Training Workshop, Plymouth, UK: 31 October – 4 November 2005 on
Analysis of Multivariate Data from Ecology and Environmental Science using PRIMER v6
taken by PRIMER-E and the Plymouth Marine Laboratory, and held at the Marine Biological Association, Citadel Hill
Content
The workshop will take place over five days and will cover the statistical analysis of assemblage data (species by
samples matrices of abundance, area cover etc) and/or multi-variable environmental data which arise in a wide range
of applications in environmental science and ecology, from local environmental impact assessments, through basic
biological studies (e.g. of dietary composition) and monitoring of large-scale biodiversity change, to purely physical or
chemical analyses. The methods covered are generic and applicable in terrestrial, freshwater and palaeontological
contexts though the examples used in the workshop will all be from marine and estuarine studies. Many of these are
of hard substrate, soft sediment or fish assemblages monitored for environmental impacts resulting from marine oil
operations, organic enrichment, physical disturbance, climate change etc, but also covered are more fundamental
biological studies, linking faunal patterns to physico-chemical variables and testing in field/mesocosm experiments,
and environmental studies, analysing suites of biomarkers, tissue/water contaminants, particle size analyses etc.
The workshop will primarily be led by Dr K R Clarke (PRIMER-E and an honorary fellow of the Plymouth Marine
Laboratory). Bob Clarke is a researcher in statistical ecology and has worked for many years at the PML, where he
was responsible for adapting and developing the methods underlying the PRIMER package. Guest lectures and
practical sessions will probably also be taken by Dr R M Warwick (honorary fellow, PML), Dr P J Somerfield
(Biodiversity Group, PML) and R N Gorley (PRIMER-E, responsible for design/coding of the Windows versions of
PRIMER). The programme will be a mixture of lectures on the methodology and computer practical sessions,
analysing real case studies, combined with the opportunity for participants to bring some of their own data to the
workshop. The emphasis throughout is on practical application and interpretation, the theoretical aspects (e.g. the
multivariate statistical methods which are the core of the course) being carefully selected to be those that are simple
to describe, robust to operate and easy to interpret, so that no prior statistical knowledge is assumed.
The exposition will cover the features available in the PRIMER (for Windows) package (Plymouth Routines In
Multivariate Ecological Research), which covers a range of univariate, graphical and multivariate routines: hierarchical
clustering into sample (or species) groups (CLUSTER); ordination by non-metric multidimensional scaling (MDS)
and principal components (PCA) to summarise patterns in species composition and environmental variables;
permutation-based hypothesis testing (ANOSIM), an analogue of univariate ANOVA which tests for differences
between groups of (multivariate) samples from different times, locations, experimental treatments etc; identifying the
species primarily providing the discrimination between two observed sample clusters (SIMPER); the linking of
multivariate biotic patterns to suites of environmental variables (BIO-ENV); comparative (Mantel-type) tests on
similarity matrices (RELATE); standard diversity indices; dominance plots; species abundance distributions and
simple species-area curves; aggregation of arrays to allow data analysis at higher taxonomic levels; and matching of
sample patterns from different faunal arrays (BVSTEP, a stepwise algorithm generalising BIO-ENV which can be
used, for example, to find ‘influential species’, and 2STAGE, a second-stage MDS in which relationships between a
large set of ordinations can be visualised). A further unique feature of PRIMER is the ability to calculate biodiversity
indices based on the taxonomic distinctness of the species making up a quantitative sample or species list, indices
whose statistical properties are robust to variations in sampling effort. These routines (TAXDTEST) allow hypothesis
tests for change in biodiversity structure at a location, by comparison with a regional ‘species pool’, and permit
comparisons of biodiversity patterns over wide space/time scales, when sampling effort is not controlled.
Lectures will also cover additional techniques available in a new PRIMER version (v6), to be released by the time
of the workshop. These include: dispersion-weighted similarities, which exploit replication to improve the
explanatory power of multivariate displays, by downweighting contributions from common but ‘noisy’ species and
upweighting less common species which are consistently observed; new global permutation tests for the
significance of dominance curves and biota-environment relations found by BIO-ENV (adjusting for selection
bias); generalisation of similarity percentage breakdowns (SIMPER) to environmental variables and two-way
layouts; non-parametric linkage trees, which relax the implicit constraint in BIO-ENV of additive environmental
effects on biotic composition; a new class of taxonomically-based similarity measures, which extend the concept of
taxonomic distinctness to multivariate analyses, etc. This is combined with many new features: calculation of a
wider range of similarity coefficients, better treatment of missing data, facilities to navigate and save the
workspace, improved MDS plots and diagnostics, merging sheets with non-matching species lists etc
This new version 6 of PRIMER will be used as the workshop software and new purchase of v6, or upgrade from
v5 to v6, will be a pre-requisite for attendance. Ordered software licences will be distributed at the start of the
workshop. Desktop PCs will be available for the lab sessions, to be shared (optimally) within groups of three,
though laptops may also be brought (spec: Win2000 or later, with 128 Mb RAM, and preferably Excel installed).
Training Workshop, Plymouth, UK: 31 October – 4 November 2005 on
Analysis of Multivariate Data from Ecology and Environmental Science using PRIMER v6
taken by PRIMER-E and the Plymouth Marine Laboratory, and held at the Marine Biological Association, Citadel Hill
This course runs for 5 full days, from 09.00 Monday to 17:00 Friday, with an opportunity on Wednesday afternoon to
visit the National Marine Aquarium in Plymouth and to explore the National Marine Biological Library at the MBA,
with the help of the chief librarian. The course is suitable both for those new to this area and those who have some
previous experience of PRIMER or other multivariate methods but wish to understand more of the background,
improve their practical, interpretational skills with these methods, or be guided through the new developments in the
finalised PRIMER v6, which will be on general release by the time of the workshop.
WORKSHOP COSTS
These are in two parts, a course fee and a single-user PRIMER v6 licence fee. (Participants will not normally be
allowed to claim temporary use of someone else’s licence.) The lab sessions will be conducted entirely with the
new version 6 of PRIMER, and all participants will require a v6 licence. There are upgrade prices for v5 holders.
Course fee (5-days): £550, reduced to £385 for full-time, registered students. This includes substantial mid-day
meals on Monday-Friday, teas & coffees during breaks, but not overnight accommodation or other main meals.
Also included is a Monday evening reception, a visit to the National Marine Aquarium on Wednesday pm, and a one-year membership of the
Marine Biological Association (without journal). The latter allows particpants free access to MBA facilities that week (NMB library, common
room, terminal room, computing support, car parking, reasonable phone use etc), and library use for the following year; also a further week’s
bench space during that year (bench fees waived). Existing (continuing) members of the MBA pay a reduced fee of £520, or £365 for students.
PRIMER v6 single-user licence fee: £560 (full licence – public or private sector use), reduced to £280 (academic use,
staff or students, within a university context). These prices are reduced by 25% for the second or subsequent v6
licences purchased for a single site address (a department, for universities), and by 50% for the fifth or subsequent v6
licences at a single site. Registered owners of a v5 licence can upgrade to v6 for 50% of these prices.
Some examples:
a) two university participants from the same department, neither with v5, pay (£280+£210)/2 = £245 each;
b) three government staff from the same lab, two of whom already have v5 licences, pay a total of £280 (upgrade) + £210 (upgrade) + £420
(new licence) = £910 between them.
Note: The software will not be available prior to the workshop.
VAT. In addition, VAT will be charged on all fees at 17.5%, with the exception of a) non-EC participants, and b)
non-UK EC participants who can provide the VAT registration number for their institution.
----------------------------------------------------------------------------------------------------------------------------------------------------- ---BOOKING FORM Please e-mail/post/FAX/phone the following information to Cathy Clarke at
E-mail: admin@primer-e.com; Post: 6 Hedingham Gardens, Roborough, Plymouth PL6 7DX, UK; Tel/Fax: +44(0)1752 783366
She can clarify your current software licence position and can arrange accommodation in nearby hotels or guest houses
Name: ………………………………………….
Organisation: …………….…………..…..…………………………………...…………..
E-mail: …………………………………………
Address: …………………………...………………………………………….….……….
Tel: …………..………… Fax:……………………....
…………………………………...……………………………………………..
Please tick the boxes [], as appropriate
………………………………………………………………………………....
Fees: I wish to be invoiced for the following (note that invoices must be settled by 31 October 2005, by transfer, cheque, card or cash):
[ ] the full course fee
[ ] a discounted student course fee
[ ] a new PRIMER v6 licence
[ ] an upgraded PRIMER v6 licence, from PRIMER v5
[ ] I qualify for discount as an existing member of the MBA (your existing membership must be renewed by direct debit)
[ ] I am from a (non-UK) EC institution whose VAT number is ………………………………………………………..……………………..
[ ] I require the invoice to be sent elsewhere (specify): ……………………………………………………………………………….……….
Accommodation:
………………………………………………………………………………………..
[ ] I would like you to arrange accommodation. I plan to arrive on …………………..……….….. and leave on .…………………………
(note: the course commences at 9am on Monday 31 October and finishes late afternoon on Friday 4 November)
[ ] I would like a room at one of Plymouth’s major hotels: this is likely to cost around £70 a night, including VAT, bed & breakfast only
[ ] I would like a room in a bed & breakfast guest house. No evening meal will be obtainable there (though there are many eating places
nearby) and single room, en suite prices, including breakfast, start from about £30 per night, including VAT
All hotels will be <1km from the venue. Participants will be responsible for settling their own bills with the hotel or guest house on departure
Training Workshop, Plymouth, UK: 31 October – 4 November 2005 on
Analysis of Multivariate Data from Ecology and Environmental Science using PRIMER v6
taken by PRIMER-E and the Plymouth Marine Laboratory, and held at the Marine Biological Association, Citadel Hill
Programme
Monday, 31 October
09:00-09:15
Introduction
09:15-10:45
Lecture: Measures of resemblance (similarity/dissimilarity/distance) in multivariate structure for
assemblage & environmental data, including pre-treatment options (standardisation,
transformation, normalisation) and the effects of different coefficient choices
10:45-11:00
Coffee break
11:00-11:30
Lecture: Hierarchical clustering of samples (CLUSTER)
11:30-12:45
Introduction to PRIMER v6 and lab session on similarity options and CLUSTER
12:45-14:00
Lunch break
14:00-15:00
Lecture: Ordination (of environmental data) by Principal Components Analysis (PCA)
15:00-16:45
Lab session on ordination by PCA (coffee break at 16:00-16:15)
16:45-18:00
Lecture: Ordination (of assemblage data) by non-metric Multi-Dimensional Scaling (MDS)
18.00-19.00
Wine and ‘nibbles’ in the Common Room at Citadel Hill
Tuesday, 1 November
09:00-10:45
Lab session on ordination by MDS, and ‘own data’ session*
10:45-11:00
Coffee break
11:00-12:00
Lecture: Multivariate testing for differences between groups of samples (1-way ANOSIM), and
comments on power
12:00-12:45
Lab session on 1-way ANOSIM
12:45-14:00
Lunch break
14:00-14:45
Lecture: Multivariate testing (2-way ANOSIM, with replication).
14:45-15:15
Lab session on 2-way ANOSIM
15:15-16:00
Lecture: Determining variables which discriminate groups of samples (1- and 2-way similarity
percentages, SIMPER), both for species and environmental variables
16:00-16:15
Coffee break
16:15-16:45
Lab session on 1-way & 2-way SIMPER
16:45-18:00
Lecture: Aggregation to higher taxonomic levels, and multivariate measures of impact: in metaanalyses of different impact studies; in increasing multivariate dispersion in response to stress
(MVDISP); and in breakdown of spatial serial change in communities
Wednesday, 2 November
09:00-10:00
Lecture: Linking potential environmental drivers to an observed assemblage pattern, via bubble
plots and the matching of multivariate structures (the BIO-ENV procedure)
10:00-10:45
Lab session on draftsman plots, PCA and BEST (BIO-ENV)
10:45-11:00
Coffee break
11:00-11:30
Lecture: Linking to environment: linkage trees (a ‘classification and regression tree’ approach)
11:30-12:45
Lab session on the LINKTREE routine and ‘own data’ session
12:45-14:00
Lunch break
14:00-16:30
Visit to the National Marine Aquarium, Sutton Harbour, Plymouth (or free time)
17.00-18:00
Visit to the National Marine Biological Library at the MBA, Citadel Hill (or free time)
Thursday, 3 November
09:00-09:45
Lecture: Diversity measures (DIVERSE) and comments on sampling properties and multivariate
treatment of multiple indices. Dominance plots and tests for differences between sets of curves
(DOMDIS), particle-size distributions etc
09:45-10:45
Lab session on DIVERSE, dominance plots and testing sets of curves in v6 (DOMDIS)
10:45-11:00
Coffee break
11:00-12:00
Lecture: Taxonomic (or phylogenetic) diversity and distinctness for quantitative data, or simple
species lists, as valid biodiversity measures (DIVERSE) over broad spatial and temporal scales;
sampling properties and testing structures (TAXDTEST)
12:00-13:00
Lab session on DIVERSE and TAXDTEST in v6
13:00-14:15
Lunch break
14:15-15:15
Lecture: Comparison of multivariate patterns I: Global hypothesis tests of no agreement between
two resemblance matrices (RELATE), comparing assemblage (or environmental) structure with
linear or cyclic models in space and time; also of no evidence for a biota-environment link,
allowing for the selection effects in finding an optimum match (the global BIO-ENV test)
15:15-16:00
Lab session on RELATE and the global BIO-ENV test in v6
16:00-16:15
Coffee break
16:15-18:00
Lab session on Fal case study, or further ‘own data’ session
Friday, 4 November
09:00-10:00
Lecture: Comparison of multivariate patterns II:
a) Testing in a 2-way layout (ANOSIM) with no replication;
b) Stepwise form of the BIO-ENV routine (BVSTEP) generalised to other comparisons, e.g. species
subsets determining overall assemblage pattern or delineating gradients, subsets of environmental
or biomarker variables acting as a ‘proxy’ for the full set, etc
10:00-11:00
Lab session in v6 on ANOSIM for 2-way tests & the BEST (BVSTEP) routine for selection
11:00-11:15
Coffee break
11:15-12:00
Lecture: Comparison of multivariate patterns III: Second-stage analysis (2STAGE) to compare
taxonomic levels and transformation or coefficient choices; also for a possible testing framework in
some repeated measures designs
12:00-13:00
Lab session on 2STAGE
13:00-14:15
Lunch break
14:15-15:15
Lecture: Further new tools in v6:
a) A global test for the presence of minimal multivariate structure in a priori unstructured biotic or
environmental samples, using similarity profiles (the SIMPROF test); also missing data estimation
b) Downweighting species whose individuals are strongly clustered (Dispersion weighting)
c) Taxonomic distinctness concepts used to define new similarity coefficients appropriate for data
with few, or no, species in common (Taxonomic dissimilarity)
15:15-16:00
Lab session on the v6 SIMPROF tests in CLUSTER, and 2STAGE to compare similarity measures
16:00-16:15
Coffee break
16:15-16:30
Wind-up session: any remaining questions
16:30-17:30
Further own data sesssion (optional)
________________________________________________________________________________________________________
* Throughout the lab sessions, participants will be given real literature data sets to analyse, but they may wish also to bring
their own data to try out, at any stage. These should be in the form of simple rectangular arrays, preferably with variables (e.g.
species) as rows and samples as columns, stored as an Excel spreadsheet. All the entries should be numeric, whether for
species or environmental-type variables (use 1/0 for presence/absence of species); non-numeric information on characteristics
of each sample (factors) is placed below this table, in the same columns, separated by a blank row