As a part of VSNi’s on-going commitment to supporting educators across the world, we have launched GenStat for Teaching - a free version of GenStat for educators and students. In today’s world of tightening budgets and justification of spending it’s vital that those at the forefront of teaching and coaching the next generation of scientists can access the best tools for in statistical analysis. With GenStat for Teaching now available free to all students and teachers world-wide, there is no reason why students cannot be taught using the best.

GenStat is known across the globe for its world class statistical tools and data analysis capability; from linear modelling to ANOVA and REML, in fact all that teaching requires. GenStat does, after all, stand for General Statistics! Its history and pedigree provides its users with reliability, trust and security.

On top of this, GenStat is one of the easiest data analysis packages on the market, with a clear and straightforward menu system to guide users through their analyses, backed up with dialogue boxes providing hints and alerts. A Save Session facility allows GenStat to be tailored around teaching sessions, breaking down the steps to fit with the learning path. A snapshot of a session can be taken at any time, and restarted at a later date, with no need to run through all the analyses again. These two benefits alone make GenStat an ideal tool for teaching; couple this with extensive statistical tests included in the software and you have a powerful tool to aid the teaching of statistics and data analysis techniques.

Additionally all users have access to the resources on our website with training available and tutorials for regression and ANOVA.

Download your free copy of GenStat for Teaching here .

New edition dispatch changes

All supported users should by now have received their CD for the GenStat 11th edition, and we hope you are enjoying and benefitting from the new developments.

In an attempt to reduce our carbon footprint, we are hoping to limit the amount we physically dispatch. As such we would like to make future upgrades available as download only from our secure website, and no-longer send out CD’s where possible. Should you still require a CD to be sent please could you email us, otherwise we will email details of any new upgrade and send you the download link.

We hope you see this as a positive step, as we do.

Technical tip - User Support

For more support and assistance don’t forget our on-line user guides for both GenStat and ASReml. These guides have also been updated and revised to include help on GenStat Discovery and GenStat for Teaching. The guides have everything from getting started to detailed statistical analysis, including reviews on the underlying methodology, explaining the output and describing the GenStat commands. Look at the full list of available documentation on our website.

Out and about with VSNi

A list of where VSNi will be this year is on our website.

On 21st July 2008 an enthusiastic group of GenStat users and developers gathered at the Agri-Food & Biosciences Institute (AFBI) in Belfast for the 14th European GenStat Applied Statistics Conference.

The programme of 12 talks was split evenly between developments and applications, with topics ranging from forest fires and salmonella in Australia to sea birds in Scotland. More locally, Irish subjects involved tuberculosis in dairy cattle and sex ratio bias in gall midges. Other application areas included microarrays, microneurography, environmental assessments and the attraction of pollen beetles to oilseed rape flowers.

A broad range of statistical topics were covered, including generalized linear mixed models, hierarchical generalized nonlinear models and meta analysis, in addition to the more usual ANOVA, REML and regression analyses. New GenStat facilities were also described, with talks on survey analysis and the new facilities in the 11th Edition for canonical multivariate analyses, graphics environments and for using mathematical algorithms from the NAG Library.

We enjoyed excellent weather, and those staying on for the Advanced Linear Models workshop on the following day also enjoyed the excellent food, drink and ambiance of Belfast during the intervening evening.

We would like to thank AFBI for hosting the meeting, and especially the local organiser Alan Gordon (on the right in the picture below with Roger Payne).

On 5-9th October, Roger Payne is again speaking at the Joint Annual Meeting of the GSA, SSSA, ASA, CSSA, GCAGS and HGA in Houston, Texas. Roger will be presenting on A Guide to Analysing Counts and Proportions in Complex Situations, during a session on New Statistical Techniques for the Analysis of Agricultural Experiments. Roger’s talk will describe the types of biological investigation that have led to the development of methods such as generalized linear mixed models and hierarchical generalized linear models. It will show how these methods extend the more familiar generalized linear models to allow you to take account of additional sources of error variation, such as blocking in a field experiment, or parental effects in animal experiments.

If you are involved in organising an event which may be of interest to VSNi and our users please let us know by emailing us.

Latest training courses

We have an ASReml course on 24-25th September. This will be held by Dr Arthur Gilmour and will include an Introduction to Mixed Models and ASReml and on the second day Genetic Analyses for plants and animals. Participants are encouraged to bring their own examples, which can be sent direct to Dr Gilmour a month before the workshop for preparation. A similar workshop will also be taking place in Buenos Aires, Argentina 9-12th September to include the following areas:

An applied workshop on Mixed Models for Plant Improvement using ASReml and r is planned for 2-5th November 2008, at the University of Western Australia, Perth. The workshop will present advanced statistical methods for the design and analysis of data arising from plant improvement programmes. Topics will include the design and analysis of single/multi environment and single/multi-phase experiments. Methods will also be presented for the integration of molecular marker and pedigree information into the analysis (and design) of these experiments.

As a part of our continued update and development of our courses, please let us know if you have any suggestions or topics for future training.

GenStat in Epidemiology

GenStat is well known and highly regarded throughout the world in its historical core area of biosciences, and specifically in agricultural research. The breadth of statistical analysis covered is well documented on websites, review articles and the like. As are the importance of its pedigree, developed, tried, tested and used by agricultural statisticians; the birthplace of GenStat (Rothamsted Experimental Station) being also the birth place of modern statistics with the likes of Sir Ronald Fisher, Frank Yates and Professor John Nelder all giving GenStat a certain kudos in statistical circles and the bioscientist’s world.

More and more disciplines are relying on statistics to uncover trends, causes and to better understand relationships between various factors. One area that has always understood the importance of statistics is epidemiology - the study of factors affecting the health and well-being of populations. Epidemiology is a vital discipline underpinning evidence-based medicine, for identifying risk factors for diseases and health effects.

The epidemiologist’s work ranges from investigations into disease outbreaks, clusters and exposure-response relationships, which may include the development of regression models to test hypotheses and estimate risk coefficients. The epidemiologist’s work at the Institute of Occupational Medicine in Edinburgh is designed to provide reliable information about health effects and risks for occupational and environmental hazards, with a view to addressing public and industry concerns, and providing a scientific basis for policies to limit disease. So it’s easy to see how a statistical analysis system such as GenStat is a vital tool for these researchers.

The IOM has been using GenStat for several decades in their studies on public health in the UK. Originally set up as a charity in 1969 to research coalminers’ lung disease, to continue a research programme set up by the National Coal Board’s medical service, the charity has been independent since 1990, and now provides research, consultancy, laboratory and measurement services in relation to potential health problems caused by occupational and environmental exposures. All the research reports published by the IOM since 1969 are available for free download from the on-line library.

GenStat has been used in a variety of different analyses, including epidemiological or observational data, which typically requires a regression model of some kind (linear, GLM, GAM, LMM, GLMM etc). It is also used for analysing data sets from designed toxicology experiments and for analysing cause-specific mortality data in comparison with reference rates.

A recent study looked at mortality rates in a group of almost 18,000 coalworkers from 10 collieries recruited from the 1950s onwards and followed up until the present time, of whom about two thirds are now deceased. One aim of the study was to compare the observed rates from certain causes of death with the male population rates for those causes in the regions where the coal pits are located. The calculations produce standardised mortality ratios (SMR’s) and their standard errors, using standard epidemiological methods.

GenStat used each individual’s entry and death or censoring dates to amass the person-years in the cohort, tabulating them by region, year and age (using GenStat’s option for sequential tabulation). The SMR calculations then used GenStat’s table manipulation functions to organise observed deaths and calculate expected numbers, ratio of observed to expected (SMR) and its standard error, etc. The outputs included overall SMR, plus a breakdown on 5 year-time groups that show how the healthy worker effect exists in the early part of the follow-up. The study has also been able to show that the risks of developing certain respiratory diseases increase with increased exposure to dust. Detailed results are available in a final report.

The summary results of comparisons of mortality in cohort with external reference rates are shown below. The table shows, for chosen cause groups, numbers of deaths, age- year- and region-standardised mortality ratios (SMR) and 95% confidence interval.

The graph shows the Standardised Mortality Ratio (SMR) for all internal causes over the length of the follow-up period, with years grouped. The solid line is the SMR while the dashed lines represent the 95% confidence interval. The dotted line shows the SMR equal to 100%.

For any complex statistical calculations a software programme that is easy to use and reliable is crucial, but specifically in this instance GenStat’s table functions make the SMR calculations “beautifully simple to program.” (Dr Brian Miller).

The ability to understand the causes of health issues, what factors may lead to ill health or mortality in populations are of critical importance world-wide: so a sound, reliable data analysis system such as GenStat is vital to assist with analysis and help produce scientifically based recommendations and policies.

Our thanks to Dr Brian Miller of The Institute of Occupational Medicine for his help in producing this feature. More information on the IOM can be found here.

Images/Tables with permission from IOM research report TM/07/06.

In support of this philosophy, for the first time, we are now offering GenStat free of charge to users in education, for teaching purposes. The ease of use and step by step processes in GenStat make it a natural choice for teaching, as it lends itself so well to structured learning.

Stewart Andrews, CEO says: “We are delighted to support teachers and educators in this way. We realise they may be using other packages and changing involves no little effort. All we would say is try it. We made this step as a result of direct feedback, particularly from those in bioscience using GenStat in commercial environments, who have a desire to see young graduates coming into their organisations with knowledge of GenStat. Of course, as with any free software, there is the risk of abuse but in the last five years our experience with the Discovery Edition has shown us that our users are a very honest group of people.”

Find out more here.

“GenStat is one of those packages with a reliable and road mapped programme of regular updates. GenStat upgrades have never been less than thorough, stable, significant and workmanlike progressions for one of the industry’s most serious packages; this is no exception.” So says Felix Grant.

He goes on to comment on the 26 new procedures in GenStat 11th Edition, highlighting those for Self Organising Maps (SOM) and canonical correspondence analysis, along with the directive level developments. Also highlighted are the new graphics enhancements.

You can read his full article here.

For the full list of the GenStat 11th Edition new features go here.

To download a trial copy or to obtain your upgrade of GenStat go here.

“…not only the study presented here but also nearly all research studies at ICRISAT use GenStat to meet their design and computing requirements”.

Subhash Chandra is the Head of Bioinformatics & Principal Statistician, at the International Crops Research Institute for the Semi-Arid Tropics, or ICRISAT, an internationally renowned, not-for-profit agricultural research organisation. As one of the fifteen Future Harvest Centres of the Consultative Group on International Agricultural Research (CGIAR), ICRISAT is well placed at the fore-front of agricultural research and development.

The Problem

Chickpea is very important, rain fed, cool season food legume, grown mainly by small farmers in the semi-arid topics, West Asia and North Africa regions. Molecular markers linked to traits of agro-economic importance, facilitate marker-aided selection of promising germplasm for rapid crop improvement. A biometric analysis was carried out using GenStat to identify microsatellite markers, out of a total of 21, tightly linked to root traits in chickpea.

The Solution

The study involved phenotyping data on 257 recombinant inbred lines (RILs) and genotyping data on these RILs for 21 microsatellite markers. GenStat’s REML facilities were used to obtain the best linear unbiased predictors (BLUPs) of average phenotypic performance of RILs. The Chi-square facilities were then used on the genotyping data on each marker to test for conformity to expected Mendelian segregation ratio, and on pairs of markers to statistically test the existence of linkage. The Kolmogorov-Smirnoff and Mann-Whitney U tests were used to compare the phenotypic distribution of genotypic classes for each marker to see whether the marker in question was significantly linked to traits. Multiple linear regression facilities, in combination with bootstrap and jackknife resampling procedures, were used for reliable and robust identification of the smallest possible subset of markers significantly linked to the root traits, treating a particular root trait as dependent and the markers as independent variables.

Subhash states that, “Using GenStat we could reliably identify one microsatellite marker that was consistently tightly linked to three of the four root traits. This is a very useful result to facilitate rapid crop improvement in chickpea.“ GenStat handled all analysis very well.”

Subhash continues, “GenStat at ICRISAT has been the major statistical computing software of choice for design and statistical analysis since 1979. It has very effectively met our design and statistical computing requirements over these years.”

“We chose to purchase GenStat as opposed to other packages after careful consideration. Following a trial run we were impressed by how easy to handle the package was. The programme is simply set out and allows users of all levels to easily navigate it”.

Helen Whitney is Technical Co-ordinator at Dalehead Foods. Established in 1969 it is now one of the leading suppliers of pig products to UK supermarkets. The company boasts a highly experienced research and development staff and operates over 250 farms, mainly in East Anglia. Animal welfare is important to the company and all Dalehead’s livestock are housed on free draining land with plenty of straw for bedding.

The Problem

Dalehead carry out work on their purpose built trial unit, with the aim of reducing the overall cost of production for their farmers. To do this they investigate how possible changes to the feeding programmes used, or the genetic lines of pigs they select from, influence the overall cost of production and quality of meat produced. They do this using designed experiments. The performance indicators growth, feed intake and Feed Conversion Ratio, as well as health of the pigs are monitored throughout the trials. Certain post slaughter measurements are also recorded.

The Solution

GenStat’s extensive Analysis of Variance makes easy work of the range of designs used by the Dalehead scientists. Factorial designs are regularly used and the ability to handle covariance in designs is imperative. GenStat’s extensive regression facilities are also regarded as essential tools for Dalehead researchers.

“The set up of the output is clear and concise, and any anomalous results are clearly identified.”

Helen states that “after consideration of the results generated by GenStat from one particular trial which showed significant differences in performance of pigs on different dietary treatments, we have made changes to our current feeding programme which should in turn result in cost benefits to our farmers.”

GenStat’s interactive graphics capabilities were incorporated into reports to “clearly and concisely” demonstrate the findings of analyses.

Technical Support and Training

As GenStat plays an integral role to research at Dalehead, the company subscribe to the annual technical support and upgrade policy. This ensures that researchers always have the latest developments and statistical advances in GenStat at their fingertips. The support policy also gives the company the flexibility to install GenStat on home and laptop PC’s; a handy benefit when researchers have to work remotely.

As supported users, Dalehead researchers have the security of knowing that should they need advice, the developers of the software are easily accessible and ready to help.

Dalehead also chose to take advantage of the in-house training opportunities available to GenStat users. VSN’s CIPD qualified training staff ensure that Dalehead researchers were given a learner-centred, positive experience of GenStat training that resulted in improved performance in the work place.

Whitney concludes, “…we are particularly impressed by the ease of use of our GenStat programme. It provides a useable, clear as well as respected output. The input boxes are easy to use, and help should you need it is readily available.”

“GenStat is well suited to our agricultural applications; much more than any other system we looked at.”

Curtis Lee is President at Agro-Tech, a contract research and development company based in North Dakota. The company conducts privately funded research within the agribusiness and biotech industries.

The Problem

As a consultant, Curt Lee operates in perhaps the most demanding of climates. The work he encounters is challenging, varied, and his reputation depends on the accuracy, reliability and speed of analyses presented to Agro-Tech clients.

In addressing Agro-Tech’s statistical software needs, Curt had to find a system that:

1. Delivered the power, the level of flexibility and the statistical pedigree necessary to handle the requirements of even the toughest of consultancy projects.
2. Offered a user-friendly interface, minimising the start-up time for new or inexperienced users to gain confidence with the system.
3. Offered an affordable cost base, both in terms of initial set-up costs, and future upgrades.

The Solution

After visiting the VSN website, Curt downloaded the fully functional, 30 day trial version of GenStat. GenStat has been used successfully by agricultural scientist for over 30 years; a solid reputation confirmed by some of Curt’s colleagues in the agricultural industry. On the completion of the trial period, Agro-tech purchased a full license, feeling sure that they had found the software solution for them.

Power and Flexibility

The trials undertaken by Agro-Tech can range from simple randomised block designs, to more complex slip-plot and other multi-layers designs. A typical example here is a split-plot design to evaluate the effect of starter fertilizers on field corn grown under conventional till and n-till systems. The ease with which GenStat could handle multi-layered experiments like this impressed Curt. He found the transition from simpler designs straightforward, and the formatting of the analysis of variance output; a section of the ANOVA table for each strata of the design, “very useful” in presenting experimental results in a clear way. Curt discovered that GenStat’s comprehensive diagnostic tools enable you “to easily visualise your data with graphics”, checking the assumptions of the models fitted – essential features for accountability. The ANOVA facilities in GenStat allow Curt to analyse any generally balanced design that a customer may require. GenStat’s REsidual Maximum Likelihood (REML) facilities however, provide him with the additional power to analyse unbalanced designs, mixed and spatial models.

“The Introduction manual is excellent”.

User-Friendly Interface

Even though GenStat is “a powerful program”, Curt was impressed at how user-friendly the pull-down menu interface is. He estimates that “most people would be up and running with GenStat within a couple of hours”. In an environment where time is money; this is a key benefit. Obtaining results from GenStat is painless. Curt says “one of the nice things I like about GenStat is when our customers come on tours, I can quickly give them a printed summary of their analysis – they feel this adds a lot of value to our service”.

“I can quickly upload data from a trial and produce graphics. GenStat is a powerful program”.

Cost Benefits

GenStat is a complete statistics system; there are no additional modules to purchase. This means that if Curt needs to analyse a split-split-plot experiment one day and fit a generalized linear model the next day – no problem, he always has the tools to hand in GenStat. Agro-Tech subscribe to the annual support and maintenance policy for GenStat. This ensures that they:

• receive automatic software upgrades
• have access to technical support from the GenStat development team
• have greater flexibility in working practice with additional copies for use on a home PC or laptop.

Curt feels that these features, together with the competitive pricing structure, renders GenStat a cost effective statistical solution; not only for the larger corporation, but also for small businesses.

We hope you are enjoying using GenStat Discovery Edition. In a continued effort to improve and progress both the software and our services we would be grateful if you could spare 10 minutes of your time to complete a short survey - accessible via the link below.

Take me to the survey

As always, we welcome your feedback and are happy to receive any comments and suggestions not covered by the survey. Email: support@vsni.co.uk

In today’s world we can barely open a newspaper or turn on the television without seeing a piece on the problems facing our world, and how we are abusing our planet and environment. But how often do you see something on activities and programs aimed at addressing these issues – and not in a futuristic sense, but things that are happening now. Programs and initiatives that are being implemented today for the benefit of the planet. Well, thankfully these programs do exist, and one such centre investigating and supporting them is The Organic Research Centre at Elm Farm. Dedicated to developing sustainable land use, The Organic Research Centre near Newbury, Berkshire is designed to look at providing solutions that develop and support sustainable agriculture and land use. Based upon organic principles to ensure the environment’s health is as protected as possible, the research programs are conducted at the farm in Berkshire and across 25 other farms in the UK. Specifically researchers in the crops programme are running projects that advance the agronomy and management of crops, as well as looking at the development of suitable oat varieties for organic systems and wheat breeding. Within the wheat breeding project for example researchers have developed, instead of varieties, Composite Cross Populations which, because of their large genetic diversity, perform stably under differing or fluctuating environmental conditions. This stability is increasingly being recognised by farmers as important for the future viability of their businesses and in the face of climate change; these are now being grown on 25 farms from Devon to Northumberland. The majority of these projects need to go through several key stages: setting hypotheses, deciding on treatment levels, designing the experiments (where GenStat comes in), carrying out field plot trials, assessing and harvesting the trials and then using GenStat to analyse the data. In designing the experiments, GenStat is used to estimate the replication required and allocate the treatments to the plots; when analysing the data the menus in GenStat are used for summary statistics, ANOVA and META analysis. Outputs are then used to see the significant effects and graphs generated from the means and associated errors. In wheat breeding trials performed by the Elm Farm researchers, the main aim was to produce wheat that performs well year after year over a range of different environments. “Over the last three years of field trials at four sites,” says Sarah Clarke of the Organic Research Centre, “the populations have indeed performed well in terms of yield and quality, but we were unable to quantify their reliability in a satisfactory way.” VSNi Consultancy At this point the researchers chose to use the consultancy service provided by the statisticians at VSNi to assist with their analyses. Specifically the VSNi statisticians used a “superiority” analysis, which generated a measure of superiority, based on the absolute yields and how stable they are. “The great aspect of this new analysis is that we can use data from all 12 experiments, i.e. 3 years over 4 sites, to work out which of the varieties and populations are both yielding and reliable,” says Sarah Clarke, ORC, “we can also split the experiments into those that are organic and those that are non-organic, to see if the populations differ between systems.” The initial results from the analysis indicate that the populations are generally performing well, but even more encouraging is that when other factors such as grain protein and canopy cover were analysed and results combined with the yield data it showed that the “offspring” populations were more reliably high performing that the parent strands. Further analysis is being carried out on the data, but so far the results look promising in terms of quality and yield quality.

Figure 1. Yield superiority indices (low = superior) in conventional (black bars) and organic (grey bars) systems of the Yield (Y) category: composite cross populations (CCP) with or without males sterility (MS); parent varieties of the population; and the mixture of the parent varieties (Y mix).

The overall assistance provided by VSNi included them performing a “health check” on some of the analysis to ascertain a base point to start from. The VSNi statisticians then performed a META analysis which combined the analyses from all the sites using reml techniques to allow for the multiple variables. The team at Elm Farm needed to evaluate the stability of the sites in their study, so programs were developed to calculate the cultivar superiority measure, mean and variance of varieties. The results were assessed with permutation tests (developed by VSNi) for significance. The additional work and assistance from VSNi was made into menus for the Elm Farm researchers to allow them to use them in future studies and projects. GenStat has enabled these researchers to perform sophisticated statistics without the need to learn the sophisticated statistics themselves; GenStat’s pedigree provides a solid basis and encourages good statistical practice, with VSNi as the safety net and back up. This means researchers can concentrate on doing what they do best, rather than worrying about the validity of the statistics behind their projects. “Without the assistance and support of the VSNi statisticians, the analysis of the data from our trials would have taken much longer and we would have not been truly able to draw conclusions on which wheat compositions perform best and under what conditions. As it is we can confidently make recommendations and refine our experiments to find the most ideal wheat for each environment.” Says Sarah Clarke ORC, “we are well equipped to understand the analysis of our data, and make predictions and recommendations for the future. Without this service our researchers may have spent valuable time and effort trying to work on complicated statistics; VSNi took the hassle out of the work and provided us with tools for future use, so that we could concentrate on the studies and results of the studies to enable better future planning.” For VSNi it’s encouraging to know that GenStat has become an important tool for any researcher in their projects, but there is an added feel-good factor knowing that the products assist with sustainability programmes around the world. You can find out more about Elm Farm through their website.

GenStat is well known and highly regarded throughout the world in its historical core area of biosciences, and specifically in agricultural research.

“……beautifully simple to program.” Dr Brian Miller

The breadth of statistical analysis covered is well documented on websites, review articles and the like. As are the importance of its pedigree, developed, tried, tested and used by agricultural statisticians; the birthplace of GenStat (Rothamsted Experimental Station) being also the birth place of modern statistics with the likes of Sir Ronald Fisher, Frank Yates and Professor John Nelder all giving GenStat a certain kudos in statistical circles and the bioscientist’s world.

More and more disciplines are relying on statistics to uncover trends, causes and to better understand relationships between various factors. One area that has always understood the importance of statistics is epidemiology – the study of factors affecting the health and well-being of populations. Epidemiology is a vital discipline underpinning evidence-based medicine, for identifying risk factors for diseases and health effects.

The epidemiologist’s work ranges from investigations into disease outbreaks, clusters and exposure-response relationships, which may include the development of regression models to test hypotheses and estimate risk coefficients. The epidemiologists’ work at the Institute of Occupational Medicine in Edinburgh is designed to provide reliable information about health effects and risks for occupational and environmental hazards, with a view to addressing public and industry concerns, and providing a scientific basis for policies to limit disease. So it’s easy to see how a statistical analysis system such as GenStat is a vital tool for these researchers.

The IOM has been using GenStat for several decades in their studies on public health in the UK. Originally set up as a charity in 1969 to research coalminers’ lung disease, to continue a research programme set up by the National Coal Board’s medical service, the charity has been independent since 1990, and now provides research, consultancy, laboratory and measurement services in relation to potential health problems caused by occupational and environmental exposures. All the research reports published by the IOM since 1969 are available for free download from the online library at www.iom-world.org.

GenStat has been used in a variety of different analyses, including epidemiological or observational data, which typically requires a regression model of some kind (linear, GLM, GAM, LMM, GLMM etc). It is also used for analysing data sets from designed toxicology experiments and for analysing cause-specific mortality data in comparison with reference rates.

A recent study looked at mortality rates in a group of almost 18,000 coalworkers from 10 collieries recruited from the 1950s onwards and followed up until the present time, of whom about two thirds are now deceased. One aim of the study was to compare the observed rates from certain causes of death with the male population rates for those causes in the regions where the coal pits are located. The calculations produce standardised mortality ratios (SMR’s) and their standard errors, using standard epidemiological methods.

GenStat used each individual’s entry and death or censoring dates to amass the person-years in the cohort, tabulating them by region, year and age (using GenStat’s option for sequential tabulation). The SMR calculations then used GenStat’s table manipulation functions to organise observed deaths and calculate expected numbers, ratio of observed to expected (SMR) and its standard error, etc. The outputs included overall SMR, plus a breakdown on 5 year-time groups that show how the healthy worker effect exists in the early part of the follow-up. The study has also been able to show that the risks of developing certain respiratory diseases increase with increased exposure to dust. Detailed results are available in a final report, downloadable from the website http://www.iom-world.org/pubs/IOM_TM0706.pdf.

Table 5.1 Summary results of comparisons of mortality in cohort with external reference rates. The table shows, for chosen cause groups, numbers of deaths, age- year- and region-standardised mortality ratios (SMR) and 95% confidence interval.

Figure 5.1 Standardised Mortality Ratio (SMR) for all internal causes over the length of the follow-up period, with years grouped. The solid line is the SMR while the dashed lines represent the 95% confidence interval. The dotted line shows the SMR equal to 100%.

For any complex statistical calculations a software programme that is easy to use and reliable is crucial, but specifically in this instance GenStat’s table functions make the SMR calculations “beautifully simple to program.” (Dr Brian Miller).

The ability to understand the causes of health issues, what factors may lead to ill health or mortality in populations are of critical importance world-wide: so a sound, reliable data analysis system such as GenStat is vital to assist with analysis and help produce scientifically based recommendations and policies.

Our thanks to Dr Brian Miller of The Institute of Occupational Medicine for his help in producing this feature. More information on the IOM can be found at www.iom-world.org

Images/Tables with permission from IOM research report TM/07/06, available at www.iom-world.org/pubs/IOM_TM0706.pdf

Readers may be less aware of the value of computers in forest research, but everything that can be quantified has to be measured and the data analysed.

For example, field experiments on tree growth, might include measurement of ground and under-storey vegetation, soil contamination, levels of infection by insects, fungi and pathogens, as well as damage caused by squirrels or deer. All these affect not only the speed of tree growth, but the way in which the tree grows and develops.

Growth trials are, by their very nature, long-term projects, for example, a survey on the effects of formative pruning on broadleaved trees (such as European ash, cherry, European beech and English oak) meant that form and growth were assessed for up to nine years. Many factors were monitored and recorded in that time, producing a wealth of data to be analysed. This particular trial’s results suggested traditional pruning methods were likely to produce an improvement in the quality of the timber.

Forestry experiments also require very careful design due to the large number of factors included in the trials, or at least to be aware of, when interpreting and analysing data. Even before any field trial is laid out, researchers have to make sure a series of other activities has taken place. For example, for a tree introduction programme, seed collections that appropriately represent species, provenances or populations are needed; researchers need to be sure that there are enough seedlings raised for the experiment to be worthwhile and a suitable trial site (or sites) needs to be found, and so the list goes on – and this is even before the trial has actually started.

In general terms, experiments usually test hypotheses, but in forestry research they can also be used for other reasons, such as, estimating wood production. Many tree improvement trials will measure timber quality (proportions of sawlogs, pulp or fuel wood), as well as pest or disease resistance, essential oil production, or the use of the foliage for animal fodder. With so many factors to take into account, careful design, planning, recording and data analysis are crucial to success.

GenStat, one of the first, and only UK-produced, statistical software packages, has largely become the tool of choice for forestry researchers worldwide. Customers range from forestry research stations and universities in Europe, Australia, Africa, North America, New Zealand and China who have come to trust and depend on the statistics within GenStat. GenStat was originally developed by statisticians at Rothamsted Experimental Station (now Rothamsted Research), the largest agricultural research centre in the UK and one of the oldest in the world. GenStat’s pedigree begins with the pioneering work at Rothamsted of Sir Ronald Fisher in the 1930s and Frank Yates in the 1950s meaning many of the statistics and analysis tools have been designed specifically for field trials and working with the complexities of agricultural data.

A research team at Moulton College in Northamptonshire has been working on a field trial to investigate how water availability affects the growth rate of young trees, and the influence on developing new woodland. The experiment was arranged in a randomized block design, which meant that given the GenStat Analysis of Variance facilities can analyse any generally balanced design (and certain partially balanced incomplete block designs), analysis of their trial was straightforward.

Another key issue for the researchers was the ability of GenStat to handle such large data sets – without this ability, the analysis of data can be lengthy, complex and prone to error.

A study by Forest Research on the regeneration of oaks within oak woodland used GenStat’s Generalised Linear Model facilities to investigate relationships between location and vegetation variables and seedling data. This same experiment also used linear regression – again a standard and simple to use function within GenStat, to analyse the height and diameter of seedlings and of vegetation cover.

Forestry experiments can involve measurements repeated over time, for example the first 5 years of growth for a seedling, or measurements that are likely to be correlated because of spatial proximity. This data can be unbalanced, however GenStat can help to overcome these issues with the use of its mixed model facilities (REML).

There are some statisticians in forestry research, but the majority are research scientists with a working knowledge of statistics, so a package that combines advanced statistics and ease of use is vital. GenStat ticks these boxes.

GenStat has made its mark in forestry research and is committed to supporting this industry worldwide. VSNi is a commercial business, however its dealing and ethical approach to sustainable development is encapsulated within the GenStat Discovery project. Here the developing world can access GenStat free of charge with recent, but not the current version of GenStat. This enables regions of the world and their researchers in particular, who are otherwise constrained by limited financial resource, to continue and to advance their research. A major user and keen supporter of GenStat are KEFRI (Kenya Forest Research Institute), who have been using GenStat Discovery for some time. For more information on GenStat visit www.vsni.co.uk or contact support@vsni.co.uk

References:

1. Experimental design and analysis for use in tree improvement; E.R. Williams & A.C Matheson.
2. Does formative pruning improve the form of broadleaved trees? Gary Kerr & Geoff Morgan, Canadian Journal of Forest Research
3. Development of Quercus robur advance regeneration following canopy reduction in an oak woodland Ralph Harmer & Geoff Morgan, Forestry
4. Moulton College www.moulton.ac.uk