Category: Book Reviews

Reviews of books featuring a summary of the book and links to related material

Jul 20 2016

Book review: The Seven Pillars of Statistical Wisdom by Stephen M. Stigler

sevenpillarsThe Seven Pillars of Statistical Wisdom by Stephen M. Stigler is a brief history of what the author describes as the key pillars of statistics. This is his own selection rather than some consensus of statistical opinion. That said, to my relatively untrained eye the quoted pillars are reasonable. They are as follows:

1 – Aggregation. The use of the arithmetic average or mean is not self-evidently a good thing. It was during the 17th century, when people were taking magnetic measurements in order to navigate, that ideas around the mean started to take hold. Before this time it was not obvious which value one should take when discussing a set of measurement purportedly measuring the same thing. One might take the mid-point of the range of values, or apply some subjective process based on your personal knowledge of the measurer. During the 17th century researchers came to the conclusion that the arithmetic mean was best.

2 – Information. Once you’ve discovered the mean, how good is it as a measure of the underlying phenomena as you increase the size of the aggregation? It seems obvious that the measure improves as the number of trials increases but how quickly? The non-trivial answer to this question is that it scales as the square root of N, the number of measurements. Sadly this means if you double the number of measurements you make, you only improve you confidence in the mean by a factor of a little over 1.4 (that being the square root of 2) . Mixed in here are ideas about the standard deviation, a now routine formulation quoted with the mean. It was originally introduced by De Moivre in 1738, for the binomial distribution, but then generalised by Laplace in 1810 as the Central Limit Theorem.

3 – Likelihood. This relates to estimating confidence that an observed difference is real, and not due to chance. The earliest work, by John Arbuthnot, related to observed sex ratios in births recorded in England and whether they could be observed by chance rather than through a “real” difference in the number of boys and girls born.

4 – Intercomparison. Frequently we wish to compare sets of measurements to see if one thing is significantly different from another. The Student t-test is an example of such a thing. Named for William Gosset, who took a sabbatical from his job at Guiness to work in Karl Pearson’s lab at UCL. As an employee Guiness did not want Gosset’s name to appear on a scientific paper (thus revealing their interest), so he wrote under the rather unimaginative pseudonym “Student”.

5 – Regression. The chapter starts with Charles Darwin, and his disregard for higher mathematics. He professed a faith in measurement and “The Rule of Three”. This is the algebraic identity a/b = c/d which states that if you know any 3 of a, b, c and d you can calculate the 4th. This is true in a perfect world, but in practice we would acquire multiple sets of our three selected values and use regression to obtain a “best fit” for the fourth value. Also in this chapter is Galton’s work on regression to the mean in particularly how parents with extreme heights had children who were on average closer to the mean height. This is highly relevant to the study of evolution and the inheritance of characteristics.

6 – Design. The penultimate pillar is design. In the statistical sense this means the design of an experiment in terms of the numbers of trials, and the organisation of the trials. This starts with a discussion of calculating odds for the French lottery (founded in 1757) and providing up to 4% of the French budget in 1811. It then moves on to RA Fisher’s work at the Rothamsted Research Centre on randomisation in agricultural trials. My experience of experimental design, is that statisticians always want you to do more trials than you can afford, or have time for!

7 – Residual. Plotting the residual left when you have made your best model and taken it from your data is a time honoured technique. Systematic patterns in the residuals can indicate your modern is wrong, that there are new as yet undiscovered phenomena to be discovered. I was impressed to discover in this chapter that Frank Weldon cast 12 dice some  315,672 times to try to determine if they were biased. Data collection can be an obsessive activity. This story from the early 20th century is not in common.

Seven Pillars is oddly pitched, it is rather technical for a general science audience. It is an entertainment, rather than a technical text. The individual chapters would have fitted quite neatly into The Values of Precision, which I have reviewed previously.

Jul 07 2016

Book review: SPQR–A History of Ancient Rome by Mary Beard

A little diversion for me next: straightforward classical history. I’ve read spqrSPQR: A History of Ancient Rome by Mary Beard. SPQR Senātus Populusque Rōmānus  is the motto of the city, meaning “The Senate and People of Rome”, it has been used since antiquity and is still in use now.

The book starts with the story of Cicero and Catiline in 63 BCE, Cicero revealed Catiline’s plot to overthrow the Roman government. It is presented as the first events where there was significant documentary evidence from multiple sources. Proper history, if you like. Even then what survives should not necessarily be read as gospel truth. Rome prior to this was seen in fragments.

Beard returns to this theme of what the evidence is and how much we can trust it throughout the book. As I read through I discover that the earliest copies of Roman writings date from about 500 AD, anything written before then has been transcribed perhaps several times. Some of this writing sounds like it is in the form of what we would understand as contemporary books but other parts are the selected, edited letters of important people. In neither case are they published and promoted in the way we see modern publishing. In terms of contemporary texts, the inscriptions on tombs and monuments provide a second source of material. In earlier years these inscriptions were limited to the most important but in the first century CE there was a huge expansion of tomb inscriptions from what appear to be relatively ordinary people. There is some writing preserved in wall paintings and less formal graffiti in rare places, like Pompeii. There is some material from the Vindolanda tablets, found at Hadrian’s Wall. We also learn of the books that are lost from references and quotes in other extant works.

The book then returns to cover the history of Rome in chronological order. Starting with the founding myth of Romulus and Remus, purportedly raised by wolves. Subsequently Romulus killed Remus over an argument about where to found the city which was to become Rome. The founding story of Romulus and Remus and fratricide can be seen as a retrospective “justification” for the almost continuous civil war within the Roman Empire. Archaeological evidence shows settlements on the site of modern Rome from around 800BCE. A second theme of the myths of early Rome is the way in which the city grew by assimilating neighbours, you didn’t need to be born in the city to be a Roman, you didn’t even need to live there. The city welcomed incomers.

Rome ran through a sequence of political structures, starting with the Regal Period (of kings) which was replaced with the Roman Republic, where two elected consuls ruled, in 509 BCE. During this period trying to re-introduce a monarchy or calling yourself “king” was seen as anathema. The consuls were finally replaced with Emperors in 44 BCE after the Roman Empire had reached almost its greatest extent. It was experimenting with ways of being a state, in the sense that the prevailing organisations at the time were on a city basis rather than a country. We take the nation-state and its political and bureaucratic structures pretty much for granted these days, for example, we have courts and police forces and so forth. In the years of the Roman Empire these structures were not well-established, and much of SPQR describes Romans feeling their way in establishing political structures.

It’s easy to project the modern world onto the Roman Empire but really it is very different. 20% of the population were slaves, newborn children were fairly casually abandoned. There was no effective system of justice in terms of an established police force or a court system designed to address simple crimes of property or violence against the ordinary person. The great majority of the written record of Rome refers to “Great Men” but Beard writes a couple of chapters on what can be inferred about women and the poor. Strikingly the poor were more likely to “eat out” than the wealthy – they couldn’t afford kitchens of their own.

I pleased to learn that the Emperor Caligula was named for his “Bootikins”, he was taken on military campaigns as a child and dressed in a soldiers uniform with “little soldier’s boots” – caligula. And a Roman writing from Britain writes of the Brittunculi – the Little Britons. Rather relevant to current affairs is the tombstone of a British woman, Regina, born north of London whose husband, Barates from Palmyra in Syria, commissioned the monument, placed near South Shields in the first century CE.

The book ends in 212 CE when the Emperor Caracalla grants everyone in the Roman Empire citizenship. This falls approximately a 1000 years after the founding of Rome, the Roman Empire in the East was to last another millennium but Beard leaves this story to another writer.

At first sight this is an intimidating tome but it reads well, and clearly. It revealed sufficient of the underlying methodology of classical scholars to pique my interest.

Jun 03 2016

Book review: Maphead by Ken Jennings

mapheadMaphead by Ken Jennings is a trip around various groups of people obsessed with maps and things geographic: collectors, makers of fantasy maps, geocachers, paper rally-ers,confluence hunters and so forth. It all makes me feel right at home!

The book starts with Jennings’ own obsession with maps. He pins his obsession to a move, at an early age, to South Korea with his family. His obsession is a plain, common or garden one with much poring over atlases and maps. He also likes toponymics, the naming of places. There are the somewhat obscene, such as Dildo, Newfoundland – my personal favourite of these is “Bresty Haw” (54.326750, –3.008447). There are also the commercial, such as Truth or Consequences in New Mexico. On a more serious note the US renamed a whole pile of places,to mildly less offensive variants such as “Dead Negro Draw”.

An early chapter discusses David Helgren’s 1983 quiz of his University of Miami students which found them to be pretty abysmal at finding even large places, such as Chicago on the map. There is much wailing and gnashing of teeth at this, bemoaning the state of education and in particular the lack of a firm grounding in geography. I was growing up in the early eighties and by that time the rote learning of places was somewhat passé, a private vice that some odd children engaged in. Geography became more the study of systems and ideas. Do we need to learn the capital of Mongolia by rote these days? Probably not, but there is a certain pleasure in knowing all of the US states or the capital cities of all the countries of the world.

The US has a National Geographic Bee where students from across the country compete to be the Queen Bee (or winner). The level of the competition seems pretty high to me. I was bemused to find the scoring scheme for the author’s own quiz at the very end of the book featuring grades of “Terrain Wreck” and “The Atlas Shrugs”.

Collectors of maps have their own chapter, I have ambivalent feelings about this. In some ways it’s just conspicuous consumption but, perhaps with all collecting of this type, is often linked with genuine expertise. Occasionally I have considered buying a complete set Ordnance Survey maps.

The highway obsessives are a group of which I was unaware. It turns out that there are people who photograph the signs on every junction of the US highway system. This has evolved into the Massacre Rally – armchair, map-based rallying! Here the players follower written questions to guide them across the country. Reading the web page I’m just a little bit tempted. The rally is based on the iconic Rand McNally road atlases which I was surprised to learn drove road signage in the US, its surveyors painted their own signage onto telegraph poles in the absence of any official markings.

Geocaching and confluence hunting get chapters of their own related to the travel clubs whose members aim to visit as many countries as possible. Geocaching came in to being when the selective availability on GPS was lifted in 2000, increasing the precision of position finding to domestic users by an order of magnitude, thereby allowing geocachers to share the coordinates of small, hidden caches with the reasonable expectation that they can be found using a GPS handset. Confluence hunters are related in that they visit locations with integer values of latitude and longitude.

The technology of maps has moved on significantly in my life time, GPS has shrunk to the size that it now fits into my watch. I can navigate to any place on earth in Google Maps, and see an overhead view, and for many locations I can also see a view from the street.This leads to interesting new games such as GeoGuessr – guess where you are from a Google Street View.

As an aside we also discover the origin of the idea of the 1:1 scale map, in Lewis Carroll’s novel Syvlie and Bruno which also introduces the idea of paintballing.

The book seems to miss my own personal obsession: filling maps with data. I spent many happy hours finding the triangulation points for Delambre and Mechain’s survey of the meridian through Paris to set the length of the metre. Or my maps of the 2010 General Election results. One of my current great pains is that the LIDAR maps the Environment Agency has released of England and Wales is the gaps in coverage. The absence of Scotland and Northern Ireland from the LIDAR coverage is an abomination in my eyes. 

Maphead is a short read, not particularly challenging and a comforting reminder that there are other people like you (for certain values of you).

May 26 2016

Book review: Lab Girl by Hope Jahren

labgirlLab Girl by Hope Jahren is an unusual book. It’s an autobiography which mixes in a fair amount of plant science. It is beautiful to read. It is strong on what being a scientist means. The closest comparison I can think of are Richard Feymann’s “Surely you are joking, Mr Feynmann” memoirs which are rather more anecdotal.

Lab Girl is chronological, starting from Jahren’s early memories of visiting the lab in her father’s school after hours but then fast forwarding to her academic career setting up laboratories in Georgia, Baltimore and finally Hawaii. It isn’t encyclopaedic in providing a detailed record of Jahren’s personal and scientific life.

A thread through the whole book is Bill, her trusty research assistant. Bill starts as a keen undergraduate who Jahren takes on when she gets her first academic position. I think in some ways Bill is something of a product of the US academic system, with support staff often funded on short term grants. In the UK such people tend to be employed on a permanent basis by the institution. My Bill was Tom when I was a PhD student, Pete and Roger when I was an assistant director of research. As a lecturer I didn’t have a Bill, and maybe that was my problem.

Several themes intertwine through the book. There is the day to day activity of a lab: labelling things, repetitive sample preparation, measuring things, fighting with equipment to get it to measure things. Wrangling undergraduates and postgraduates. There are trips out into the field. For Jahren, as a biologist, the field is very literally the field (or Irish bog, Canadian tundra etc). There is attending academic conferences. Mixed with this there is the continual struggle for tenure and funding for your research and the fight for resources with grants that don’t go quite far enough.

It’s fair to say Jahren put in an awful lot more hours than I did as a young academic but then I didn’t turn into an successful, older academic. Make of that what you will. It’s difficult to measure your success as an academic, grant applications are so hit and miss that winning them is only a measure of your luck and skill at writing grant applications, papers are relatively sparse and rarely provide much feedback. Sometimes putting in hours seems the only way of measuring your worth.

A second strand is plant biology, mingling basic background and the cutting edge research that Jahren does. I absorbed this in ambient fashion, I now think a little more like a tree. I didn’t realise that willow deliberately drop  whole branches so as to propagate themselves. This explains the success of our willow dome construction which was made by unceremoniously plonking willow sticks into the ground and weaving them together. They then gamely got on and grew. Soil is a recurring theme in the book, the teaching of the taxonomy of soil to undergraduates in particular. I had glimpses of this rich topic whilst doing a Kaggle challenge on tree cover. Finally, there is mass spectroscopy and isotope analysis.

And finally there is the personal, Jahren’s mental health, her struggles with pregnancy, marriage and a growing son. Some of this is painful and personal reading but its good to hear someone saying what we perhaps find unsayable. Lab Girl says relatively little about the difficulties she particularly faced as a woman, although Jahren has written about it elsewhere.

I observed a while back when reviewing In Defence of History that whilst historians seemed interested in literary style in technical writing, scientists rarely did. Lab Girl is an exception, which makes it well worth a read.

At the end of the book, Jahren asks us all to plant a tree. I pleased to say we’ve achieved this, although perhaps not quite the right sort of trees for American sensibilities, used to larger gardens. In the front garden we have a crab apple tree which, in the right sort of year, flowers on my birthday. There are several apple trees spread through the front garden. In both front and back gardens we have acers and now, at the bottom of the garden we have an amelanchier. I have longed for a Cedar of Lebanon in my front garden but fear I will never own a house large enough for this to be practicable.

May 18 2016

Book review: Mauve by Simon Garfield

mauveMauve: How one man invented a color that changed the world by Simon Garfield is a biography of William Perkin. Who first synthesised the aniline dye, mauve, in 1856 at the age of 18.

Synthetic dyes were to form the catalyst for the modern chemical industry, an area close to my heart since I worked at Unilever on fluorescent and “shader” dyes for the colouring of laundry and teeth. For my undergraduate degree and PhD I was close to organic synthesis labs but didn’t participant with any any enthusiasm (everything gets mixed up and you can poison, burn or explode yourself!).

The book starts with a trip by William Perkin to the United States in 1906, and a series of events to celebrate the fiftieth anniversary of his discovery. It’s very reminiscent of similar celebrations on a visit of Lord Kelvin at around the same time. By the later years of his life he was lauded in his field, if not so much beyond it.

Chemistry as a subject was relatively unformed in the middle years of the 19th century. Lavoisier, Davy, Dalton and others had laid the foundations of the modern subject in the early years of the century but it looked nothing like it does today. Chemical formulae were understood but their structural meaning was still a mystery and certainly not liable to routine elucidation. There were chemical industries of sorts, such as the manufacture of gunpowder, the preparation of dyes and tanning. Coal gas was made from coal, producing a variety of by-products including coal tar.

Perkin was studying at the Royal College of Chemistry as an assistant to August Hofmann who was focused on the idea of synthesising quinine from coal tar. He had been encouraged in his scientific studies by Faraday, and Hoffmann had personally intervened with his father for him to study at the Royal College, who had a career in architecture in mind for him.

There is a superficial similarity in the chemical compositions of aniline, a component of coal tar, and quinine. At the time it seemed plausible to synthesis the one from the other. Quinine was highly valued as an antimalarial drug whose supply was very limited. In the end quinine was not to be synthesised until 1944 by Robert Woodward. The synthesis of useful analogues of natural compounds continues to be one of the driving forces in synthetic chemistry.

In 1856, whilst trying to make quinine, Perkin synthesised an attractive colour (mauve) that dyed silk. Such a discovery was not entirely novel or unknown, the colouring properties of coal tar derivatives had been observed before. However, Perkin saw commercial potential and approached a Scottish dye manufacturer, Robert Pullar for advice. At the time dyes such as madder, indigo and cochineal were derived from animal or vegetable matter and were expensive and unpredictable. The natural growth process meant you were never quite sure of the quality of product you were making, or using.

Colouring something is only half the story with dyes, it is also important that the dye sticks to the target and stays there after washing or exposure to light. The techniques and materials for achieving this depends on whether the target is cotton, silk, wool, paper or whatever. With a new class of dyes, new techniques were required. So alongside the colouring material Perkin also provided technical services to help his customers use the dyes he made.

The business was boosted when mauve became a fashionable colour, worn by Queen Victoria. Perkin grew his factory in Greenford, and ultimately sold it when he was 35 for around £100,000 (which appears to be something around £75million in current value). After this he seems to have focused on further research rather than any other commercial venture. His motivation for selling up seemed to be that German companies had become dominant in the production of dye. It was felt that they had better access to trained technical personnel, and their companies were more willing to spend money on research (a complaint still heard today). Then, as now, it was argued that the British were good at inventing but not exploiting.

From dyes the synthetic chemical industries expanded into new areas. In the first instance dyes were useful in themselves in preferentially staining different microscopic structures. It was then discovered that some of them had biological activity, such as methylene blue. And from the aniline dyes were synthesised the antibiotic sulfa drugs and then other, uncoloured medicines.

The synthetic adventure was to continue with synthetic polymers which, in common with mauve, started as an unpromising black sludge at the bottom of a reaction vessel.

The chemical industry in Britain was resuscitated by World War I. Britain found itself dependent on German companies for dyes for military uniforms and precursors to explosives at the onset of war. The strategy, repeated across many industries, was for government to take direct control with the resulting organisations continuing after the war. For the chemical industry this lead to formation of ICI, Imperial Chemical Industries. The manufacture of bulk chemicals has largely moved to China now and ICI broke up and was sold between the early nineties and 2010.

Mauve is an enjoyable read but lacks depth.