On 19 January 2015, I attended the meeting on Big Data at the RSS. The speakers included: Kenneth Cukier (Data Editor at The Economist); Haishan Fu (Director of Development Data Group at the World Bank); Alex ‘Sandy’ Pentland (Professor at MIT and Academic Director of Data-Pop Alliance); Nuria Oliver (Scientific Director at Telefonica); John Pullinger (UK National Statistician), with Denise Lievesley (Dean of Faculty, King’s College) as Chair.

It is impossible to summarise the contributions or the excellent discussion, but here are some comments (recorded approximately) that give a flavour of the discussion.

Kenneth Cukier: “Big Data allows data to be produced as frequently as is needed, not at the convenience of the producers.”

Haishan Fu: “The WB’s aim is to support national data producers and to incentivise the private sector … with a particular aim to help poorer countries ‘leap-frog’ to catch up”.

Nuria Oliver: “Access to data from phone systems allows inferences, at macro levels about responses to large-scale flooding, and at individual levels about the socio-economic status of the user or their likely responses on a range of social issues.”

Sandy Pentland: “Having access to more data will allow us to solve more problems … data [ownership? / access?] should be decentralised to the citizen.”

John Pullinger: “Big Data provides a wake-up call, and an opportunity, for our statistical institutions.”

At the end of the session, the Chair, Denise Lievesley, asked for reactions from the audience, in terms of what we would take away from the meeting. My reaction was that the discussion had made me realise, even more strongly, that statisticians (along with others) over the years have refined a number of crucial ideas, based on a sense of methodological quality (or validity). These relate to several issues.

First, causality is to be distinguished from correlation. This can of course be accomplished by RCT designs, as well as by carefully-controlled and replicated non-experimental studies.

Second, it is important to appreciate how the available indicators have been constructed and understood by the human beings (or processes) producing them. Hence John Pullinger’s timely offer of a course in questionnaire design to one of the “Big Data-enthusiasts” on the panel.

Third, the data analyst also needs knowledge of how the sample before us has been selected, and attenuated by various forms of non-response.

These three methodological concerns are not always fully acknowledged by enthusiasts for big data. An era when “Big Data” is being extensively hyped will produce additional challenges for statisticians re. data management and data analysis. These are already being addressed by inter-disciplinary teams many in universities and organisations. But there is no reason for statisticians to be reticent about the contributions they can make to these clearly important debates.

Jeff Evans

On 7 November,  Water Minister Dan Rogerson argued in response to a written question from Chris Ruane, Labour MP for the Vale of Clwyd, that water filtering within households is unnecessary, as monitoring by drinking water regulators shows tap water quality in the UK is “equivalent to the best in Europe”. (I’m not aware of a data series that would underpin this claim). 

On 9 December, a statistical study by engineer Marc Edwards was published showing that cheap water filters certified to remove lead, together with advice to run taps and consider bottled water in older buildings, prevented hundreds of miscarriages in Washington DC in 2004-2006, when a change in water treatment caused a city wide spike in lead in water levels (links below).   The paper also examines a miscarriage cluster in an office undergoing renovation, where lead in water from solder on copper pipes may have been wrongly excluded as a factor, because water was tested too late. 

The study compared fetal death rates and birth rates in Washington DC against a similar sized city with the same water supply (Baltimore), and the US as a whole, before, during and after two incidents when lead “rust” from lead pipes and from solder on copper pipes was disturbed. The first lead spike was caused by a change in disinfection chemicals, the second by attempts to solve the first problem by replacing sections of lead pipe work. 

Appropriate domestic water filters can reduce chlorination by-products present in tap water from chemical disinfection, together with the herbicides, other farm chemicals and pharmaceutical residues present in some river water (but not in water from boreholes favoured for bottled supplies). Filtering tap water was recommended in 2010 by the US President’s Cancer Panel, along with washing fruit and vegetables to remove pesticide residues and avoiding charred meat. 

Concerned over the known toxicity of disinfection by-products, the Netherlands has abandoned the use of chlorine in a water safety system which prioritizes choosing the safest raw water sources for drinking water (link below). Edwards’ statistical analysis shows that the US change in disinfection practice – initiated and persisted with in an attempt to reduce miscarriages from chlorination byproducts – did not achieve its health goal. Possibly the by-products of the replacement disinfectant regime, though less studied, are equally noxious. A troubling pattern for regulatory changes. 

Edwards’ key recommendations  – supported by his laboratory test simulating lead release from solder in response to physical disturbance – are that pregnant women should always receive advice to use filters, flushing or bottled water in older premises, and that everyone should receive warnings and take precautions when plumbing is disturbed. Currently no such advice is issued in the UK, despite a predominance of older properties (lead free solder was only available from the late ‘80s),  on-going lead pipe replacement to meet a stricter lead in water standard from the end of this year, and programmes to retrofit water meters.

It would be interesting to review fetal death rate trends within the Netherlands, to see whether the package of changes they made to how river water was treated (areas with better water sources never used chlorination) measurably improved maternal health. There is no easy switch to the Dutch method – the need for residual disinfection here goes hand in hand with the c. 25% leakage rate from poorly maintained pipework (vs. 4% for the Netherlands). Bottled water and home/office filtration are the policy options currently available in the UK to safeguard fetal health. 

Lucy Borland

Links: 

Lucy Borland’s paper on Drinking Water Regulation in Rad Stats: https://www.radstats.org.uk/no109/Borland109.pdf

Hansard, Written Answers 7 Nov 2013: http://www.publications.parliament.uk/pa/cm201314/cmhansrd/cm131107/text/131107w0001.htm#13110787000006

Marc Edwards: http://www.vtnews.vt.edu/articles/2013/12/121313-engineering-edwardsnewstudylead.html; http://pubs.acs.org/doi/abs/10.1021/es4034952; Increase in miscarriages coincided with high … – Washington Post

2008-2009 – Environmental Factors in Cancer: Reducing Environmental Cancer Risk, What We Can Do Now available at http://deainfo.nci.nih.gov/advisory/pcp/annualReports/

The Dutch Secret: how to provide safe water without chlorine in the Netherlands, P. W.M. H. Smeets, G. J. Medema, J. C. van Dijk:  available to download at www.drink-water-eng-sci.net/2/1/2009/dwes-2-1-2009.pdf