Statistics and individuals

Ramesh Ramloll recently posted on Facebook about two apparently contradictory news reports on vitamin D, one entitled “Recommendation for vitamin D intake was miscalculated, is far too low, experts say” and the other  “High levels of vitamin D is suspected of increasing mortality rates“.

While specifically about diet and vitamin D intake, there seems to be a number of lessons from this: about communication of science (Ramesh’s original reason for posting this), widespread statistical ignorance amongst scientists (amongst others), and the fact that individuals are not averages.

Ramesh remarked:

Science reporting is broken, or science itself is broken … the masses are like deer in headlights when contradictory recommendations through titles like these appear in the mass media, one week or so apart.

I know that rickets is currently on the increase in the UK, due partly to poverty and poor diets leading to low dietary vitamin D intake, and due partly to fear of harmful UV and skin cancer leading to under-exposure of the skin to sunlight, our natural means of vitamin D production.  So these issues are very important, and as Ramesh points out, clarity in reporting is crucial.

Looking at the two articles, the ‘too low’ article came from North America, the ‘too much’ article, although reported in AAAS ‘EurekaAlert!’ news, originated in University of Copenhagen, so I thought that maybe the difference is that health conscious Danes are simply overdosing.

However, even as a scientist, making sense of the reports is complicated by the fact that they talk in different units.  The ‘too low’ one is about dietary intake of vitamin D measured in ‘IU/day’, and the Danish ‘too much’ report discusses blood levels in ‘nanomol per litre’.  Wow that makes things easy!

Furthermore the Danish study (based on 247,574 Danes, real public health ‘big data’) showed the difference between ‘too much’ and ‘too little’, was a factor of two, 50 vs 100 nanomol/litre.  It suggests, Goldilocks fashion, that 70 nanomol/liter is ‘just right’.  Note however, the ‘EurekaAlert!’ news article does NOT quantify the relative risks of over and under dosing, which does make a big difference to the way they should be read as practical advice, and does not give a link to the source article to find out (this is the AAAS!).

Digging a little deeper into the “too low” news report, it is based on an academic article in the journal ‘Nutrients’,A Statistical Error in the Estimation of the Recommended Dietary Allowance for Vitamin D“, which is re-assessing the amount of dietary vitamin D to achieve the same 50 nanomol/litre level used as the ‘low’ level by the Danish researchers.  The Nutrients article is based not on a new study, but a re-examination of the original meta-study that gave rise to the (US and Canadian) Institute of Medicines current recommendations.   The new article points out that the original analysis confused study averages and individual levels, a pretty basic statistical mistake.

nutrients-06-04472-g001-1024  nutrients-06-04472-g002-1024

 Graphs from “A Statistical Error in the Estimation of the Recommended Dietary Allowance for Vitamin D“. LHS is study averages, RHS taking not account variation within studies.

A few things I took from this:

1)  The level of statistical ignorance amongst those making major decisions (in this case at the Institute of Medicine) is frightening. This is part of a wider issue of innumeracy, which I’ve seen in business/economic news reporting on the BBC, reporting of opinion polls in the Times, academic publishing and reviewing in HCI, and the list goes on.  This is an issue that has worried me for some time (see “Cult of Ignorance“, “Basic Numeracy“).

2) Just how spread the data is for the studies. I guess this is because individual differences and random environmental factors are so great.  This really brings home the importance of replication, which is so hard to get funded or published in many areas of academia, not least in HCI where individual differences and variations within studies are also very high.  But it also emphasises the importance of making sure data is published in such a way that meta-analysis to compare and combine individual studies is possible.

3) Individual difference are large.  Based on the revised suggested limits for dietary vitamin D, designed to bring at least 39/40 people over the recommended blood lower limit of 50 nanomol/litre, half of people would end up with blood levels higher than four or five times that lower limit, that is more than twice as high as the level the other study says leads to deleterious over-consumption levels.  This really brings home that diet and metabolism vary such a lot between people and we need to start to understand individual variations for health advice, not simply averages.  This is difficult, as illustrated by the spread of studies in the ‘too low’ article, but may become possible as more mass data, as used by the Danish study, becomes available.

In short:

individuals matter in statistics

and

statistics matter for individuals

 

 

 

 

It started with a run … from a conversation at Tiree Tech Wave to an award-winning project

Spring has definitely come to Tiree and in the sunshine I took my second run of the year. On Soroby beach I met someone else out running and we chatted as we ran. It reminded me of another run two years ago …

It was spring of 2013 and a busy Tiree Tech Wave with the launch of Frasan on the Saturday evening. A group had come from the Catalyst project in Lancaster, including Maria Ferrario and she had mentioned running when she arrived, so I said I’d do a run with her. Only later did I discover that her level of running was somewhat daunting, competing in marathons with times that made me wonder if I’d survive the outing.

Happily, Maria modified her pace to reflect my abilities, and we took a short run from the Rural Centre to Chocolates and Charms (good to have a destination), indirectly via Soroby Beach, where I ran today.

Running across the sand we talked about smart grids, and the need to synchronise energy use with renewable supply, and from the conversation the seeds of an idea grew.

fiona-crossapol-beach-2663997355_ea73a75f4c_z-cropped

I started my walk round Wales almost immediately after (with the small matter of my daughter’s wedding in between), but Maria went back to Lancaster and talked to Adrian Friday, who put together a project proposal (with the occasional, very slow email interchange when I could get Internet connections). Towards the end of the summer we heard we had been short-listed and I joined Adrian via Skype for an interview in July.

… and we were successful 🙂

The OnSupply project was born.

OnSupply was a sub-project of the Lancaster Catalyst project. The wider Catalyst project’s aims were to understand better the processes by which advanced technology could be used by communities. OnSupply was the main activity for nine-months of the last year of Catalyst.

OnSupply itself was focused on how people can better understand the availability of renewable energy. Our current model of energy production assumes electricity is always available ‘on demand’ and the power generation companies’ job is to provide it when wanted. However, renewable energy does not come when we want it, but when the wind blows, the tides run and the sun shines. That is in the future we need to shift to a model where energy is used when it is available, ‘on supply’ rather than ‘on demand’.

The Lancaster team, led by Adrian consisted of four full time researchers, Will, Steve, Peter, and of course, Maria, and the other project partners were Tiree Tech Wave, the Tiree Development Trust, Goldsmiths University, and Rory Gianni, an independent developer based in Scotland specialising in environmental issues.

The choice of Tiree was of course partly because of Tiree Tech Wave and my presence here, but also because of Tilly, the Tiree community wind turbine, and the slightly parlous state of the electricity cable between Tiree and the mainland. In many ways the island is just like being on the mainland, you flick the switch and electricity is there. While Tilly can provide nearly a megawatt at full capacity, this simply feeds into the grid, just like the wind farms you see over many hillsides.

However, there is also an extent to which we, as an island population, are more sensitised to issues of electricity and renewable energy.

TTW6_DanPictsForSaturdayPitch-3-604x270

First is the presence of Tilly, which can be seen from much of the island; while the power goes into the grid, when she turns this generates income, which funds various island projects and groups.

But, the same wind that drives Tilly (incidentally the most productive land-based turbine in the UK), shakes power lines, and at its wildest causes shorts and breakages. The fragile power reduces the lifetime of the sophisticated wireless routers, which provide broadband to half the island, and damages fridge compressors.

Furthermore, the aging sea-cable (now happily replaced) frequently broke so that island power was provided for months at a time from backup diesel generator. As well as filling the ferry with oil tankers, the generator cannot cope with the fluctuating power from Tilly, and so for months she is braked, meaning no electricity and so no money.

So, in some ways, a community perfect for investigating issues of awareness of energy production, sensitised enough that it will be easier to see impact, but similar enough to those on the mainland that lessons learnt can be transferred.

wirlygigThe project itself proceeded through a number of workshops and iterative stages, with prototypes designed to provoke discussions and engagement. My favourites were machines that delivered brightly coloured ping-pong balls as part of a game to explore energy uses, and wonderful self-assembly kits for the children, incorporating a wind and solar energy gauge.

The project culminated in a display at the Tiree Agricultural Show.

While OnSupply finished last summer, the reporting continues and a few weeks ago a paper about the project, to be presented at the CHI’2015 conference in South Korea in April, was given a best paper award at the CHI’2015 conference.

… and all this from a run on the beach.