Monthly Archives: April 2016

On Statistical Progress in Ecology

There is a general belief that science progresses over time and given that the number of scientists is increasing, this is a reasonable first approximation. The use of statistics in ecology has been one of ever increasing improvements of methods of analysis, accompanied by bandwagons. It is one of these bandwagons that I want to discuss here by raising the general question:

Has the introduction of new methods of analysis in biological statistics led to advances in ecological understanding?

This is a very general question and could be discussed at many levels, but I want to concentrate on the top levels of statistical inference by means of old-style frequentist statistics, Bayesian methods, and information theoretic methods. I am prompted to ask this question because of my reviewing of many papers submitted to ecological journals in which the data are so buried by the statistical analysis that the reader is left in a state of confusion whether or not any progress has been made. Being amazed by the methodology is not the same as being impressed by the advance in ecological understanding.

Old style frequentist statistics (read Sokal and Rohlf textbook) has been criticized for concentrating on null hypothesis testing when everyone knows the null hypothesis is not correct. This has led to refinements in methods of inference that rely on effect size and predictive power that is now the standard in new statistical texts. Information-theoretic methods came in to fill the gap by making the data primary (rather than the null hypothesis) and asking the question which of several hypotheses best fit the data (Anderson et al. 2000). The key here was to recognize that one should have prior expectations or several alternative hypotheses in any investigation, as recommended in 1897 by Chamberlin. Bayesian analysis furthered the discussion not only by having several alternative hypotheses but by the ability to use prior information in the analysis (McCarthy and Masters 2006). Implicit in both information theoretic and Bayesian analysis is the recognition that all of the alternative hypotheses might be incorrect, and that the hypothesis selected as ‘best’ might have very low predictive power.

Two problems have arisen as a result of this change of focus in model selection. The first is the problem of testability. There is an implicit disregard for the old idea that models or conclusions from an analysis should be tested with further data, preferably with data obtained independently from the original data used to find the ‘best’ model. The assumption might be made that if we get further data, we should add it to the prior data and update the model so that it somehow begins to approach the ‘perfect’ model. This was the original definition of passive adaptive management, which is now suggested to be a poor model for natural resource management. The second problem is that the model selected as ‘best’ may be of little use for natural resource management because it has little predictability. In management issues for conservation or exploitation of wildlife there may be many variables that affect population changes and it may not be possible to conduct active adaptive management for all of these variables.

The take home message is that we need in the conclusions of our papers to have a measure of progress in ecological insight whatever statistical methods we use. The significance of our research will not be measured by the number of p-values, AIC values, BIC values, or complicated tables. The key question must be: What new ecological insights have been achieved by these methods?

Anderson, D.R., Burnham, K.P., and Thompson, W.L. 2000. Null hypothesis testing: problems, prevalence, and an alternative. Journal of Wildlife Management 64(4): 912-923.

Chamberlin, T.C. 1897. The method of multiple working hypotheses. Journal of Geology 5: 837-848 (reprinted in Science 148: 754-759 in 1965). doi:10.1126/science.148.3671.754.

McCarthy, M.A., and Masters, P.I.P. 2005. Profiting from prior information in Bayesian analyses of ecological data. Journal of Applied Ecology 42(6): 1012-1019. doi:10.1111/j.1365-2664.2005.01101.x.

Walters, C. 1986. Adaptive Management of Renewable Resources. Macmillan, New York.


Reducing Greenhouse Gases at the Local Scale

This blog is devoted to the simple question of what we might do about climate change at a very small scale. As individuals we can do little directly about the big issues of fracking and oil extraction from tar sands and shale deposits. Of course we can and should vote about these large issues, but my question is what can we do at a local level to support the Paris Agreement?

This was all brought to my attention on a recent drive of 50 km from Haines Junction in the southern Yukon north to Kluane Lake. Along the side of the Alaska Highway on each side of the road for a perpendicular distance of perhaps 20 m the highways department had mowed down all the vegetation to the ground level along a stretch of about 25 km. Willows 1-2 m in height, small aspen, spruce and poplar trees up to 3 m in height were all mowed down and chopped into small pieces. This observation gave rise to two thoughts. First, highways departments have always done this kind of mowing so why worry about it? But second, why should we keep doing now what we always did in the past?

We have just signed the Paris Agreement to try to stop the increases of greenhouse gases in the atmosphere. This means we should be looking at everything we do to see if it is generating more greenhouse gases than necessary. Mowing down the edges of highways has two detrimental effects on our environment. First, diesel or petrol is used to run the machines that do the mowing, Second, we have now lost the only mechanism we currently have for taking CO2 out of the atmosphere, plant growth via photosynthesis. We mow down the plants, thus making compost that releases CO2 as it decays, and we lose the structure of the road edge that captures CO2 at no cost to us. But of course new plants will now start to colonize and re-grow along the road edge, capturing CO2, but the key point here is that in northern Canada it will take probably 20-30 years to have the vegetation recover to the point that it was before mowing. Thus on every score this mowing along the highway is a direct affront to the Paris Agreement.

The argument about road edges is always to protect vehicles from wildlife suddenly coming out of the forest on to the road and causing a collision. The frequency of this for the larger species would have to be measured, and the assumption that a mowed strip reduces collisions with wildlife would have to be quantified. In my observations a nicely mowed strip in northern Canada becomes green early in the spring and in fact then attracts large and small herbivores like moose, bison, and hares to the edges of the road. Thus mowing might actually increase the probability of collisions with wildlife. In Newfoundland Tanner and Leroux (2015) showed that moose browsed less in recently cut highway edges but this effect might be lost within a few years. The critical question if moose-vehicle collisions are to be reduced is to know exactly what actions produce fewer accidents (Jägerbrand and Antonson, 2016). Reducing speed limits has a strong effect on accident rates. No one has looked into the greenhouse gas issue regarding the cost and benefit of roadside clearing. Many authors (e.g. Meisingset et al. 2014) point out how little serious experimental work has been done on the wildlife collision issue, another opportunity for adaptive management.

The highways department would probably consider this all very silly to worry about. But it does raise the more general issue that many others have pointed out: should we somehow have a greenhouse gas indicator app that would tell us for our own houses, vehicles, and property what we are doing in our everyday actions to assist the reduction of greenhouse gases as mandated in the Paris Agreement. It cannot simply be business as usual.

Jägerbrand, A.K., and Antonson, H. 2016. Driving behaviour responses to a moose encounter, automatic speed camera, wildlife warning sign and radio message determined in a factorial simulator study. Accident Analysis & Prevention 86(1): 229-238. doi:10.1016/j.aap.2015.11.004.

Meisingset, E.L., Loe, L.E., Brekkum, Ø., and Mysterud, A. 2014. Targeting mitigation efforts: The role of speed limit and road edge clearance for deer–vehicle collisions. Journal of Wildlife Management 78(4): 679-688. doi:10.1002/jwmg.712.

Tanner, A.L., and Leroux, S.J. 2015. Effect of roadside vegetation cutting on moose browsing. PloS One 10(8): e0133155. doi:10.1371/journal.pone.0133155.