# Herd immunity: how it really works

There are few concepts as trivial yet as widely misunderstood as herd immunity. In a sense, it’s not all that surprising, because frankly, there’s something almost magical about it – herd immunity means that in a population, some people who are not or cannot be immunized continue to reap the benefit of immunization. On its own, this may even be counter-intuitive. And so, unsurprisingly, like many evidently true concepts, herd immunity has its malcontents – going so far as to condemn the very idea as a ‘CDC lie’ – never mind that the concept was first used in 1923, well before the CDC was established.1

Now, let’s ignore for a moment what Dr Humphries, a nephrologist-turned-homeopath with a penchant for being economical with the truth when not outright lying, has to say – not because she’s a quack but because she has not the most basic idea of epidemiology. Instead, let’s look at this alleged ‘myth’ to begin with.

### Herd immunity: the cold, hard maths

Our current understanding of herd immunity is actually a result of increasing understanding of population dynamics in epidemiology, towards the second half of the 20th century. There are, on the whole, two ways to explain it. Both are actually the same thing, and one can be derived from the other.

#### The simple explanation: effective $R_0$$R_0$ depletion

The simple explanation rests on a simplification that makes it possible to describe herd immunity in terms that are intelligible at the level of high school maths. In epidemiology, $R_0$ (pron. ‘arr-nought‘, like a pirate), describes the basic reproduction rate of an infectious disease.2 To put it at its most simplistic: $R_0$ is the number of cases produced by each case. The illustration on the side shows the index case (IDX) and the first two generations of an infection with $R_0 = 3$.

Now, $R_0$ is a theoretical variable. It is usually observationally estimated, and don’t take measures intended to reduce it into account. And that’s where it gets interesting.

Consider the following scenario, where a third of the population is vaccinated, denoted by dark black circles around the nodes representing them. One would expect that of the 13 persons, a third, i.e. about. 4 , would remain disease-free. But in fact, over half of the people will remain disease-free, including three who are not vaccinated. This is because the person in the previous generation did not pass on the pathogen to them. In other words, preventing spread, e.g. by vaccination or by quarantine, can affect and reduce $R_0$. Thus in this case, the effective $R_0$ was closer to 1.66 than 3 – almost halving the $R_0$ by vaccinating only a third of the population.

We also know that for infections where the patient either dies or recovers, the infection has a simple ecology: every case must be ‘replaced’. In other words, if the effective $R_0$ falls below 1, the infection will eventually peter out. This happens quite often when everyone in a population is dead or immune after an infection has burned through it (more about that later).

Thus, the infection will be sustainable if and only if

$R_{0} \geq 1$

Under the assumption of a 100% efficient vaccine, the threshold value $\bar{p_V}$ after which the infection will no longer be able to sustain itself is calculated as

$\bar{p_V} = 1 - \frac{1}{R_0}$

Adjusting for vaccine efficacy, $E_V$, which is usually less than 100%, we get

$\bar{p_V} = \frac{1-\frac{1}{R_0}}{E_V} = \frac{R_0 - 1}{R_0 E_V}$

For a worked example, let’s consider measles. Measles has an $R_0$ around 15 (although a much higher value has been observed in the past, up to 30, in some communities), and the measles vaccine is about 96% effective. What percentage of the population needs to be vaccinated? Let’s consider $\bar{p_V}$, the minimum or threshold value above which herd immunity is effective:

$\bar{p_V} = \frac{R_0 - 1}{R_0 E_V} = \frac{15-1}{15 \cdot 0.96} = \frac{14}{14.4} \approx 97.22\%$

#### The more complex explanation: $\mathcal{SIR}$$\mathcal{SIR}$ models

Note: this is somewhat complex maths and is generally not recommended unless you’re a masochist and/or comfortable with calculus and differential equations. It does give you a more nuanced picture of matters, but is not necessary to understand the whole of the argumentation. So feel free to skip it.

The slightly more complex explanation relies on a three-compartment model, in which the population is allotted into one of three compartments: $\mathcal{S}$usceptible, $\mathcal{I}$nfectious and $\mathcal{R}$ecovered. This model makes certain assumptions, such as that persons are infectious from the moment they’re exposed and that once they recover, they’re immune. There are various twists on the idea of a multicompartment model that takes into account the fact that this is not true for every disease, but the overall idea is the same.3 In general, multicompartment models begin with everybody susceptible, and a seed population of infectious subjects. Vaccination in such models is usually accounted for by treating them as ‘recovered’, and thus immune, from $t = 0$ onwards.

Given an invariant population (i.e. it is assumed that no births, deaths or migration occurs), the population can be described as consisting of the sum of the mutually exclusive compartments: $P = \mathcal{S}(t) + \mathcal{I}(t) + \mathcal{R}(t)$. For the same reason, the total change is invariant over time, i.e.

$\frac{d \mathcal{S}}{d t} + \frac{d \mathcal{I}}{d t} + \frac{d \mathcal{R}}{d t} = 0$

Under this assumption of a closed system, we can relate the volumes of each of the compartment to the transition probabilities $\beta$ (from $\mathcal{S}$ to $\mathcal{I}$) and $\gamma$ (from $\mathcal{I}$ to $\mathcal{R}$), so that:

$\frac{d \mathcal{S}}{d t} = - \frac{\beta \mathcal{I} \mathcal{S}}{P}$

$\frac{d \mathcal{I}}{d t} = \frac{\beta \mathcal{I} \mathcal{S}}{P} - \gamma \mathcal{I}$

$\frac{d \mathcal{R}}{d t} = \gamma \mathcal{I}$

Incidentally, in case you were wondering how this connects to the previous explanation: $R_0 = \frac{\beta}{\gamma}$.

Now, let us consider the end of the infection. If $\mathcal{S}$ is reduced sufficiently, the disease will cease to be viable. This does not need every individual to be recovered or immune, however, as is evident from dividing the first by the third differential equation and integrating and substituting $R_0$, which yields

$\displaystyle \mathcal{S}(t) = \mathcal{S}(0) e^{\frac{-R_0 (\mathcal{R}(t)-\mathcal{R}(0))}{P}}$

Substituting this in, the limit of $\mathcal{R}$, as $t$ approaches infinity, is

$\displaystyle \lim_{t\to\infty}\mathcal{R}(t) = P - \lim_{t\to\infty}\mathcal{S}(t) = P - \mathcal{S}(0) e^{\frac{-R_0 (\mathcal{R}(t)-\mathcal{R}(0))}{P}}$

From the latter, it is evident that

$\displaystyle \lim_{t\to\infty}\mathcal{S}(t) \neq 0 \mid \mathcal{S}(0) \neq 0$

In other words, once the infection has burned out, there will still be some individuals who are not immune, not immunised and not vaccinated. These are the individuals protected by herd immunity. This is a pretty elegant explanation for why herd immunity happens and how it works. There are three points to take away from this.

First, herd immunity is not unique to vaccination. The above finding in relation to the nonzero limit of $\lim_{t\to\infty}\mathcal{S}(t)$ holds as long as $\mathcal{S}(0) \neq 0$, but regardless of what $\mathcal{R}(0)$ is. In other words, herd immunity is not something artificial.

Two, for any $i \in \mathcal{S}$ (that is, any susceptible person) at time $t$, the probability of which compartment he will be in at $t+1$ depends on whom he encounters. That, statistically, depends on the relative sizes of the compartments. In this model, the assumption is that the sample $i$ will encounter will reflect the relative proportions of the individual compartments’ sizes. Thus if $i$ meets $n$ people at time $t$, each compartment will be proportionally represented, i.e. for any compartment $\mathcal{C}$, the proportion will be $\frac{\mathcal{C}(t)}{P-1}$ for all $\mathcal{C} \neq \mathcal{S}$, for which the proportion will be $\frac{\mathcal{S}(t) - 1}{P - 1}$, since one cannot meet oneself. Given that the transition probability $\beta_{i}(t)$ is assumed to equal the probability of meeting at least one element of $\mathcal{I}$, the following can be said. $i$‘s risk of infection depends on the relationship of $n$ and $\mathcal{I}(t)$, so that $i$ is likely to get infected if

$\displaystyle n \frac{\mathcal{I}(t)}{P-1} \geq 1$

This elucidates two risk factors clearly, and the way to reduce them: reduce interactions (quarantine/self-quarantine), thereby reducing $n$, and reduce the proportion of infectious cases ($\frac{\mathcal{I}(t)}{P-1}$). The latter is where herd immunity from immunisation comes in. Recall that for a constant $n$, $i$‘s risk of infection at $t$ rises as $\mathcal{I}(t)$ rises.4 Recall also that while susceptible cases can turn into infectious cases, recovered (or vaccinated) cases cannot. And so, as $\mathcal{R}(0)$ converges to $P-1$,5 $i$‘s risk of infection at any time $t$, denoted by $\beta_{i}(t)$, falls. In other words,

$\displaystyle \lim_{\mathcal{R}(0) \to P-1} \beta_{i}(t) = 0$

Or to put it simply: the more are vaccinated at the start, the lower the probability, all things being equal, to meet someone who can pass on the infection.6

A final point to note is that this is primarily a model of statistical dynamics, and deals with average probabilities. It does not – it cannot – take account of facts like that some some susceptible people are just darn unlucky, and bump into a flock of unvaccinated, shiny-eyed snowflakes. Equally, in some places, susceptible people and infected people congregate, creating a viral breeding ground, also known as a Waldorf school. There are agent based models, which are basically attempts at brute force hacking reality, that can take account of such disparities. The takeaway is that herd immunity does not mean no susceptible individual will get infected. What it does mean is that their probability of getting infected is going to be significantly lower, for two reasons. First given a constant number of encounters ($n$), the likelihood of one of them being with an infectious individual is going to be much lower. More importantly, however, because of herd immunity, the disease is going to be able to persist in the population for a far shorter time – eventually it will burn through the small number of ‘accessible’ susceptible persons. Since the cumulative risk $\beta_{i}^T$ for $i \in \mathcal{S}$ for an infection that dies out after time $T$ is defined as

$\beta_i^T = \displaystyle \int\limits_0^T \beta_{i}(t) \, \mathrm{d}t$

– the sooner the infection dies out, the smaller the likelihood that $i$ will be infected. With that mathematical basis, let’s tackle a few of the myths about herd immunity.

### Myth #1: herd immunity only works with naturally acquired immunity

This argument goes roughly along the following lines: herd immunity does exist, but it only exists if and where the immunity is acquired the ‘natural’ way, i.e. by surviving the disease. Case in point:

The \$64,000 question, of course, is what the difference is between the residual immunity from a vaccine and the residual immunity from having survived the illness. A vaccine effectively ‘simulates’ the illness without actually causing the pathological symptoms. From the perspective of the immune system, it is largely irrelevant whether it has been exposed to an actual virus that can damage the body, or merely a capsid protein that is entirely harmless but will nonetheless elicit the same immune reaction. That should suffice to bust this myth, but it’s worth considering immunity quantitatively for a moment. As we have seen above, the source of immunity doesn’t matter. In fact, it doesn’t even have to be immunity: culling every animal except one in a herd is an entirely good way to reduce disease transmission. So is sealing oneself away from the rest of society and spending the evenings telling sexually explicit stories, as the heroes and heroines of Boccaccio’s Decameron have done, since we know that

$\displaystyle n \frac{\mathcal{I}(t)}{P-1} \geq 1$

Boccaccio’s crowd of assorted perverts knew nothing of all this, of course, but they did know that if they reduced $n$, the number of contacts with possibly infected persons, their chances of surviving the plague would increase. As it indeed did. Score one for medieval perverts. The bottom line is that it is entirely immaterial how immunity was obtained.

### Myth #2: Herd immunity is a concept deriving from animals. It doesn’t work on humans.

This is one of the more outlandish claims, but shockingly, it actually has a tiny kernel of truth.

Now, much of the above is a veritable storehouse of insanity, but the point it makes in the beginning has some truth to it. In human populations, herd immunity sometimes behaves anomalously, because humans are not homogenously distributed. This is true a fortiori for humans who decide not to vaccinate, who – for better or worse – tend to flock in small groups. The term of venery for a bunch of anti-vaxxers is, in case you were wondering, a ‘plague’.7

Herd immunity was, in fact, observed in a range of species. Humans are different as we can knowingly and consciously decide to create herd immunity in our population and protect our fellow men, women and children, the last of whom are particularly susceptible to infectious diseases, from some of the worst killers.

### Myth #3: If herd immunity can be obtained through natural immunity, surely we don’t need vaccines.

This argument has recently been peddled by the illustrious Kelly Brogan MD, who bills herself as a ‘holistic psychiatrist’ who threw away her script pad, which means she tends exclusively to the worried well and those with mild mental health issues where medication does not play as decisive a role as it does in, say, schizophrenia, severe PTSD, crippling anxiety disorders or complex neuropsychiatric post-insult phenomena.8 Here’s her foray into epidemiology, something she vaguely remembers studying in her first year of med school.

In this, Dr Brogan has successfully found almost a century old evidence for what everybody knew, namely that herd immunity can be naturally obtained. To anyone who has read the maths part above, this should evoke a sensation of ‘DUH!’. The problem is twofold. One, the ‘actual virus’ has an unsavoury fatality rate of 0.1%, not including the horribly tragic, heartbreaking late consequence of measles known as SSPE.9 Two, and perhaps more important: you don’t get lifelong, natural immunity if you die. This may have somehow escaped Dr Brogan’s attention, but part of the point of herd immunity is to protect those who would not survive, or would suffer serious sequelae, if they contracted the infection. What we don’t know, of course, how many of that 68% suffered permanent injuries, and how many are not included because they died. What we do know is that all 68% probably had a miserable time. Anyone who thinks measles is so fantastic should start by contracting it themselves.

### Myth #4: Herd immunity means 95% need to be vaccinated to prevent a disease.

This one comes courtesy of Sarah aka the Healthy Home Economist,10, who, to what I presume must be the chagrin of her alma mater, states she has a Master’s from UPenn. Suspiciously enough, she does not state what in. I am somehow pretty sure it’s not public health.

The tedious conspiracy theory aside, it is quite evident just how little she understands of herd immunity. No – herd immunity is not based upon11 the idea that 95% must be vaccinated, and it is most definitely not based on the idea that 100% must be vaccinated. Indeed, the whole bloody point of herd immunity is that you do not need to vaccinate 100% to protect 100%. In fact, given the $R_0$ and vaccine efficacy $E_V$, we can predict the threshold vaccination rate for herd immunity quite simply, as demonstrated earlier: the threshold value, $\bar{p_V}$, can be calculated as

$\bar{p_V} = \frac{R_0 - 1}{R_0 E_V}$

As an illustration, the herd immunity threshold $\bar{p_V}$ for mumps, with an efficacy of 88%12 and an $R_0$ of around 5.5, is $\approx 92.98\%$, while for Ebola, which has a very low $R_0$ around 2.0, herd immunity sets in once about 50% are immune.13

And those ‘conventional health authorities’? That’s what we call health authorities whose ideas work.

### Myth #5: If vaccines work, why do we need herd immunity?

This argument is delightfully idiotic, because it, too, ignores the fundamental underlying facts of herd immunity. Quite apart from the fact that some people cannot receive some or all vaccines and other people can receive vaccines but may not generate sufficient antibody titres to have effective immunity, sometimes vaccines simply fail. Few things are 100%, and while vaccines are designed to be resilient, they can degrade due to inappropriate storage or fail to elicit a sufficient response for some other reason. Unlike wearing deodorant (or ‘deoderant’, as spelling-challenged anti-vaxxers would say), infections can sometimes be imagined as a chain of transmission. This is a frequently used model to explain the consequences of not vaccinating on others.

In this illustration, an index patient (IDX) is infected and comes in contact with G1, who in turn comes into contact with G2 who in turn comes into contact with G3. In the first case, G1, G2 and G3 are all vaccinated. The vaccine may have a small failure rate – 2% in this case – but by the time we get to G3, his chances of contracting the infection are 1:125,000 or 0.0008%. In the second case, G2 is unvaccinated – if G1’s vaccine fails, G2 is almost guaranteed to also fall ill. By not vaccinating, his own risk has increased 50-fold, from 0.04% to 2%. But that’s not all – due to G2’s failure to vaccinate, G3 will also be affected – instead of the lottery odds of 1:125,000, his risk has also risen 50-fold, to 1:2,500. And this 50-fold increase of risk will carry down the chain of potential transmission due to G2’s failure to vaccinate. No matter how well vaccines work, there’s always a small residual risk of failure, just as there is a residual risk of failure with everything. But it takes not vaccinating to make that risk hike up 50-fold. Makes that deodorant (‘deoderant’?) analogy sound rather silly, right?

## Conclusion

Admittedly, the mathematical basis of herd immunity is complex. And the idea itself is somewhat counterintuitive. None of these are fit excuses for spreading lies and misinformation about herd immunity.

I have not engaged with the blatantly insane arguments (NWO, Zionists, Masonic conspiracies, Georgia Guidestones), nor with the blatantly untrue ones (doctors and public health officers are evil and guided just by money as they cash in on the suffering of innocent children). I was too busy booking my next flight paid for by Big Pharma.14 Envy is a powerful force, and it’s a good way to motivate people to suspect and hate people who sacrificed their 20s and 30s to work healing others and are eventually finally getting paid in their 40s. But it’s the myths that sway the well-meaning and uncommitted, and I firmly believe it’s part of our job as public health experts to counter them with truth.15

In every social structure, part of co-existence is assuming responsibility not just for oneself but for those who are affected by our decisions. Herd immunity is one of those instances where it’s no longer about just ourselves. Many have taken the language of herd immunity to suggest that it is some sort of favour or sacrifice done for the communal good, when it is in in fact the very opposite – it is preventing (inadvertent but often unavoidable) harm to others from ourselves.

And when the stakes are this high, when it’s about life and death of millions who for whatever reason cannot be vaccinated or cannot form an immune response, getting the facts right is paramount. I hope this has helped you, and if you know someone who would benefit from it, please do pass it on to them.

References   [ + ]

 1 ↑ Topley, W. W. C. and Wilson, G. S. (1923). The spread of bacterial infection; the problem of herd immunity. J Hyg 21:243-249. The CDC was founded 23 years later, in 1946. 2 ↑ Why $R_0$$R_0$? Because it is unrelated to $\mathcal{R}$$\mathcal{R}$, the quantity denoting recovered cases in $\mathcal{S(E)IR}$$\mathcal{S(E)IR}$ models – which is entirely unrelated. To emphasize the distinction, I will use mathcal fonts for the compartments in compartment models. 3 ↑ I hope to write about SIS, SEIR and vital dynamic models in the near future, but for this argument, it really doesn’t matter. 4 ↑ Technically, as $\frac{\mathcal{I}(t)}{P - 1}$$\frac{\mathcal{I}(t)}{P - 1}$ rises, but since the model presupposes that $P$$P$ is constant, it doesn’t matter. 5 ↑ Since otherwise $\mathcal{R} = P$$\mathcal{R} = P$ and $\mathcal{S} = 0$$\mathcal{S} = 0$, and the whole model is moot, as noted above. 6 ↑ Note that this does not, unlike the $R_0$$R_0$ explanation, presuppose any degree of vaccine efficacy. An inefficiently vaccinated person is simply in $\mathcal{S}$$\mathcal{S}$ rather than $\mathcal{R}$$\mathcal{R}$. 7 ↑ Initially, ‘a culture’ was proposed, but looking at the average opponent of vaccination, it was clear this could not possibly work. 8 ↑ In other words, if you have actual mental health issues, try an actual psychiatrist who follows evidence-based protocols. 9 ↑ Subacute sclerosing panencephalitis is a long-term delayed consequence of measles infection, manifesting as a disseminated encephalitis that is invariably fatal. There are no adjectives that do the horror that is SSPE justice, so here’s a good summary paper on it. 10 ↑ As a rule, I don’t link to blogs and websites disseminating harmful information that endangers public health. 11 ↑ Correct term: ‘on’ 12 ↑ As per the CDC. 13 ↑ Efficacy $E_V$$E_V$ is presumed to be 100% where immunity is not acquired via vaccination but by survival. 14 ↑ Anyone in public health is happy to tell you those things don’t merely no longer exist, they never even existed in our field. 15 ↑ And, if need be, maths.

# Are you looking for a data science sensei?

Maybe you’re a junior data scientist, maybe you’re a software developer who wants to go into data science, or perhaps you’ve dabbled in data for years in Excel but are ready to take the next step.

If so, this post is all about you, and an opportunity I offer every year.

You see, life has been very good to me in terms of training as a data scientist. I have been spoiled, really – I had the chance to learn from some of the best data scientists, work with some exceptional epidemiologists, experience some unusual challenges and face many of the day-to-day hurdles of working in data analytics. I’ve had the fortune to see this profession in all its contexts, from small enterprises to multi-million dollar FTSE100 companies, from well-run agile start-ups to large and sometimes pretty slow dinosaurs, from government through the private sector to NGOs: I’ve seen it all. I’ve done some great things. And I’ve made some superbly dumb mistakes.

And so, at the start of every year, I have opened applications for young, start-of-career data scientists looking for their Mr. Miyagi. Don’t worry: no car waxing involved. I will be choosing a single promising young data scientist and pass on as much as I can of my so-called wisdom. At the end, your skills will shine like Mr. Miyagi’s 1947 Ford Deluxe Convertible. There’s no catch, no hidden trap, no fees or charges involved (except the one mentioned below).

### Eligibility criteria

To be eligible, you must be:

• 18 or above if you are taking a gap year or not attending a university/college.
• You do not have to have a formal degree in data science or a relevant subject, but you must have completed it if you do. In other words: if you’re in your 3rd year of an English Lit degree, you’re welcome to apply, but if you’re in the middle of your CS degree, you have to wait until you’re finished – sorry. The same goes if you intend to go straight on to a data science-related postgrad within the year.
• Have a solid basis in mathematics: decent statistics, combinatorics, linear algebra and some high school calculus are the very minimum.
• You must be familiar with Python (3.5 and above), and either familiar with the scientific Python stack (SciPy, NumPy, Pandas, matplotlib) or willing to pick up a lot on the go.
• Be willing to put in the work: we’ll be convening about once every week to ten days by Skype for an hour, and you’ll probably be doing 6-10 hours’ worth of reading and work for the rest of the week. Please be realistic if you can sustain this.
• If, as recommended, you are working on an AWS EC2 instance, be aware this might cost money and make sure you can cover the costs. In practice, these are negligible.
• You must understand that this is a physically and intellectually strenuous endeavor, and it is your responsibility to know whether you’re physically and mentally up for the job. However, no physical or mental disabilities are regarded as automatically excluding you of consideration.
• You must not live in, reside in or be a citizen of any of the countries listed in CFR Title 22 Part 126, §126.1(d)(1) and (2).
• You must not have been convicted of a felony anywhere. This includes ‘spent’ UK criminal convictions.

Sounds good? Apply here.

### Preferred applicants

When assessing applications, the following groups are given preference:

• Persons with mental or physical disabilities whose disability precludes them from finding conventional employment – please outline this situation on the application form.
• Honourably discharged (or equivalent) veterans of NATO forces and the IDF – please include member 4 copy of DD-214, Wehrdienstzeitbescheinigung or equivalent document that lists type of discharge.

### What we’ll be up to

Over the 42 weeks to follow, you will be undergoing a rigorous and structured semi-self-directed training process. This will take your background, interests and future ambitions into account, but at the core, you will:

• master Python’s data processing stack,
• learn how to visualize data in Python,
• work with networks and graph databases, including Neo4j,
• acquire the correct way of presenting results in data science to stakeholders,
• delve into cutting-edge methods of machine learning, such as deep learning using keras,
• work on problems in computer vision and get familiar with the Python bindings of OpenCV,
• scrape data from social networks, and
• learn convenient ways of representing, summarizing and distributing our results.

The programme is divided into three ‘terms’ of 14 weeks each, which each consist of 9 weeks of directed study, 4 weeks of self-directed project work and one week of R&R.

### What you’ll be getting out of this

In the past years, mentees have noted the unusual breadth of knowledge they have acquired about data science, as well as the diversity of practical topics and the realistic question settings, with an emphasis on practical applications of data science such as presenting data products. I hope that this year, too, I’ll be able to convey the same important topics. Every year is a little different as I try to adjust the course to meet the individual participant’s needs.

The programme is not, of course, accredited by any accreditation body, but a certificate of completion will be issued to any participant who wishes so.

### Application process

Simply fill in the form below and send it off by 14 January 2018. The top contenders will be contacted by e-mail or telephone for a brief conversation thereafter. Finally, a lucky winner will be picked by the 21st January 2018. Easy peasy!

### FAQ

#### Q: What does ‘semi-self-directed’ mean? Is there a fixed curriculum?

A: No. There are some basic topics (see list above) that I think are quite likely to come up, but ultimately, this is about making you the data scientist you want to be. For this reason, we’ll begin by planning out where you want to improve – kinda like a PT gives you a training plan before you start out at their gym. We will then adjust as needed. This is not an exam prep, it’s a learning experience, and for that reason, we can focus on delving deeper and getting the fundaments right over other cramming in a particular curriculum.

#### Q: Can I bring your own data?

A: Sure. In general, we’ll be using standard data sets, because they’re well-known and high-quality data. But if you have a dataset you collected or are otherwise entitled to use that would do equally well, there’s no reason why we couldn’t use it! Note that you must have the right to use and share the data set, meaning it’s unlikely you’re able to use data sets from your day job.

#### Q: Will this give me an employment advantage?

A: I don’t quite know – it’s impossible to predict. The field of data science degrees is something of a Wild West still, and while some reputable degrees have emerged, others are dubious. Employers still don’t know what to go by. However, you will most definitely be better prepared for an employment interview in data science!

#### Q: Why are you so keen on presenting data the right way?

A: Because as data scientists, we’re expected to not merely understand the data and draw the right conclusions, but also to convey them to stakeholders at various levels, from plant management to C-suite, in a way that gets the right message across at the first go.

#### Q: You’re a computational epidemiologist. Can I apply even if my work doesn’t really involve healthcare?

A: Sure. The principles are the same, and we’re largely focusing on generic topics. You might be exposed to bits and pieces of epidemiology, but I can guarantee it won’t hurt.

#### Q: Why do you only take on one mentee?

A: To begin with, my life is pretty busy – I have a demanding job, a family and – shock horror! – I even need to sleep every once in a while. More importantly, I want to devote my undivided attention to a worthy candidate.

#### Q: How come I’ve never heard of this before?

A: Until now, I’ve largely gotten mentees by word of mouth. I am concerned that this is keeping some talented people out and limiting the pool of people we should have in. That’s why this year, I have tried to make this process much more transparent.

No.

No.

#### Q: I have more questions.

A: You can ask them here.

# The sinful algorithm

In 1318, amidst a public sentiment that was less than enthusiastic about King Edward II, a young clerk from Oxford, John Deydras of Powderham, claimed to be the rightful ruler of England. He spun a long and rather fantastic tale that involved sows biting off the ears of children and other assorted lunacy.1 Edward II took much better to the pretender than his wife, the all-around badass Isabella of France, who was embarrassed by the whole affair, and Edward’s barons, who feared more sedition if they let this one slide. As such, eventually, Deydras was tried for sedition.

Deydras’s defence was that he has been convinced to engage in this charade by his cat, through whom the devil appeared to him.2 That did not meet with much leniency, it did however result in one of the facts that exemplified the degree to which medieval criminal jurisprudence was divorced from reason and reality: besides Deydras, his cat, too, was tried, convicted, sentenced to death and hung, alongside his owner.

Before the fashionable charge of unreasonableness is brought against the Edwardian courts, let it be noted that other times and cultures have fared no better. In the later middle ages, it was fairly customary for urban jurisdictions to remove objects that have been involved in a crime beyond the city limits, giving rise to the term extermination (ex terminare, i.e., [being put] beyond the ends).3 The Privileges of Ratisbon (1207) allowed the house in which a crime took place or which harboured an outlaw to be razed to the ground – the house itself was as guilty as its owner.4 And even a culture as civilised and rationalistic as the Greeks fared no better, falling victim to the same surge of unreason. Hyde describes

The Prytaneum was the Hôtel de Ville of Athens as of every Greek town. In it was the common hearth of the city, which represented the unity and vitality of the community. From its perpetual fire, colonists, like the American Indians, would carry sparks to their new homes, as a symbol of fealty to the mother city, and here in very early times the prytanis or chieftain probably dwelt. In the Prytaneum at Athens the statues of Eirene (Peace) and Hestia (Hearth) stood; foreign ambassadors, famous citizens, athletes, and strangers were entertained there at the public expense; the laws of the great law-giver Solon were displayed within it and before his day the chief archon made it his home.
One of the important features of the Prytaneum at Athens were the curious murder trials held in its immediate vicinity. Many Greek writers mention these trials, which appear to have comprehended three kinds of cases. In the first place, if a murderer was unknown or could not be found, he was nevertheless tried at this court. Then inanimate things – such as stones, beams, pliece of iron, etc., – which had caused the death of a man by falling upon him-were put on trial at the Prytaneum, and lastly animals, which had similarly been the cause of death.
Though all these trials were of a ceremonial character, they were carried on with due process of law. Thus, as in all murder trials at Athens, because of the religious feeling back of them that such crimes were against the gods as much as against men, they took place in the open air, that the judges might not be contaminated by the pollution supposed to exhale from the prisoner by sitting under the same roof with him.
(…)
[T]he trial of things, was thus stated by Plato:
“And if any lifeless thing deprive a man of life, except in the case of a thunderbolt or other fatal dart sent from the gods – whether a man is killed by lifeless objects falling upon him, or his falling upon them, the nearest of kin shall appoint the nearest neighbour to be a judge and thereby acquit himself and the whole family of guilt. And he shall cast forth the guilty thing beyond the border.”
Thus we see that this case was an outgrowth from, or amplification of the [courts’ jurisdiction trying and punishing criminals in absentia]; for if the murderer could not be found, the thing that was used in the slaying, if it was known, was punished.5

Looking at the current wave of fashionable statements about the evils of algorithms have reminded me eerily of the superstitious pre-Renaissance courts, convening in damp chambers to mete out punishments not only on people but also on impersonal objects. The same detachment from reality, from the Prytaneum through Xerxes’s flogging of the Hellespont through hanging cats for being Satan’s conduits, is emerging once again, in the sophisticated terminology of ‘systematized biases’:

Clad in the pseudo-sophistication of a man who bills himself as ‘one of the world’s leading thinkers‘, a wannabe social theorist with an MBA from McGill and a career full of buzzwords (everything is ‘foremost’, ‘agenda-setting’ or otherwise ‘ultimative’!) that now apparently qualifies him to discuss algorithms, Mr Haque makes three statements that have now become commonly accepted dogma among certain circles when discussing algorithms.

1. Algorithms are means to social control, or at the very least, social influence.
2. Algorithms are made by a crowd of ‘geeks’, a largely homogenous, socially self-selected group that’s mostly white, male, middle to upper middle class and educated to a Masters level.
3. ‘Systematic biases’, by which I presume he seeks to allude to the concept of institutional -isms in the absence of an actual propagating institution, mean that these algorithms are reflective of various biases, effectively resulting in (at best) disadvantage and (at worst) actual prejudice and discrimination against groups that do not fit the majority demographic of those who develop code.

Needless to say, leading thinkers and all that, this is absolute, total and complete nonsense. Here’s why.

# A geek’s-eye view of algorithms

We live in a world governed by algorithms – and we have ever since men have mastered basic mathematics. The Polynesian sailors navigating based on stars and the architects of Solomon’s Temple were no less using algorithms than modern machine learning techniques or data mining outfits are. Indeed, the very word itself is a transliteration of the name of the 8th century Persian mathematician Al-Khwarazmi.6 And for most of those millennia of unwitting and untroubled use of algorithms, there were few objections.

The problem is that algorithms now play a social role. What you read is determined by algorithms. The ads on a website? Algorithms. Your salary? Ditto. A million other things are algorithmically calculated. This has endowed the concept of algorithms with an air of near-conspiratorial mystery. You totally expect David Icke to jump out of your quicksort code one day.

Whereas, in reality, algorithms are nothing special to ‘us geeks’. They’re ways to do three things:

1. Execute things in a particular order, sometimes taking the results of previous steps as starting points. This is called sequencing.
2. Executing things a particular number of times. This is called iteration.
3. Executing things based on a predicate being true or false. This is conditionality.

From these three building blocks, you can literally reconstruct every single algorithm that has ever been used. There. That’s all the mystery.

So quite probably, what people mean when they rant about ‘algorithms’ is not the concept of algorithms but particular types of algorithm. In particular, social algorithms, content filtering, optimisation and routing algorithms are involved there.

Now, what you need to understand is that geeks care relatively little about the real world ‘edges’ of problems. They’re not doing this out of contempt or not caring, but rather to compartmentalise problems to manageable little bits. It’s easier to solve tiny problems and make sure the solutions can interoperate than creating a single, big solution that eventually never happens.

To put it this way: to us, most things, if not everything, is an interface. And this largely determines what it means when we talk about the performance of an algorithm.

Consider your washing machine: it can be accurately modelled in the following way.

Your washing machine is an algorithm of sorts. It’s got parameters (water, power, dirty clothes) and return values (greywater tank levels, clean clothes). Now, as long as your washing machine fulfils a certain specification (sometimes called a promise7 or a contract), according to which it will deliver a given set of predictable outputs to a given set of inputs, all will be well. Sort of.

“Sort of”, because washing machines can break. A defect in an algorithm is defined as ‘betraying the contract’, in other words, the algorithm has gone wrong if it has been given the right supply and yields the wrong result. Your washing machine might, however, fail internally. The motor might die. A sock might get stuck in it. The main control unit might short out.

Now consider the following (extreme simplification of an) algorithm. MD5 is what we call a cryptographic hash function. It takes something – really, anything that can be expressed in binary – and gives a 128-bit hash value. On one hand, it is generally impossible to invert the process (i.e. it is not possible to conclusively deduce what the original message was), while at the same time the same message will always yield the same hash value.

Without really having an understanding of what goes on behind the scenes,8 you can rely on the promise given by MD5. This is so in every corner of the universe. The value of MD5("Hello World!") is 0xed076287532e86365e841e92bfc50d8c in every corner of the universe. It was that value yesterday. It will be that value tomorrow. It will be that value at the heat death of the universe. What we mean when we say that an algorithm is perfect is that it upholds, and will uphold, its promise. Always.

At the same time, there are aspects of MD5 that are not perfect. You see, perfection of an algorithm is quite context-dependent, much as the world’s best, most ‘perfect’ hammer is utterly useless when what you need is a screwdriver. As such, for instance, we know that MD5 has to map every possible bit value of every possible length to a limited number of possible hash values (128 bit worth of values, to be accurate, which equates to 2^128 or approximately 3.4×10^38 distinct values). These seem a lot, but are actually teensy when you consider that they are used to map every possible amount of binary data, of every possible length. As such, it is known that sometimes different things can have the same hash value. This is called a ‘collision’, and it is a necessary feature of all hash algorithms. It is not a ‘fault’ or a ‘shortcoming’ of the algorithm, no more than we regard the non-commutativity of division a ‘shortcoming’.

Which is why it’s up to you, when you’re using an algorithm, to know what it can and cannot do. Algorithms are tools. Unlike the weird perception in Mr Haque’s swirl of incoherence, we do not worship algorithms. We don’t tend to sacrifice small animals to quicksort and you can rest assured we don’t routinely bow to a depiction of binary search trees. No more do we believe in the ‘perfection’ of algorithms than a surgeon believes in the ‘perfection’ of his scalpel or a pilot believes in the ‘perfection’ of their aircraft. Both know their tools have imperfections. They merely rely on the promise that if used with an understanding of its limitations, you can stake your, and others’, lives on it. That’s not tool-worship, that’s what it means to be a tool-using human being.

# The Technocratic Spectre

We don’t know the name of the first human who banged two stones together to make fire, and became the archetype for Prometheus, but I’m rather sure he was rewarded by his fellow humans rewarded with very literally tearing out his very literal and very non-regrowing liver. Every progress in the history of humanity had those who not merely feared progress and the new, but immediately saw seven kinds of nefarious scheming behind it. Beyond (often justified!) skepticism and a critical stance towards new inventions and a reserved approach towards progress (all valid positions!), there is always a caste of professional fear-mongerers, who, after painting a spectre of disaster, immediately proffer the solution: which, of course, is giving them control over all things new, for they are endowed with the mythical talents that one requires to be so presumptuous as to claim to be able to decide for others without even hearing their views.

The difference is that most people have become incredibly lazy. The result is that there is now a preference for fear over informed understanding that comes at the price of investing some time in reading up on the technologies that now are playing such a transformative role. How many Facebook users do you think have re-posted the “UCC 1-308 and Rome Statute” nonsense? And how many of them, you reckon, actually know how Facebook uses their data? While much of what they do is proprietary, the Facebook graph algorithms are partly primitives9 and partly open. If you wanted, you could, with a modicum of mathematical and computing knowledge, have a good stab at understanding what is going on. On the other hand, posting bad legalese is easier. Much easier.

And thus, as a result, we have a degree of skepticism towards ‘algorithms’, mostly by people like Mr Haque who do not quite understand what they are talking about and are not actually referring to algorithms but their social use.

And there lieth the Technocratic Spectre. It has always been a fashionable argument against progress, good or ill, that it is some mysterious machination by a scientific-technical elite aimed at the common man’s detriment. There is now a new iteration of this philosophy, and it is quite surprising how the backwards, low-information edges of the far right reach hands to the far left’s paranoid and misinformed segment. At least the Know-Nothings of the right live in an honest admission of ignorance, eschewing the over-blown credentials and inflated egos of their left-wing brethren like Mr Haque. But in ignorance, they both are one another’s match.

The left-wing argument against technological progress is an odd one, for the IT business, especially the part heavy on research and innovation that comes up with algorithms and their applications, is a very diverse and rather liberal sphere. Nor does this argument square too well with the traditional liberal values of upholding civil liberties, first and foremost that of freedom of expression and conscience. Instead, the objective seems to be an ever more expansive campaign, conducted entirely outside parliamentary procedure (basing itself on regulating private services from the inside and a goodly amount of shaming people into doing their will through the kind of agitated campaigning that I have never had the displeasure to see in a democracy), of limiting the expression of ideas to a rather narrowly circumscribed set, with the pretense that some minority groups are marginalised and even endangered by wrongthink.10

Their own foray at algorithms has not fared well. One need only look at the misguided efforts of a certain Bay Area developer notorious for telling people to set themselves on fire. Her software, intended to block wrongthink on the weirder-than-weird cultural phenomenon of Gamergate by blocking Twitter users who have followed a small number of acknowledged wrongthinkers, expresses the flaws of this ideology beautifully. Not only is subtleness and a good technical understanding lacking. There is also a distinct shortage of good common sense and, most of all, an understanding of how to use algorithms. While terribly inefficient and horrendously badly written 11, the algorithm behind the GGAutoblocker is sound. It does what its creator intended it to do on a certain level: allow you to block everyone who is following controversial personalities. That this was done without an understanding of the social context (e.g. that this is a great way to block the uncommitted and those who wish to be as widely informed as possible, is of course the very point.

The problem is not with “geeks”.

The problem is when “geeks” decide to play social engineering. Whey they suddenly throw down their coding gear and decide they’re going to transform who talks with whom and how information is exchanged. The problem is exactly the opposite: it happens when geeks cease to be geeks.

It happens when Facebook experiments with users’ timelines without their consent. It happens when companies implement policies aimed at a really laudable goal (diversity and inclusion) that leads to statements by employees that should make any sane person shudder (You know who you are, Bay Area). It happens when Twitter decides they are going to experiment with their only asset. This is how it is rewarded.

The problem is not geeks seeing a technical solution to every socio-political issue.

The problem is a certain class of ‘geeks’ seeing a socio-political use to every tool.

# Sins of the algorithm

Why algorithms? Because algorithms are infinitely dangerous: because they are, as I noted above, within their area of applicability universally true and correct.

But they’re also resilient. An algorithm feels no shame. An algorithm feels no guilt. You can’t fire it. You can’t tell them to set themselves on fire or, as certain elements have done to me for a single statistical analysis, threaten to rape my wife and/or kill me. An algorithm cannot be guilted into ‘right-think’. And worst of all, algorithms cannot be convincingly presented as having an internal political bias. Quicksort is not Republican. R/B trees are not Democrats. Neural nets can’t decide to be homophobic.

And for people whose sole argumentation lies on the plane of politics, in particular grievance and identity politics, this is a devastating strike. Algorithms are the greased eels unable to be framed for the ideological sins that are used to attack and remove undesirables from political and social discourse. And to those who wish to govern this discourse by fear and intimidation, a bunch of code that steadfastly spits out results and to hell with threats is a scary prospect.

And so, if you cannot invalidate the code, you have to invalidate the maker. Algorithms perpetuate real equality by being by definition unable to exercise the same kind of bias humans do (not that they don’t have their own kind of bias, but the similarity ends with the word – if your algorithm has a racial or ethnic or gender bias, you’re using it wrong). Algorithms are meritocratic, being immune to nepotism and petty politicking. A credit scorer does not care about your social status the way Mr Jones at the bank might privilege the child of his golf partners over a young unmarried ethnic couple. Trading algorithms don’t care whether you’re a severely ill young man playing the markets from hospital.12 Without human intervention, algorithms have a purity and lack of bias that cannot easily be replicated once humans have touched the darn things.

And so, those whose stock in life is a thorough education in harnessing grievances for their own gain are going after “the geeks”.

Perhaps the most disgusting thing about Mr Haque’s tweet is the contraposition between “geeks” and “regular humans”, with the assumption that “regular humans” know all about algorithms and unlike the blindly algorithm-worshipping geeks, understand how ‘life is more complicated’ and algorithms are full of geeky biases.

For starters, this is hard to take seriously when in the same few tweets, Mr Haque displays a lack of understanding of algorithms that doesn’t befit an Oregon militia hick, never mind somebody who claims spurious credentials as a foremost thinker.

“Regular humans”, whatever they are that geeks aren’t (and really, I’m not one for geek supremacy, but if Mr Haque had spent five minutes among geeks, he’d know the difference is not what, and where, he thinks it is), don’t have some magical understanding of the shortcomings of algorithms. Heck, usually, they don’t have a regular understanding of algorithms, never mind magical. But it sure sounds good when you’re in the game of shaming some of the most productive members of society unless they contribute to the very problem you’re complaining about. For of course ‘geeks’ can atone for their ‘geekdom’ by becoming more of a ‘regular human’, by starting to engage in various ill-fated political forays that end with the problems that sent the blue bird into a dive on Friday.

Little of this is surprising, though. Anyone who has been paying attention could see the warning signs of a forced politicisation of technology, under the guise of making it more equal and diverse. In my experience, diverse teams perform better, yield better results, work a little faster, communicate better and make fewer big mistakes (albeit a little more small ones). In particular, gender-diverse and ethnically diverse teams are much more than the sum of their parts. This is almost universally recognised, and few businesses that have intentionally resisted creating diverse, agile teams have fared well in the long run.13 I’m a huge fan of diversity – because it lives up to a meritocratic ideal, one to which I am rather committed after I’ve had to work my way into tech through a pretty arduous journey.

Politicising a workplace, on the other hand, I am less fond of. Quite simply, it’s not our job. It’s not our job, because for what it’s worth, we’re just a bunch of geeks. There are things we’re better at. Building algorithms is one.

But they are now the enemy. And because they cannot be directly attacked, we’ll become targets. With the passion of a zealot, it will be taught that algorithms are not clever mathematical shortcuts but merely geeks’ prejudices expressed in maths.

And that’s a problem. If you look into the history of mathematics, most of it is peppered by people who held one kind of unsavoury view or another. Moore was a virulent racist. Pauli loved loose women. Half the 20th century mathematicians were communists at some point of their career. Haldane thought Stalin was a great man. And I could go on. But I don’t, because it does not matter. Because they took part in the only truly universal human experience: discovery.

But discovery has its enemies and malcontents. The attitude they display, evidenced by Haque’s tweet too, is ultimately eerily reminiscent of the letter that sounded the death knell on the venerable pre-WW II German mathematical tradition. Titled Kunst des Zitierens (The Art of Citing), it was written in 1934 by Ludwig Bieberbach, a vicious anti-Semite and generally unpleasant character, who was obsessed with the idea of a ‘German mathematics’, free of the Hilbertian internationalism, of what he saw as Jewish influence, of the liberalism of the German mathematical community in the inter-war years. He writes:

“Ein Volk, das eingesehen hat, wie fremde Herrschaftsgelüste an seinem Marke nagen, wie Volksfremde daran arbeiten, ihm fremde Art aufzuzwingen, muss Lehrer von einem ihm fremden Typus ablehnen.”

“A people that has recognised how foreign ambitions of power attack its brand, how aliens work on imposing foreign ways on it, has to reject teachers from a type alien to it.”

Algorithms, and the understanding of what they do, protect us from lunatics like Bieberbach. His ‘German mathematics’, suffused with racism and Aryan mysticism, was no less delusional than the idea that a cabal of geeks is imposing a ‘foreign way’ of algorithmically implementing their prejudices, as if geeks actually cared about that stuff.

Every age will produce its Lysenko and its Bieberbach, and every generation has its share of zealots that demand ideological adherence and measure the merit of code and mathematics based on the author’s politics.

Like on Lysenko and Bieberbach, history will have its judgment on them, too.

Head image credits: Max Slevogt, Xerxes at the Hellespont (Allegory on Sea Power). Bildermann 13, Oct. 5, 1916. With thanks to the President and Fellows of Harvard College.

References   [ + ]

 1 ↑ It is now more or less consensus that Deydras was mentally ill and made the whole story up. Whether he himself believed it or not is another question. 2 ↑ As an obedient servant to a kitten, I have trouble believing this! 3 ↑ Falcón y Tella, Maria J. (2014). Justice and law, 60. Brill Nijhoff, Leiden 4 ↑ Falcón y Tella, Maria J. and Falcón y Tella, Fernando (2006). Punishment and Culture: a right to punish? Nijhoff, Leiden. 5 ↑ Hyde, Walter W. (1916). The Prosecution and Punishment of Animals and Lifeless Things in the Middle Ages and Modern Times. 64 U.Pa.LRev. 696. 6 ↑ Albeit what we currently regard as the formal definition of an algorithm is largely informed by the work of Hilbert in the 1920s, Church’s lambda calculus and, eventually, the emergence of Turing machines. 7 ↑ I discourage the promise terminology here as I’ve seen it confuzzled with the asynchronous meaning of the word way too often 8 ↑ In case you’re interested, RFC1321 explains MD5’s internals in a lot of detail. 9 ↑ Building blocks commonly used that are well-known and well-documented 10 ↑ Needless to say, a multiple-times-over minority in IT, the only people who have marginalised and endangered me were these stalwart defenders of the right never to have to face a controversial opinion. 11 ↑ Especially for someone who declaims, with pride, her 15-year IT business experience… 12 ↑ It was a great distraction. 13 ↑ Not that any statement about this matter is not shut down by reference to ludicrous made-up words like ‘mansplaining’.