Origin of the p-value

The story of the p-value used in statistics starts with William Gossett, better known under the pseudonym Student. Gossett worked in a brewery and was tasked with maintaining quality by assessing the looks and fragrance of plants used in the brewery for flavoring. To do this, he had to understand how ideal and representative a sample would exactly be with small sample sizes. To put it in other words, what do the results of a sample size of 1 or 2 say about the results when applied to a population of millions of samples. In statistical terms, you could answer the question by calculating the error distribution of the mean and comparing it with small and large sample sizes.

In more and other words…

Gossett would collect a few samples and average some results. Yet the average result never matched the actual result in larger samples. There was a certain error. He wanted to know, how the sample size would affect that error. For example, he wanted to know how many sample results one needs in order to make good predictions of the results of a million samples.

In more practical language…

Gossett needed to determine the quality of beer. Lets say the company produced 100 bottles of beer. Gossett could not test all the bottles, so he wanted to know the minimum of bottles one should test for quality in order to make accurate predictions of the quality of those 100 bottles.

One could ask the question: What is the chance that 100 bottles are perfect when only 5 bottles are tested to be perfect. Gossett turned the question around: How many bottles should I test that turn out to be perfect, before I can say with a certainty of x% that all 100 bottles are perfect. The term perfect refers to the degrees sacharrine of the malt extract, which had to be within 0.5 degrees of the targeted 133 degrees.

Gossett calculated this accuracy of estimates from different sample sizes and plotted it in a table. We call it the t-table and the method is named after the Student t-test. He found out that with only 4 samples, he could get within the 0.5 degrees in 92% of the time.

The Student pseudonym

Gossett was not allowed to publish under his own name, since other breweries would find out the efficiency of their method to test for quality. However, he was allowed to publish under a pseudonym, namely Student. The publication of his work went largely unnoticed. However, Some people, amongst which R.A. Fisher thought Gossett’s ideas were brilliant and could determine whether results between two groups were statistically significant. In 1925 1 Fisher published an important work. If a certain result has a probability of less than 5% to occur by chance, it’s stated to be statistically significant. The choosing of 5%, or 0.05 (also known as the p-value) was arbitrary and became quite controversial. Medical, Economic and Psychology Journals use the p-value in research.

Crisis in science

However, lately there has been a crisis in science 2. Not only because of so-called p-hacking, but also low power, publication bias, transparency etc. which make reproducibility of studies a major difficulty. According to several studies of medicine, psychology and economics, more than half of studies are not reproducible. 34.

With these issues coming to mind, a p-value of 0.005 is proposed. This value, however, is also arbitrary. Perhaps we should follow Gossett’s methodology. He was a man that looked to be rational in his work. He did not want to create structures for how research ought to be or create criteria for quality assessment. No, he was more interested in solving problems.

P-values have no significance when they do not solve problems. Significant p-values have no value when they do not solve problems. 


Articles used:

Researchers want to redefine the threshold for scientific discovery from 0.05 to 0.005
The Guinness brewer who revolutionzed statistics

The rise of the low-fat diet

The rise of the low-fat diet

In the 1980s and 1990s American 1 medical culture was dominated by the idea that a low-fat diet was the key to a healthy diet. Not only science promoted this idea, but government, food industry and media played an important role too. How did this ideology of low-fat conquer America?

The author uses four areas to answer this question

  • The American tradition of low-fat low-calorie diets for weight reduction
  • The diet-heart hypothesis dating from the post-WW II era
  • The politics of food and low fat
  • The promotion of low fat by the popular health media

The American tradition of low-fat low-calorie diets for weight reduction
Peter Stearns 2 showed that dieting culture started early in the 20th century. American women wanted to lose weight, especially the middle and upper-middle class white women. The impetus was aesthetic rather than health. Women wanted to look good in the new fashionable and less revealing clothing of the 1920s. And by the end of the 20th century we knew that 1g of fat contains 9 calories, whereas 1 g of carbohydrates or protein contains 4 calories. Low calorie intake meant low fat intake. Women started to weigh themselves and the conquering idea was that your weight should stay constant over the years. A 40-year old women should weigh the same as when she was 18 or 25-years old. This notion of weight stability is contested now. According to new research 3, being slightly overweight is health-promoting, especially in elderly people.

The main point, argues the author, is that the low-fat diet to reduce weight idea started off for aesthetic reasons and only in 1950s became popularly promoted by physicians for cardiovascular health. Even though middle-class Americans were familiar with the low-fat concept, they did not like it and this was well before the fast-food market rise in the 1950s. Middle-class Americans consumed a lot of meat and less emphasis was placed on fruits and vegetables. Anne Barone [4.  A lifestyle author], recounts the 1950s in Texas: “The only sanctioned pleasurable activity was eating”. These American values stem from consumerism: “bigger is better” and “quantity over quality”. A supermarket would have more desserts than fresh fruits. Only in the late 1950s – due to medical and technological research advances – experts advised a low-fat diet to those with risk factors and by the 1980s for every American. The idea of a low-fat diet became the norm. It was widely accepted that all Americans would benefit from a low-fat diet.

The diet-heart hypothesis dating from the post-WW II era
In the 1940s coronary heart disease was the leading cause of death in the USA. This triggered a host of studies 4 to identify the causes of heart disease. These studies formulated what became known as the diet-heart hypothesis which holds that diets high in saturated fats and cholesterol are a major cause of coronary heart disease. Several scientists 5 and the American Heart Association proposed a modest proposal to subscribe to low fat diets. In 1977, the American Senate issued a report urging Americans to eat healthier and avoid high-fats. At the same time, economic forces were trying to sabotage this effort. By 1984 scientists supported the idea that healthy food not only prevented heart disease, but also promoted weight loss. Thus a healthy diet was not only for those at risk, but for everyone except babies. The diet-heart hypothesis won support in federal public policy, among health-care practitioners and the popular media, despite not being proven true. Fat was blamed for overweight, obesity and coronary heart disease. Other reports by Surgeon General emphasized the health dangers of dietary fat and in 2000 it was labeled 6 as the unhealthiest part of the American diet.

The politics of food and low fat
The Senate’s report was issued in 1977 telling people to eat low fat. They recommended eating more fruits, vegetables, poultry, and fish and less meat, eggs and high-fat foods. Under pressure from especially the food industry, the report changed its recommendation. For example, the revision changed ‘reduce meat consumption’ to ‘choose meats and fish that will reduce saturated fats’. Other institutions followed, and year after year, the policies became clearer despite protests by the food industry and a consensus among scientists was forged. By the end of the century both Surgeon General and WHO were promoting low fat. The food industry changed its course and realized profit-making opportunities. By the 1990s the industry replaced fat with sugar in processed foods and these took over the supermarket shelves. Low-fat foods had just as many calories as former high-fat versions 7. In 1992, the food pyramid 8 was released and gained wide publicity, promoting low fat. The AHA 9 released its own low-fat campaign by selling approval seals on food products. Fresh food was not labeled, and consumers thought processed foods were healthier. At the end of the paragraph, the author asks rhetorically whether low fat is the only determinant to healthy food, since processed products filled with sugar qualified for the AHA healthy-heart seal. These products, ironically, promoted the fattening of America.

The promotion of low fat by the popular health media
Cholesterol and fat were destroyed by the 1980s due to scientific reports and federal campaigns. The magazine Prevention gained popularity with articles promoting healthy dieting and generated revenue from low-fat processed food advertisements. Another popular media platform, the New York Times, was spreading the message too. In the late 1980s cholesterol took the center stage. Scientific studies suggested that cholesterol was very bad. Yet there was no proof of low-fat dieting reducing heart disease. The New York Times promoted low-fat dieting based on ‘an accumulation of indirect evidence.’ Studies done by Dr.Ornish 10 suggested that a low-fat diet could not only prevent heart disease, but also reverse it. This led to the idea of if low fat is good, then no fat is better. Scientists wondered about the general applicability: whether low-fat dieting should be recommended for every American, since by then it was known that the body produces its own cholesterol too. Also, studies until then studied middle-aged men. Scientists had not studied women or the elderly. Yet the consensus was that cholesterol should be lowered and low-fat dieting should apply for every American. With this consensus in place and the idea that no fat is better than low-fat, Prevention magazine filled their pages with nonfat processed food advertisements. Weight loss was the hype of 1992 and people focused more on fat than on calories. Editor Bricklin praised Snackwell’s nonfat cookies. Two years later, he would write about the Snackwell phenomenon; that the nonfats in fact contributed to the rise of obesity. Yet, fat-free ads continued to dominate the public mind. Americans thought they could eat anything as much as they liked if it was low in fat. With the advancement of science, researchers found out that men and women react differently to heart disease. Also, the idea of the set-point theory found ground. This is the idea that each person’s weight has a stable set point which is difficult, if not impossible, to change. In the late 1990s Jane Brody 11 explained that dieting needs an individualized approach, suggesting that a one-size-fits-all model might not be the most effective. This is a change from her earlier stance on the matter.

Two important challenges to low-fat diet emerged: the development of statin and its proven use in lowering cholesterol therapeutically, suggesting drugs are more effective than dieting and thus challenging the hegemony of low-fat diet. The second is scientific dissent. Already in the early 1950s researchers 12 claimed it was not about the amount of fat, but the kind of fat one consumes. This skepticism re-emerged in the 1990s. Dr. Willet 13 noted that public health officials had been very dogmatic about the low-fat diet’s efficacy and explained that there was no proof the diet worked. Other researchers noted that the evidence is not as clear as wanted, but that the strategy of low-fat consumption was overall a laudatory goal. 14. Dr. Willet also noted that the substitution of carbohydrates for fats caused the body to reduce HDL 15 while raising triglyceride fats, thought to be bad fats. The skeptics recommended the Mediterranean diet: high in monounsaturated fats, low in saturated fats. This idea of the kind of fat was making place for the idea of the amount of fat. Another popular idea was that only calories count.

Since the 1970s America had gotten fatter. Obesity rose by 50%. People were confused. The millennium change brought new problems; sugar and stress came to the center of the stage and nor people nor scientists agreed on the best method to prevent obesity. Scientists had no consensus and thus the general advice would be to consume in moderation. There is no one-size-fits-all advice. Fat diets differ between genders, ages, borders, races, and cultures. By now, it is clear that the low-fat diet campaign had unintended consequences and made people believe that they could eat anything in any quantity as long as its low in fat.


So how did the low-fat idea conquer America? There was already a culture beginning to form of low-fat dieting for aesthetic reasons. When science confirmed the health benefits, people were reluctant to follow and have faith in science. This tremendous faith in science as the ultimate truth came to the political scene. The state promoted low-fat dieting and the food industry played in on this. The popular media, which carried this faith in science, preached the message of low-fat, without regarding the voice of skeptics such as Robert Atkins – whose diet turned out to have effect. Not only did they not regard their ideas, they vigorously attacked them.

Can we really say that the low-fat campaign was not effective? Epidemiologists note a paradox. The mortality due to heart disease fell enormously between 1950-1999, yet the incidence of heart disease remained the same. A study in 1998 16 suggested that the reduced mortality was due to better medical/surgical interventions and secondary prevention rather than primary.

And the low-fat diet, does it work? Not really 17. As of now – but maybe not in the future – the so-called Mediterranean diet is favored.


This article is an excerpt of a summary of La Berges How the Ideology of Low Fat Conquered America
J Hist Med Allied Sci (2008) 63 (2): 139-177