CRAMP Home
Long Term Monitoring
Rapid Assessment
Methods
Site Selection
Geographic Coordinates
Biological Parameters
Environmental Parameters
Statistical Methods
Multivariate Statistics
Statistical Transformations
Fish Statistical Techniques
Bio-Indicators
Results
Mapping
Watersheds
Publications
Search the CRAMP Website
Navigate the CRAMP Website
Bibliographic Search
CRAMP Rapid Assessment. Multivariate Statistical Methods
Coral reef communities encompass large spatial and temporal scales that are often extremely heterogeneous and vary in their type and severity of disturbances, thus susceptible to highly variable data collection. Complex interactions and numerous causal relationships add to this variability. Causes of variability have been attributed to chance distribution of individuals, local disturbances, animal movement, statistical and methodological limitations, error and environmental heterogeneity. This variability can significantly reduce statistical power (Brown et al. 2003).
When working with such an extensive, diverse database involving numerous parameters, multivariate techniques are commonly used to group similar sets of samples. This type of analysis is highly efficient in summarizing data for intrinsic analysis of ecological communities (Gauch 1982). Multivariate analysis can reveal the distribution of species along environmental gradients, highlight patterns in the data through spatial comparisons and habitat characterization, clarify habitat relationships and reveal trends and patterns with minimal expression of the noise typical in community data. With ordination techniques, similar entities are placed close to each other while dissimilar species or samples are located far apart in ordination space.
In community analysis involving large data sets that have several community gradients and high variability, as in the case of this research, detrended correspondence analysis (DCA) and non-metric multidimensional scaling (MDS) have been shown to be highly effective (Gauch 1982; Clarke and Warwick 2001). These robust methods of multivariate analysis are relatively free from distortion and give equal emphasis to all data. These quantitative techniques are useful in identifying differences in community types and environmental gradients. Principal components analysis (PCA) is more appropriate for environmental variables than for species data with its large percentage of zero counts. Axes can be normalized so all data have comparable, dimensionless scales. Extrinsic analysis linking environmental variables to biological factors can then provide environmental interpretation.
References:
Brown, E. K., Cox, E.F., Tissot, B., Jokiel, P. L., Rodgers, K.S., Smith, W.R., and Coles, S.L. 2003. Development of benthic sampling methods for the Coral Reef Assessment and Monitoring Program (CRAMP) in Hawai’i. Pacific Science 58 (2):145-158.
Clarke, K.R., and Gorley, R.N. 2001. PRIMER v5: user manual/Tutorial. PRIMER-E: Plymouth, United Kingdom. 91 pp.
Clarke, K.R., and Warwick, R.M. 2001. Change in marine communities: an approach to statistical analysis and interpretation. 2nd edition. PRIMER-E.: Plymouth, United Kingdom.
Gauch, H.G. Jr. 1982. Multivariate Analysis in Community Ecology. Press Syndicate of the University of Cambridge, New York, NY. 298 pp.
Last Update: 04/21/2008
By: Lea Hollingsworth
Hawai‘i Coral Reef Assessment & Monitoring Program
Hawai‘i Institute of Marine Biology
P.O. Box 1346
Kāne‘ohe, HI 96744
808-236-7440 phone
808-236-7443 fax
email: jokiel@hawaii.edu