Hypothesis tests‎ > ‎


This page is a stub
This page is under construction. If you would like to contribute to this endpoint, please let us know through our user forum!
== incomplete ==

The main idea...

The similarity profile routine (SIMPROF; Clarke et al. 2008) is a hypothesis test which may be used during exploratory analyses. SIMPROF tests data, with no required a priori groupings (in contrast to e.g. ANOSIM), against the null hypothesis of "absence of structure". In type I SIMPROF, the null hypothesis used is: 'sample (i.e. object) abundance profiles are homogeneous and have no multivariate structure', while in type II SIMPROF the null hypothesis is: 'species (i.e. variable) abundance profiles are homogeneous and have no associations'. Type III SIMPROF may follow type II SIMPROF to test whether clusters of species (variables) are coherently associated (Somerfield and Clarke, 2013).

Clarke et al. (2008) suggest the combination of SIMPROF with hierarchical cluster analysis to indicate which clusters have non-random structure and thus are more interesting for further analysis. Further, Somerfield and Clarke (2013) describe how SIMPROF may be used to find groups coherently covarying species (i.e. variables).

SIMPROF has been used in several microbial ecology contexts (e.g. Kelly et al. 2012; Kim et al. 2014).