae, Pseudomonas, Acinetobacter, Flavobacterium and Aeromonas. BIOENV analysis explained the best possible environmental parameters i.e., carbohydrate, total nitrogen, temperature, pH and sand at 50m depth and organic matter, BPC, protein, lipid and temperature at 200m depth controlling the distribution pattern of heterotrophic bacterial population in shelf sediments. The Principal Component Analysis (PCA) of the environmental variables showed that the first and second principal component accounted for 65% and 30.6% of the data variance respectively. Canonical Correspondence Analysis (CCA) revealed a strong correspondence between bacterial distribution and environmental variables in the study area. Moreover, non-metric MDS (Multidimensional Scaling) analysis demarcated the northern and southern latitudes of the study area based on the bioavailable organic matter

Environmental factors and vegetation composition, Lefka Ori Massif, Crete, S. Aegean

Aim The aim of this study was to explore the environmental factors that determine the spatial distribution of oro-mediterranean and alti-mediterranean plant communities in Crete. Location The paper provides a quantitative analysis of vegetation-environment relationships for two study areas within the Lefka Ori massif Crete, a proposed Natura 2000 site. Methods Eleven environmental variables were recorded: altitude, slope, aspect, percentage of bare rock, percentage of unvegetated ground, soil depth, pH, organic matter content and percentages of sand, silt and clay content. Classification of the vegetation was based on twinspan, while detrended correspondence analysis (DCA) and canonical correspondence analysis (CCA) were used to identify environmental gradients linked to community distribution. Results One hundred and twenty-five species were recorded from 120 plots located within the two study areas. Forty-seven of the recorded species are endemic, belonging to 35 families. Hemicryptophytes and chamaephytes were the most frequent, suggesting a typical oro-mediterranean life form spectrum. The samples were classified into five main community types and one transitional. The main gradients, identified by CCA, were altitude and surface cover type in the North-west site, while in the Central site the gradients were soil formation-development and surface cover type. Main conclusions The use of classification in combination with ordination techniques resulted in a good discrimination between plant communities and a greater understanding of controlling environmental factors. The methodology adopted can be employed for improving baseline information on plant community ecology and distribution in Mediterranean mountain zones.

Macrophyte community structure and species occurrence in relation to environmental determinants in the ephemeral aquatic habitats of Gavdos, Greece

The aims of this study were to explore the environmental factors that determine the distribution of plant communities in temporary rock pools and provide a quantitative analysis of vegetation-environment relationships for five study sites on the island of Gavdos, southwest of Crete, Greece. Data from 99 rock pools were collected and analysed using Two-Way Indicator Species Analysis (TWINSPAN), Detrended Correspondence Analysis (DCA) and Canonical Correspondence Analysis (CCA) to identify the principal communities and environmental gradients that are linked to community distribution. A total of 46 species belonging to 21 families were recorded within the study area. The dominant families were Labiatae, Gramineae and Compositae while therophytes and chamaephytes were the most frequent life forms. The samples were classified into six community types using TWINSPAN, which were also corroborated by CCA analysis. The principal gradients for vegetation distribution, identified by CCA, were associated with water storage and water retention ability, as expressed by pool perimeter and water depth. Generalised Additive Models (GAMs) were employed to identify responses of four dominant rock pool species to water depth. The resulting species response curves showed niche differentiation in the cases of Callitriche pulchra and Tillaea vaillantii and revealed competition between Zannichellia pedunculata and Chara vulgaris. The use of classification in combination with ordination techniques resulted in a good discrimination between plant communities. Generalised Additive Models are a powerful tool in investigating species response curves to environmental gradients. The methodology adopted can be employed for improving baseline information on plant community ecology and distribution in Mediterranean ephemeral pools.

Soil profile, relief features and their relation to structure and distribution of Brazilian Atlantic rain forest trees

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Caracterização florística e estrutural das florestas naturalmente fragmentadas no Parque Estadual do Guartelá, município de Tibagi, estado do Paraná

A Floresta Ombrófila Mista na região dos Campos Gerais do Paraná é naturalmente fragmentada, ocorrendo em forma de capões ou ao longo dos cursos d'água. Com o objetivo de caracterizar a composição e estrutura destes fragmentos e avaliar as correlações entre a distribuição das espécies e variáveis do solo de tal região, realizou-se um estudo no Parque Estadual do Guartelá, Município de Tibagi (24°39'10S e 50°15'25W). Foram alocadas 50 parcelas de 10x10m, distribuídas em capões de diferentes tamanhos e ao longo da floresta que acompanha o Rio Iapó, amostrando todos os indivíduos com altura > 3m. Foram encontrados um alto número de espécies (140) e uma elevada diversidade (H'=4,10), valores acima daqueles relatados para o domínio da Floresta Ombrófila Mista. As análises da composição e estrutura revelaram uma flora de transição entre a Floresta Ombrófila Mista e a Floresta Estacional Semidecidual, com uma maior similaridade com esta última, possivelmente influenciada pelo clima. Uma análise de correspondência canônica identificou as variáveis textura e acidez como as correlacionadas com a distribuição de abundâncias das espécies, ordenando dois grupos distintos: um formado pelas parcelas distribuídas nos capões, relacionadas fortemente à textura do solo; e outro pelas parcelas alocadas na floresta de galeria, associadas principalmente com a disponibilidade de nutrientes.

Relação entre heterogeneidade ambiental e distribuição de espécies em uma floresta paludosa no Município de Cristais Paulista, SP, Brasil

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Environmental heterogeneity: Anuran diversity in homogeneous environments

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Effects of daily changes in environmental factors on the abundance and richness of Odonata

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)