ENVIRONMENTAL STABILITY AND COMMUNITY PERSISTENCE - A MULTIVARIATE PERSPECTIVE

Six physical and hydrological variables were used to assess environmental stability at sites on 10 contrasting streams in the Southern Alps of New Zealand. Five of the streams were spring-fed and initially designated ''stable'', and the others, which were predominantly catchment-fed, were designated ''unstable''. At each site, depth, current velocity, and water temperature were measured monthly for 19 mo, and the distances moved by marked stones in three size groups were determined over 18 mo. Stone invertebrate communities were sampled at each site at three monthly intervals. Tractive force measurements and the Pfankuch stability index were also calculated. Monthly depth and current variability, temperature range, Pfankuch stability scores, and substrate movement were all greater at the five ''unstable'' sites, but the rank order of sites obtained with each measure was not consistent. Tractive force was the only stability measure that did not differ significantly between ''stable'' and ''unstable'' streams. Principal components analysis (PCA) was used to combine values for all six variables into single multivariate instability scores (PCA scores for Axis 1). These scores were strongly correlated with all individual stability variable scores with the exception of those for tractive force. We suggest that the effects of environmental stability on community structure should be assessed using a measure that is representative of all the physical characteristics at a study site, and we believe the multivariate instability score goes some way towards achieving this. Such a procedure, however, does not negate the use of individual measures for examining specific environmental relationships as well. Although differences in the persistence of some community characteristics could be detected using the initial ''stable/unstable'' groups, others could only be seen when plotted on a more continuous scale using the multivariate instability scores. Persistence of the dominant invertebrate taxa was high at all sites, but persistence of the entire fauna was higher at the stable sites.