• The guides on the Help menu do not work
• Problems following instructions for zooming on graph
• When a data file is opened, all the data are dumped into the first cell, rather than opening in the grid properly
• I entered the data in a spreadsheet program, and saved it as a csv file. When I try to open it in CAP, the numbers are separated by ; not , so the analysis will not run.
• The TWINSPAN dendrogram cluster id is not working
• I have removed sparse columns or rows from my data set, now some methods, including TWINSPAN, will not run properly
• Interpretation of TWINSPAN out results
• Invalid floating point operation
• Error messages saying "'' is not a valid floating point value" or "Range Check Error"
• I/O error 32 - access denied
• My files do not appear to be saved
• I want to use a similarity or distance measure that is not offered by CAP
• I have a huge data set. Can CAP handle it?
• My data set has a large number of columns (sites/samples), but Excel will only allow me to have up to 255
• How long will it take to run MDS on a large data set?
• None of the above

Recent versions
I want to use a similarity or distance measure that is not offered by CAP
Contact PISCES; we may be able to add the measure to the program

Error messages saying '' is not a valid floating point value or "Range Check Error"
This will occur if the raw data holds columns or rows that consist of all 0s. Remove blank columns and rows by using '0 issues' in the working data window. It may also occur if the raw data holds a blank cell. In some cases CAP will identify the problem cell which should be edited. Normally it is because the data has been prepared in a spreadsheet using blanks to represent zero values.

Invalid floating point operation
This often indicates that there are rows or columns with no data in them. Use the Zero Issues button on the working data tab to find and remove the offending row or column.

I have a huge data set. Can CAP handle it?
Older versions of CAP were limited to a 1000 species (rows) x 1000 samples (columns) data set. Version 3.0 allows effectively unlimited data set size: the power and available memory of your computer is the only limiting factor. Most reasonably fast computers should easily handle a 5000 x 5000 data set.

In TWINSPAN OUT: concerning the list of Indicators and their sign (i.e. Species 1 (+), Species 2 (-)), does the (+) represent species present in the class and (-) represent species NOT present in the class? If so, then are the only sample points (quadrats) representing the TWINSPAN classes those listed under the positive group?
In the TWINSPAN output Species1 (+) indicates that species1 is characteristic of the quadrates classified to the right of the centroid of the primary axis of the ordination. It does not mean that the Species1 is absent in all the quadrates to the left of the centroid. An output of, say, Species2 (-) would mean that Species2 is characteristic of quadrates to the left of the centroid. Remember that if TWINSPAN is not undertaken on presence/absence data it uses pseudospecies so the same species can be an indicator at different levels of abundance.

In the case of presence/absence data there will certainly be a strong tendency for a positive species only to be present in the group of quadrats to the right. However, this is not necessarily always the case.

My data set has a large number of columns (sites/samples), but Excel will only allow me to have up to 255
A common problem with large data sets. The simplest way is to arrage your data the other way round in Excel, so that rows represent samples/sites, and columns represent species. You can then have up to 255 species, and over 65,000 samples. When you open the data set in CAP, you can then use the Transpose function on the Working Data Set page to restore the data to the right way round before performing your analyses.

Alternatively, use our ListCombiner utility to combine large data sets effortlessly!

Version 4 & earlier
The guides on the Help menu do not work
To ensure that the guides and tutorials work correctly, please make sure that both your default internet browser, and Internet Explorer, will allow popup windows (i.e., any popup-blocking utility is disabled). Also, playing the demonstrations requires that both Internet Explorer and your default browser have the Macromedia Flash player installed as a plugin. If the plugin is not installed, the program will seek to download and install it from the internet. If your PC is connected to the internet, this process will occur automatically. If your PC is not connected to the internet, or is blocked by a firewall, this may interfere with the playing of the guides.

I/O error 32 - access denied
This will occur if the data file you are trying to open is currently being used by another program - normally the spreadsheet which was used to organise the data. Close the file in other programs and try again.

Version 3 & earlier
Problems following instructions for zooming on graph
In some old printed copies of the CAP instruction manual on page five, it says that to zoom in on an area of a graph you move from the top right to bottom left. This should have read top left to bottom right. Please download the latest CAP manual.

When a data file is opened, all the data are dumped into the first cell, rather than opening in the grid properly.
This is usually because there are one or more blank cells in the second row of data. If the blanks are replaced by zeros, or another row with no blanks is put in the second position, the problem should disappear. Row 2 is the crucial one; blank cells are tolerated elsewhere.

I entered the data in a spreadsheet program, and saved it as a csv file. When I try to open it in CAP, the numbers are separated by ; not , so the analysis will not run.
This is because some non-British systems use ; instead of , to separate values in a csv file. Open Windows Explorer, and change the file extension from csv to txt (i.e. Filename.csv becomes Filename.txt). Open the txt file in Word or another word-processing program. Use the Find/Replace function to replace every ; with a , then save the file again. Change the txt file extension back to csv. It should now open and run perfectly in CAP.

How long will it take to run MDS on a large data set?
MDS computations on a 150 species by 150 sample array will be completed on a 266 Pentium in about 2 minutes. On faster modern machines, it will be just a few seconds, if not instantaneous.

Version 1
The TWINSPAN dendrogram cluster id is not working
This was fixed in version 1.1.2.

I have removed sparse columns or rows from my data set, now some methods, including TWINSPAN, will not run properly
If you use the 'Remove Sparse Columns' and 'Remove Sparse Rows' functions, it is possible that rows and columns in the data set will now be left with no non-zero observations. When you remove sparse columns or rows, always follow up by using the 'Delete 0 columns' and 'Delete 0 rows' functions.

My files do not appear to be saved
This is often caused by the lack of the correct file extension. The program only shows files with the .csv extension. To see other files in the open file dialog type *.* into the file name box and press return. - WARNING this will show all the files in the directory - whether they are compatible with the program or not. If you have saved a file without an extension either add the extension outside the program or open the file and save with the correct extension using Save As.

Here is the update history for CAP. To upgrade to the latest version, please contact PISCES. The cost of upgrading is:
Version 1, 2, 3, 4 or 4 to the latest version: £79, plus postage (Buy online NOW, or see How To Buy)
Users who have already purchased Version 6.x can upgrade to the latest FREE - please contact PISCES.

Version 6.3.4.x; September 2023

• Fixed a bug with the mislabeling of the vectors in PCA.
• Program no longer tries to store the name of the demo data set when closing it.
• Minor bug fixes and cosmetic improvements.

Version 6.2.4.x; August 2019

• Updated group popup list when editing name in popup window.
• Minor bug fixes and cosmetic improvements.

Version 6.2.3.472; Spring 2018

• Replaced PCA with new version.
• Removed redundant DLLs.
• Reload raw data button always shows.
• Cluster charts now fit to screen with short stub.
• Improved data checking speed on opening file.

Version 6.0; started Feb. 2017

• Implemented use of R code from within the program.

Version 5.6; Jan 2017

• Removed an old reference to an unused .ini file.
• Fixed error on clicking on the Create Group button.
• Grouping tab creates a new group name if group is deleted from middle of data and a new group added.
• Grouping tab columns automatically resize.
• Grouping tab retains sort order after renaming a group.
• Working Data tab warns of empty rows or values in data set when deleting rows or colums.
• Grouping Tab Select Variable drop-down is now in alphabetical order.
• Improved checking of column names for duplicates.
• Improved File: New - names, data check, etc.

Version 5.5; July 2016

• Fixed font colour on groups when background is dark.
• Fixed sorting groups by value when a value has been removed from the data set.
• Fixed scatter plot - in compare samples - not picking up new values.

Version 5.4; Feb. 2015

• Gradient on all 3D points removed.
• Fixed group editing, not having a known group on startup.
• Fixed multiple tool bars in graphs.

Version 5.3.3.472, July 2014

• Fixed memory issues for 64-bit version of Windows 7 OS.
• Fixed errors related to spaces after sample names.
• Fixed error in TWINSPAN handling of decimal numbers.
• Fixed error in TWINSPAN handling of data sets of over 500 species.
• Fixed Save As error when data is pasted into a new grid.
• Minor bug fixes.
• Updated Help system to reflect the above.

Version 5.0.0.465, Spring 2014

• Windows 8 compatible.
• Methods for selecting and editing group membership updated - now much simpler and quicker!
• Dendrogram plotting options completely revised.
• Scree plot added to PCA analysis, showing the fraction of total variance explained by each Principal Component.
• Bubble plot added to NMDS, showing relative abundance of selected variables and the contribution of each variable to the ordination.
• New data exploration options: Profile plot, Scatter plot and Matrix plot.
• Compare Samples facility more versatile.
• Print Preview and printing options completely revised.
• Video guides updated, and now hosted on YouTube.
• Minor bug fixes.

Version 4.1.3.384, December 2007

• Improvements to plotting of charts
• Windows Vista compatible
• Minor bug fix for TWINSPAN calculations for data sets with few or no zero observations

Version 4.0, June 2007

• Added Linear Discriminant Analysis (otherwise called Canonical Variate Analysis)
• Added Mahalanobis distance measure
• Compare Sample function allows the user to check for species in common between samples, and species unique to each sample
• Increased number of similarity/distance measures for Multidimensional Scaling (NMDS)
• Methods for data manipulation and transformation extended
• Ability to select group membership directly from a plot
• In PCA, plots of variables against axis scores can now be done
• Major improvements to plotting of charts; Themes introduced
• Complete revision of Help system
• Added range of video demonstration guides to using the program
• Redesigned to be clearly relevant to all fields of research that use multivariate methods including biology, geology, archeology, anthropology, economics and sociology. Includes example data sets from a wide variety of disciplines, and terminologies generally used in all fields of research.

Version 3.2, March 24th 2006

• Added Squared Chord distance measure

Version 3.11, Feb. 23rd 2005

• Minor bug fix in calculation of possible number of groups in ANOSIM for very large data sets.

Version 3.1, January 31st 2005

• Minor bug fix
• Powerstation_fish.csv now released as a sqrt dataset to overcome problems in TWINSPAN analysis
• Now exports charts in .png and .pdf formats.
• Improvements to dendrogram labelling and TWINSPAN output

Version 3.02, Sept. 10th 2004

• Minor bug fix

Version 3.01, July 7th 2004

• Corrected Range Check Error in Decorana and Reciprocal Averaging experienced by Windows 98 users

Version 3.0, released June 2004

• Unlimited data set size: data set size is now limited only by your computer's power and memory - even for highly complex calculations like TWINSPAN. Most reasonably fast computers should handle a 5000 x 5000 data set easily.
• Improved graphics: Plotting of graphs and dendrograms has been improved; in addition, CAP can now plot groups of samples in different colours and styles.
• New methods: 2 new methods for testing grouped samples have been added - ANOSIM and SIMPER
• Faster calculation: The speed at which CAP performs most calculations has been dramatically increased, thanks to new data array handling technology.
• Help system and manual: CAP's Help system has been much improved, and a new feature, Instant Assist has been added. This gives you help and information on the program and its methods exactly where you need it. The full Instruction manual has also been completely revised.

Version 2.15, released 2/5/03

• Minor alteration to calculation of similarity indices, incl. S4 and Kulczynski.

Version 2.14, released 16/4/03

• Minor alteration to labelling of PCA charts.

Version 2.13, released 06/02/03

• Twinspan output 'twinout.rtf' now saved to C:\Program Files\CAP, rather than to the folder containing the data file: prevents errors when running data from a read-only source such as a CD.

Version 2.12, released Feb. 2003

• Modification made to Sorenson distance calculation

Version 2.1 released 23/12/02

• Corrections implemented to clustering analyses

Version 2.06 released 13/12/02

• 1 - (Jaccards) and 1 - (Sorenson) distance measures added to list of similarity measures.

Version 2.04 released 27/8/02

• Minor bug fix

Version 2.03, released 17/7/02

• Matrices enlarged to overcome Range Check Error in TWINSPAN for large data sets.

Version 2.02, released 20/6/02

• Sites now coloured correctly on TWINSPAN dendrogram plot, if levels not set to '6'.
• Added [+] or [-] to indicator species on TWINSPAN dendrograms.
• Added hourglass cursor to some potentially long operations, i.e. transposing large data sets.

Version 2.01, released 22/5/02.

• In MDS, when stress is plotted against dimensions, now plots full number of dimensions selected.
• Dendrograms can now be exported, via the Export button on File menu.

Version 2.0, released 14/5/02

• Improvements in memory usage allow maximum size of data set to be increased from 500 samples x 500 species to 1000 x 1000 - even for TWINSPAN and DECORANA calculations.
• Improved chart editing and labelling functions; now allows graphs to be exported in .BMP, .EMF, .JPEG, .PCX and .PNG file formats, and chart data series as plain text, XML, HTML tables or in Excel format.
• CAP automatically checks for, and removes, blank cells and zero-sum rows on opening a data set.
• Rows or columns can be deselected, allowing you to work with only part of the data set.
• Help system and manual revised, and now include a Worked Example.
• New ordination method known as Species Filtering has been added.

Version 1.52 18/2/02

• Minor bug in old-style TWINSPAN output fixed

Version 1.51

• Updated grid.

Version 1.50 11/10/01

• PCA plot labelling improved

Version 1.4.2 - 23/8/01

• Labelling on TWINSPAN sample dendrograms improved.

Version 1.4.1 - 25/5/01

• Bug in graph export fixed.
• Option of removing labelling on TWINSPAN dendrograms added

Version 1.4 - 29/3/01

• Bray-Curtis similarity added.
• Czenkanowski renamed mean character difference.
• All distance measures implemented in clustering.
• Dendrogram printing improved.
• Improved graphs.

Version 1.3.2 - 16/11/00

• Association analysis bug fixed.
• Demo launched

Version 1.3.1 - 9/11/00

• Arrowheads added to PCA vector plots.
• 0 issues in summary table fixed.

Version 1.3 - 31/8/00

• Full chart editing.
• Grid print preview improved.
• Minor error in small dataset handling from TWINSPAN and DECORANA fixed.

Version 1.2 - 3/2/00

• Refresh error in dendrogram fixed.
• Dendrogram problem with negative diagonal plots fixed.
• Dendrogram printing improved.
• TWINSPAN bug fixed on high levels of cuts and divisions.
• Spellings corrected.

Version 1.1.2 - 26/8/99

• Misleading explanation in TWINSPAN dendrogram changed
• Cluster id button removed from TWINSPAN.

Version 1.1.1 - 20/7/99

• Minor error in diversive clustering setup fixed.
• Axis bug in diversive clustering fixed.

Version 1.1 - 8/7/99

• Non metric Multidimensional Scaling added.
• Resize species name column.
• Bug fix on Summary to show more than 19 rows of data.
• Bug fix for space row and column handling.
• Bug fix in TWINSPAN species dendrogram.
• Removed obsolete colour change button from dendrograms.
• Implemented scale on cluster dendrograms.
• Correct labels on cluster dendrograms.
• Dynamic sizing in cluster summary grid.

First release Version 1.0 May 1999