Biology, images, analysis, design...
Medical Diversity Livestock Invasives
"It has long been an axiom of mine that the little things are infinitely the most important" (Sherlock Holmes)

Search this site



Biological / statistical controversies of our time

  1. Do we need badger culling to control bovine tuberculosis (TB)?

    In England the cattle tuberculosis situation is best described as 'out of control' with the number of infected cattle doubling every four and a half years. A 'link' with tuberculosis infection in badgers has been suspected for many years, but it is unclear whether cattle are infecting badgers and/or vice versa.

    Unusually, a randomized trial was carried out to assess the impact of badger culling on number of herds affected with cattle tuberculosis. Based on this The Independent Scientific Group on Cattle TB concluded that culling was not a viable component for control, yet the current government policy is to resume badger culling next year.

    Why was this decision made, and who is right?

    European badgers at a wildlife park in England


  2. Does organic farming benefit diversity?

    Here we consider whether this conservation paradigm really is evidence-based. We examine how critically the results were reviewed, how strong the evidence really is, what the potential biases are, and how such studies might be improved.

    "'Circumstantial evidence is a very tricky thing'
    answered Holmes thoughtfully.
    'It may seem to point very straight to one thing, but if you shift your own point of view a little, you may find it pointing in an equally uncompromising manner to something entirely different'.

    Sir Arthur Conan Doyle (1859-1930) The Boscombe Valley Mystery


    Conservation strips at a non-organic farm in Cambridgeshire, UK

    (Photo: courtesy of Wikipedia/Michael Trolove)


  3. The MMR vaccine controversy

    This is about a supposed link between autism and the combined measles-mumps-rubella (MMR) vaccine. A research paper and a subsequent letter published in the medical journal The Lancet prompted a media scare which led to a serious decline in the number of children protected against life threatening diseases.

    Many argued at the time that the paper(s) suggesting the link were seriously flawed, but they were still accepted for publication in a respectable medical journal. Only when a journalist identified fraudulent practice by the scientist was the research paper finally retracted.

    We look at the obvious flaws in the original papers and ask why the papers were ever accepted in the first place.

    A boy with autism, and the line of toys he made before falling asleep

    (Photo: courtesy of Wikipedia/Nancy J Price)


  4. In praise of spanners

    Here we consider why the normal paradigm has achieved such an unhealthy dominance, and review some of its effects. As pointed out long ago, the statisticians' and mathematicians' long-standing love of the normal distribution (and its brethren) has little foundation in the real world:
    "Everyone believes in the [normal] law of errors:
      the mathematicians because they think it is an experimental fact;

      and the experimenters, because they suppose it is a theorem of mathematics".

    Gabriel Lippmann. Quoted in Whittaker & Robinson, 1967

  5. Introducing some spanners

    Despite the dominance of the normal paradigm, few scientists ever explore how their data (or errors or statistics) actually are distributed. Here we consider some of the many ways that R can be used for this purpose. We point ot that rank-based methods are usually far more powerful than the usual histogram approach whether comparing a sample distribution to a theoretical distribution, or (as in the figure) comparing two sample distributions.


  6. Using Monte Carlo to learn about statistics

    This shows why using simulation-modelling is a useful way for students and statisticians to understand simple statistics. This approach is one reason why using R can enable algebra-phobes to master biostatistics - in depth.


  7. Why is biostatistics in such a mess?

    Here we consider the reasons for continuing concerns about inadequacies and errors in the way experiments are designed, data are analysed, and results interpreted.

    To introduce this problem consider the following:

    "It's science's dirtiest secret:

    The 'scientific method' of testing hypotheses by statistical analysis stands on a flimsy foundation. Statistical tests are supposed to guide scientists in judging whether an experimental result reflects some real effect or is merely a random fluke, but the standard methods mix mutually inconsistent philosophies and offer no meaningful basis for making such decisions.

    Even when performed correctly, statistical tests are widely misunderstood and frequently misinterpreted.

    As a result, countless conclusions in the scientific literature are erroneous, and tests of medical dangers or treatments are often contradictory and confusing."

    Siegfried, 2010

    In a University graveyard



    •  Siegfried, T. (2010). Odds are, it's wrong. Science fails to face the shortcomings of statistics. Science News 177 (7), 26-29. Abstract Full text
    •  Whittaker, E.T. & Robinson, G. (1967). The calculus of observations: A treatise on numerical mathematics. Dover, New York.