Wednesday, 13 July 2016

On Travel

Why do people travel? I was reading Karl Pilkington's two books titled 'An idiot Abroad', detailing his travels to the modern seven wonders of the world, and a few other 'must see before you die' places, and his reluctance to be impressed by what he sees. As is often the case with being presented with a contrarian perspective, it made me rethink my own views about travel.

I actually like Karl Pilkington immensely. I think he's your everyday regular happy guy (even if he doesn't look it) and leads a happy existence without any wants. He's happy with what he has, and therefore doesn't feel a yearning for something he doesn't want, like travelling the world to see the Great Wall of China or gorillas or whales or swim with sharks or to skydive. He's just happy to wake up in his own bed everyday, go to work, go to the pub for a pint and then go to bed.

To a Western observer, this would be perceived as narrow or small-mindedness. In the enlightened West, you can't appear to turn down an opportunity at international travel, the chance to expand your horizons, broaden your mind and learn from other cultures. You're supposed to put aside your city comforts and challenge your perceptions of life and society by immersing yourself in different cultures and experiences as this might give you a different perspective on your own life and make you a better more rounded human being [insert mandatory joke about Pilkington's head]. 

While I empathise with the open-mindedness of this narrative, I also see the danger of it turning into an overbearing patronising one, that turns the world-weary traveller into a self-entitled preacher who looks down at anyone not as well-travelled as himself/herself. "You haven't seen the Northern lights? You haven't spent a night in a treehouse in an Amazonian village? You haven't accidentally slept with a ladyboy in Bangkok? You're missing out on so much. You can't be as happy as I am. You're not as complete as I am."

I wonder if this narrative is something we need to recognise. This narrative that tells us that we aren't happy unless we do x,y,z. I don't buy into it. Sure, you can learn a lot from international travel, but how healthy is this action when it comes from a personal yearning brought about by comparing yourself to other people and their lives? At what point can you truly travel the world as an individual, and not because society tells you that you can't be a fulfilled individual until you do it. If backpacking the world is the same as following a trend, then how different is climbing Mount Kilimanjaro from buying a new smartphone?

What then are more righteous reasons to travel? Curiosity? Boredom? Excess time or money? I actually find these better reasons to travel, though some people today would frown upon anything that doesn't involve an immersive experience for purposes of enlightenment. You know who I mean. People who classify themselves as travellers rather than tourists.


It's interesting to look at these two forms of travel. The tourist route is more of a work hard, play hard phenomenon. We lead these stressful rat races that we tell ourselves is normal, and then go on vacation to 'de-clutter' or 'de-stress'. Is travel then our means to escaping stress, like pressure being released from a valve? Is it a by produt of living a certain type of existence? Well, not necessarily. You can live a relatively stress-free life w.r.t work and still want to travel occasionally. What would make you want to travel? Maybe it's still peer pressure, curiosity, a desire for more excitement in your life. Whatever the reason, it's an expectation that needs to be fulfilled, just like long term/immersive travel/backpacking, but with a different or missing snob factor. The difference between these two forms of travel has been presented in documentaries like 'A Map for Saturday'. 

Personally, I'm against being judgemental about any particular kind of phenomena. I find it more interesting to observe why a phenomena exists and how it came to be. Looking at the process, the mechanism, the underlying factors can tell us how society functions.

One aspect is money. I think anyone would travel if they had an excess of money. I think that people of means are merely doing what any one would with a shortage of time, given work constraints and an excess of money, i.e make the most of your vacation time. I understand why people do this. I don't completely understand why people backpack. If we are truly satisfied with our lives, we wouldn't want to change them. People who backpack i.e green travellers as opposed to grey travellers, could be curious about the world, afraid they're missing out, or maybe they're looking to find themselves, or a feeling of belonging. Which again comes down to expectations.

I suppose people are different in terms of what they want from life. Some people like Karl Pilkington are happy with what they have. Others just want more. Maybe our expectations are linked to our upbringing, circumstances and personality.


Looking at the exact opposite of this viewpoint, I am reminded of certain characters from the Alexander McCall Smith series I've been reading - 'The No.1 Ladies Detective Agency'. Set in Botswana, the lead character and her friends have no desire to leave home. That is where their happiness lies. They have a connection their their land and the lives connected to it, and even though they have problems, they are generally happy where they are.

You tend to see this a lot in certain societies. Again, I'm not saying that village or small town life is better than a life spent learning and travelling. It's not like village life in India is ideal, even accounting for only rich villages. Being tied to a place culturally can give you a strong sense of identity, but it can also lead to narrow-mindedness, suspicion, and in-group out-group mentality. I'm certainly not a fan of that. But to assume that the opposite of small town insularity is travel is ridiculous. You can spend your life under house arrest and still be a wise person. You probably won't have experienced as much as the international nomad, but you won't necessarily be the most insular person around, just as the nomad won't be the most broad-minded person around.

Maybe the best way forward is to not define yourself and your happiness in terms of other people's expectations. Easier said than done I imagine. You will always be influenced  by the decisions of others. Cultural evolution theories tell us that this makes our lives easier.


Interesting also is the media depiction of travel. Western society tends to depict travel from a highly individualistic point of view, in keeping with the self-actualisation narrative that they love. "You are special, if you are unhappy in your current situation, it's because you are misaligned with your place in the universe, and you need to find yourself and your place in the universe in order to be happy". 

You can see this in films like 'The Art of travel' where a high school grad decides to embark on a jungle adventure after his carefully laid plans go astray, helping him find himself in the process (or rather a new self he didn't know he had). Or in road trip films like 'Paper Towns',  where the protagonist realises that life is more than plans and chasing dreams and should be more 'live in the moment', or 'The Secret Life of Walter Mitty, where the protagonist experiences something he missed out on in his youth that now 'completes him' and 'makes him whole again'. I wasn't impressed by the Walter Mitty film. It was beautifully shot, and I get the appeal that a certain section of society have for it, and that some people who feel like they missed out on travel in their youth might identify with the main character. A lot of these films are films that I might have identified with 10 years ago, but not now. 

I'm not negatively criticising this narrative. In fact I don't have much to compare it to since I'm not aware of how other cultures represent travel in their media.


Thursday, 7 April 2016

On Art

A friend and I visited the Tate Modern on the weekend. The last time I was there, London was hosting the Olympic games. My visit then was brief, just a short walk around and a quick photo, like most first-time tourists in the city. This time we went specifically to see the Alexander Calder exhibit. The American sculptor worked mostly with wire, constructing familiar faces and figures and eventually more abstract forms. 


I don't often go to galleries and art exhibitions, which is peculiar given that one of the first things I do in a new city is see the museums and galleries. I suppose it's just something I do to tick things off of my list, to make sure I'm using my time well and not missing out on anything society deems it appropriate one experience in a new city i.e the typical tourist's attitude. 

I also think it's partly due to my minimalist approach to lifelong learning. I have a fixed set of interests, like learning, behaviour, psychology, data science, etc., and I tend to surround myself with stimuli that pique my interests in these areas. The fine arts, though beautiful, have never really inspired in me any thought or action whereby I improve in any of my interest areas and so to save time I minimise the time I spend on what isn't of obvious utility to me.

Perhaps this is a failing on my part. I suppose there are narratives in the arts that reflect on the sciences and philosophy that maybe enable us to interpret our interests from a newer richer more useful point of view. Maybe I just haven't discovered this yet. In all fairness, I do try to spend as much time as I can when I'm at a gallery actually trying to reflect on and interpret what I see in the context of my own interests. 

The problem is, and I have noticed this when I was at the National Portrait Gallery in both London and Edinburgh, is that there are no obvious stories being told or narratives being fed into by the pictures. Yes, there's a bunch of pretty pictures arranged chronologically or by artist on the walls, but after a while they all tend to blend together into a pastiche. I find that I'm not interested in something that holds no value for me because it doesn't seem to rearrange what I already know in a new way that inspires me to act or think differently. 

Perhaps art would make more sense if, like science, exhibitions focused on modelling the work of one or more artists in terms of specific narratives that make sense to the viewer, rather than treating the viewer to a boring history lesson. A case in point would be the recent Big Bang Data exhibition at Somerset House. I could tell the exhibit designers had a lot of valuable raw content to work with, and they chose to design exhibits in order to fit a number of narratives, though personally I found it a bit left-leaning. Nevertheless, it was interesting.


Which is why I was glad I visited the Alexander Calder exhibit. Unlike my previous underwhelming forays into the world of art, I was able to see not just art itself but expressions of love. Here was a man who truly let himself be inspired by assorted phenomena, many of which are of interest to me, and worked them into what was then a novel medium. This is way more interesting and relevant to me than the evolution of brushstrokes across canvas over the last 500 years in Europe. I'm fascinated by the thought process connoted by humans through physical expressions of things they are interested in, and three dimensional physical objects seem to appropriate this for me in a way that paint doesn't.

Among other things that struck me is how artists tend to come from families with other artists. I wonder if there's room here for an experimental study. If this is true, what moderates the phenomena of a artist emerging from a non-artistic family, apart from genes and interest in the arts? Is it familial support, money, independence, society, culture, stability?

Another thought I had was how frequently artists tend to be inspired by each other. Calder for example was inspired by Piet Mondrian. I'm sure there are other examples.

Calder seems like a guy who loved to play with objects, first wire to denote actual objects, and use them in performances, and later to denote static and then moving abstract images, some of them scientific in nature. I particularly liked this because I was able to draw parallels between Calder and Jan ┼ávankmajer, who worked with claymation and puppets to tell beautiful stories. 

The use of art to reflect scientific phenomena is a separate field in itself, there are so many examples of scientists, programmers, designers, artists and even landscape designers working on science-inspired projects, and these appeal to the geek in me.


We also saw the Performing for the Camera exhibit while we were there. Also very thought provoking, I can still remember that photo of Ai Weiwei breaking a two thousand year old vase, to protest government control. I get it. If your country is corrupt to you, then the objects it uses to symbolise it's apparent greatness mean nothing to you, and a great way to protest this is to destroy that object, similar to flag burning. 

I doubt that many people in a country like India would understand an act like that. Burning the Indian flag would be seen as tantamount to treason or sedition, on the basis that the ideals that the flag represents are indisputable, which is of course false. Nothing is beyond protest. And any attempt to push back and prevent any disagreement with the establishment will only concentrate the opposition. 

You see this happening consistently across history. The status quo is disrupted by an outside group, the two groups struggle until there's a new order which becomes the new establishment which is then challenged and so on. I think countries would benefit from taking the long view.of things, seeing as how everything that is happening now has happened before. A better understanding of power structures and leverage would actually serve to help reduce conflict times and speed up progress.


Wednesday, 23 March 2016

How to convince an atheist of God's existence

How do you convince a non-believer that God is real? Fight them on their terms. Atheists like rationality, experiments, data and hypothesis testing. So devise a study that has predictive validity. It's that simple. 

Make a specific verifiable prediction about the future whose outcome is not subject to vague or multiple interpretations apart from a religious one. A specific prediction that is so unlikely to occur except in the event of supernatural intervention. And if it were to occur then the only possible inference would be the supernatural. This is your hypothesis. Then devise an experiment to test this hypothesis, with controls.

For example, here's one hypothesis to prove that God is real and he answers prayers - over time t, a clear majority of n number of people suffering from a terminal illness who pray to be healed, will be healed from that illness. As a control, we can compare the results from this study to those from a group of n number of people with a terminal illness who do not pray to be healed. If the death rate is significantly lower in group A, then prayer works and God is real, if it is more or less the same in both groups then prayer has no effect and God is less likely to be real.

Also, the number of people who pray to be healed and die, or the number that don't pray to be healed and live should be so minuscule as to be negligible. In other words, for us to know that prayer works, the majority in both praying and non-praying groups should be true positives and true negatives respectively. And the number of false positives and false negatives should be tiny.

This is a good hypothesis because it separates a real effect from what would be chance or randomness but which might be confused for something else by believers.

One person being healed after prayer is not valid or reliable evidence in itself. It could be due to a number of factors, some of which could be as yet unexplained. A true effect would be visible over a group of people over time under similar conditions. And even if this happened, if a large number of people got better repeatedly after praying, you would still need to compare that effect to a similarly large group of people who got better repeatedly over the same time period without praying. By controlling for this one variable, you would ensure that prayer alone and not other confounding factors were at work.

No rationalist will every accept the results of a study as proof of course. You never 'prove' anything in science. You merely suggest that something is more or less likely. You goal here is to conduct an experiment that demonstrates that obtaining the results you obtained by chance alone would be so unlikely as to be as good as accepting that God exists (or perhaps an alien or the Matrix posing as God). This is as close that any scientist will come to believing in God.

I have yet to come across any data that shows that prayer works. All the evidence I am usually shown is no different from statistical noise (false positives or negatives) rather than true effects. But the experimental design is robust and I'm willing to change my beliefs and believe in God if that's what the model reflects. But we all know that's never going to happen.


Counter claims like God shouldn't be tested, God chooses not to be tested, God does what he will, you can't understand the mind of God, God has a larger plan, etc. to explain why prayer doesn't always work are all invalid and pointless as they don't support God's existence. They merely offer data that is no different from random chance or statistical noise (if not worse), making you question why you would choose to believe in God to begin with. If all the evidence for God is so inconsistent as to be no different from evidence for no God, then why hold to such a theory? 

And the argument that you're trying to measure something that isn't measurable or isn't supposed to be measurable is of course rubbish. That's the point of doing the measuring. If you can't measure an effect, then you have no reason to believe in it. And if you still believe in it, on what basis? 

Of course, a true believer doesn't trouble himself or herself with such trivial concepts like evidence. The best way to Know is to surrender yourself to the unknowable, to have the humility to know that you will never understand what you were never meant to understand, to take a leap into darkness, which is a good way to delude yourself into believing anything, true or false, and which also comprises logical fallacies like circular reasoning and false premise reasoning by first assuming something is true in order to believe in it. 

While this may bring comfort to people it is still the equivalent of a logical fallacy, and if something is the equivalent of a logical fallacy, it is as likely to be true as untrue. Which is why I default to not believing and people who prefer comfort default to believing. Two different frameworks for making sense of the world. Ironically, it's the scientific one that actually does more to prove the existence of the supernatural. Which is why we build verifiable models to make sense of the world. Religious models are just lazy. They explain too much by being deliberately vague. Great for self-delusional comfort, not a good way to derive insight.


Sunday, 28 February 2016

One ball at a time

I recently read Andrew Flintoff's biography - Second Innings: My Sporting Life - and was quite taken with his descriptions of the ups and downs in his playing performance over the years. Yes, there was alcohol, intrinsically linked to it all, but there was also his own psychological state, choppy and uneven. Reading about his mind made me contrast his mental make-up with those of players in the Australian team, who seem more naturally aggressive in the most nonchalant way, almost childlike in the way they approach life. 

I don't know much about sports psychology, but It seems to me that you're at your best when you're simply playing and not thinking too much about playing. Flintoff was at his best when he was on a mood high, happy with his place in the world, playing without care, visualising himself as a giant, fearless, untouchable and taking it one ball at a time. I think it's an attitude thing. It might be better for your performance to stop thinking about your performance, and just live in the moment, one ball at a time. 

Perhaps that's why the Australians are so good at cricket. That and trust. you've got to have good camaraderie with your team mates, coach and management to put you in a good mood and clear your mind. But other that that, there's an element of not caring about the outcome of a match that I think helps. Because really, you have no control over much, less so the outcome of a sports match, and the sooner you accept that, the better off you will be. Because then no matter how good or bad the match outcome, you see no reason to blame yourself, to doubt yourself. You did your best, everything else was out of your control, better luck next time.

And I suppose the ability to see things in the larger perspective helps - it's just a match, there are people on this planet with real problems and bigger issues, you're just swinging a bat or throwing a ball. Just do the best you can do at that moment and let everything else sort itself out. If you really suck, they'll replace you with someone else. That's their problem, not yours.

I wonder if extending this attitude to business helps. Maybe the most successful business professionals are those who don't act one way or another but simply live out their natural mental states at work. Focus on the job at hand, let everything else sort itself. Whether the organisation lives or dies is not your immediate concern. Leave that to someone else. Do a good job. Be the best you can be. How your work fits into the larger scheme of things is a useful way to think if it's part of your job, if it will help you get better at what you do,  but if it's only going to fill you with self doubt and stress, then what's the point? I guess that works if you're a specialist and not the owner of a company, because then you're going to need a slightly different attitude to your work. Or maybe not. Perhaps even owners just need to tackle one challenge at a time.


Sunday, 7 February 2016

On Hiking Differences

The biggest difference between hiking in the UK and South/West India is the investment in equipment. 

In Mumbai, and I suppose Pune, Chennai, Bangalore or anywhere in South India, you can afford to be a minimalist when you hike i.e you don't need a lot of stuff. All I used to wear on a day trip from Mumbai was a t-shirt, non-denim trousers, sneakers and a light raincoat. I'd swap the trousers for shorts if it was a shorter hike, involved a beach, flat open ground, or involved wading through water. I'd stick with trousers if it involved forests, shrubbery, thorns and mosquitoes. The fact that most of my hikes took place in the monsoons didn't matter. It was still humid enough to warrant the bare essentials. I did carry a wool pullover on overnight trips just in case it got cold. It was the only time I ever used the pullover normally stashed away in the back of my wardrobe in Mumbai. 

I usually carried a light raincoat. Not among the most durable of apparel, it did its job, which was to keep the bulk of the rain off my body and cotton clothing till the end of my hike. I know guys who hiked shirtless. In a humid monsoon hike, maybe polyester shorts and shoes are all you need. I wore a simple hat to keep the sun out of my eyes and the rain off my glasses. Most people didn't. They found it too hot, irritating or distracting. 

My shoes were initially everyday sneakers. Yeah they weren't the best for rough hiking, but they were great for most of my hikes that involved flat trails. I switched to Woodlands, which helped with longevity. Again, not a priority for casual hikers who stick to flip-flops or sandals. I never considered wearing gaiters. No idea if you can even buy them in India. We just considered water in our shoes a normal unavoidable thing. Gaiters can help keep your shoes dry to an extent, but not when you're shin deep in a flowing river. My socks were normal cotton ones. I never needed insulating ones. There was no cold to protect against. In hindsight I think wearing thick or double pairs of cotton socks would have meant less damage to my toes. 

Contrast this with the UK, where people usually wear professional branded light stretchable hiking trousers that wick rain away. And waterproof overalls over wear over your trousers in heavy rain. And hiking trousers with thick lining on the inside in case it's a winter hike. Or perhaps just thermal on the inside. Or maybe lycra running pants. As long as you have a base layer. The more expensive the better the quality. Depending on your budget, you can buy anything from £5 thermals that are 50% synthetic, to £25 thermals that are 100% synthetic. And professional hiking T-shirts that wick sweat away. Short sleeves in summer and long sleeves in winter. With probably a base layer underneath in winter. With a mid layer and jacket on top. The weather dictates what you wear.

You always carry a rain jacket, preferably one made of weather-proof Gore-Tex for toughness. Or one that's simply weather resistant. Cheaper, but shorter-lasting. You could wear a mid layer like a fleece jumper if it's colder. A medium or heavy fleece in cold weather, or a medium fleece with a jacket if it's snowing/raining. A micro-fleece in autumn, or a jacket on top if it's snowing/raining. Or just a jacket with fleece lining on the inside to combine the best of both worlds, unless it gets warm and you'll have to either keep it on a sweat, or take it off and freeze. This is why layers are useful. Thermal monkey caps or hats that protect your ears against the cold and wind are common. And so are wide brimmed hats that protect against the sun. And hiking sticks to keep your balance and take the pressure off your knees on downhill climbs.

And then there's the shoes. You get weather-resistant hiking shoes (Gore-tex again). And professional thick hiking socks. I usually buy my shoes one or two sizes too large and then wear a couple of thick hiking socks to protect my toes and keep my toenails. The cushioning helps. If you don't hike often, you can always reuse your running or gym equipment. I've seen a lot of people show up for hikes in tights, running/sports jackets and running shoes. I suppose this is OK for day hikes on easy ground. Running/sports clothing tends to be fragile as it's made for quiet straightforward runs along city streets that only involve sweat, cold and light rain. On a challenging hiking trail involving thorns, rocks, stretching, mud, sleet and hours of continuous use, they'd fall apart.

And then there's the brands. In India, we mostly wore what we had lying around. My total annual clothing budget for hikes was zero. In the UK, my hiking trousers are from Craghoppers, my fleece from Pierre Cardin, my jackets from many assorted places, my hat and gaiters from Karrimor, my shoes from Crivit, my socks from Gelert. It will get worse if I do winter hikes. Other common brands are Merrell, Patagonia, Berghaus, Rab, The North Face, Regatta, Marmot, Paramo and Hi-tec. And then there's the walking poles, head torches and energy bars. You could spend hundreds of pounds a year on equipment.


Sunday, 3 January 2016

On Null Hypothesis Significance Testing, P values and the Scientific Method

Hypothesis Testing 

Hypothesis testing is essential in science to determine the presence of an effect. A technique commonly used is NHST, which tests if the data points in your alternative distribution are representative of the normal distribution i.e if your data distribution is different from what would be considered 'normal', and assigning a p value to your data. If the Mean in your data sample is different from the one in the normal distribution, this might tell you that your data is not simply a random sample but that an effect (your variable) is present.

We conduct Hypothesis Testing by comparing our alternative hypothesis against a null hypothesis. You either reject or fail to reject the null hypothesis (double negatives can be used in statistics - not implausible, failed to reject, etc.).

Failing to reject the null hypothesis - This does not mean that the null hypothesis is true, only that this sample does not show that the alternative is true. Not rejecting a position like the null hypothesis does not mean that we're saying it is correct.

Rejecting the null hypothesis - This does not mean that the null hypothesis is false/not true. Neither does it mean that the alternative is true. It just means that this sample shows that the data is different from the null. Another sample might not. 

These two points above are important to understand because when we look for effects in data, particularly noisy data which might be influenced by a lot of factors, you cannot simply reduce the act of spotting an effect to rejecting or failing to reject a null hypothesis. This is because the null hypothesis is almost always false. 

When you sample from a population, it will be a coincidence indeed if you get the exact same means in both your experimental and control samples. I think the more important question to ask is how much of an effect is present and under what conditions will it vary. Statistics is no substitute for thinking. You need to decide what an important effect is. 

Other points to remember - 

- If you have a research question, circle around the problem, address it in different ways. Don't frame it in one specific manner and pin your conclusions on a null hypothesis to be tested.

- Hypothesis testing does not have to be applied to all questions. You can have one-off events worth studying that do not need falsification.

- It's OK to conceive your hypothesis after you have conducted research but it should be before you have analysed data statistically (more on this later).

- Hypothesis tests are always about population parameters, never about sample statistics. We always use the sample data to hypothesise about the population mean, not the sample mean.

- Hypothesis testing and significance testing are different things. Hypothesis testing or Null Hypothesis testing is about  rejecting or failing to reject a null hypothesis, Significance testing is about assigning a p value. We commonly use these two together in a hybrid called NHST, which is controversial.

Null Hypothesis Significance Testing (NHST) and P values

In order to conduct a hypothesis test, we usually assign a significance value, a threshold on which we decide whether to reject or fail to reject the null hypothesis. This is how the NHST methodology works, but it has drawbacks, like a dependance on the p value. A p value is supposed to quantify the strength of evidence against the null value. It tells you how unusual the occurrence would be if it was due to chance.

The p value is the probability of observing a sample statistic like the mean being at least as extreme/favourable as it is in this sample, given our assumptions of the population mean.

p value = P(sample mean being as extreme | assumption about population mean)

It is simply the probability distribution on a normal normalised distribution like a Z score table (you can find it using the pnorm function in R). For example if you test two groups of people and group A gets 5 and group B gets 7 and you want to see if their scores are significantly different from each other, you subtract the differences and get 2 and then decide if this is significantly different from your null value, whatever it is (probably 0), given a certain standard error (Remember that all statistics is essentially a test statistic divided by the error in that statistic). 

One way to do this is to be so immersed in your subject matter, be a complete expert at it and have full subjective contextual knowledge that you know subjectively if a difference of 2 really matters, if it really translates to real world significance. Remember that real world and statistical significance are two different things. 

In statistical significance, you would run your test statistic against a normalised distribution, assuming it follows one, and your data might just be deemed significant if you get a low p value. The low p value is supposed to tell you that the probability of getting this difference of 2 is low i.e on the lower end of one end of the normal distribution, given a null default. 

There are a few drawbacks to using p values as indications of significance. This paper shows us the harmful effects of using NHST and confusing statistical significance with real life significance but I've included my own notes below.

Significance testing tells you more about the quality of your study (variation and sample size) than about your effect size which is more important. Andy Field has written a very easy-to-follow chapter on this topic.

- As I said before, p values are the probability of observing what you observed given a null default, but the default is never null. The null hypothesis might always be false since two groups rarely have the same mean. How then do you make sense of how probable your data is?

- The p value is conditional on the null hypothesis. It is not a statement about underlying reality. Even if it is accurate, the p value is a statement about data when the null is true, it cannot be a statement about data when the null is false.

- A p value is not the probability of the null hypothesis being true or false. The p value is the probability of extreme data conditional on a null hypothesis. 

- It is not the probability of a hypothesis conditional on the data. P values tell us about our data based on assumptions of no effect, but we want a statement of hypotheses based on our data. To infer latter from a p value is to commit the logical fallacy of inverting conditionals. 

- P values do not tell you if the result you obtained was due to chance, they tell you if the result was consistent with being due to chance.

- p values do not tell you the probability of false positives. The sig level (not the p value) is the probability of the type I error rate i.e P(Type 1 error) or P(reject | H0 is true).

- This paper does a good job of expanding on my points above, listing a lot of the common misconceptions about p values and NHST. Highly recommended.

If you're studying a non-stable process that spits out random values, p values are not meaningful b/c they are path dependent. In these cases, the p value isn't meaningful b/c it is a summary of data that has not happened, under assumptions that further data will follow a certain distribution. 

- People use 0.05 as a significance level, but need to remember that hypothesis tests are designed to call a set of data sig. 5% of the time, even when the null is true.

- Many studies show that you have a a very good chance of getting a significant result that isn't really significant with a significance level of 0.05 (about 30% of the time). This paper in particular does a good job of explaining the high false discovery rate using a significance level of 0.05 and compares it to the screening problem, and this article summarises the points well. You can use a lower level like 0.001, but it really is up to you to decide what is statistically significant. 

The Scientific Method

All of this tells me that it is best, when tackling a solution to go back to the philosophical foundations of why we do things. 

Note that you only create a theory or hypothesis after you have evidence. Theories have to be based on evidence, preferably good data-driven evidence. You can't first make up a theory and then look for evidence to confirm or falsify your theory. This is how superstitions and pseudoscience are created. A deliberately vague theory will never be confirmed or falsified, only made to look unlikely. While quantifying how likely or unlikely the existence of an effect is, is the point of science, doing so is a waste of everyone's time if the effect was made up to begin with, so don't do this.

If you see something weird you can't explain, you don't automatically give it a name. That's merely classifying a phenomena, putting it in a box that represents what you already know of the universe, which is incomplete. And your classification system or model or framework could be wrong. You need to do more. It is best to sit on the fence, admit your ignorance, and keep exploring, digging and asking questions of your phenomena, all the while building better and better models to explain it and make predictions. This is preferable to classifying your phenomena in terms of some-pre existing narrative that fits your own socio-cultural context, which would be a failure of critical reasoning.

I see this all the time. Once people identify with a narrative, everything they see will serve to strengthen that narrative. Supporters of a political party do not support that party because the evidence led them to support that party, they do so because of other reasons, like values that they identify with. But once the decision is made, evidence doesn't matter. We are slaves to narratives. Everything that follows is confirmation bias.

We use models because of their usefulness, not because they are correct. It seems to me that the best way to tackle a scientific question or puzzle is to first do exploratory research, just lots of multiple comparisons, or A-B testing, and obviously we wouldn't use p values here. We look at our exploratory data, at possible trends we see and that might or might not be true, that might reflect some underlying connections, and then create hypotheses based on what we've found in the data. 

Here is where we switch from exploratory to confirmatory research. To confirm or falsify our hypotheses, we need to run experiments, which can involve hypothesis testing. And we have to gather new data for this. We cannot use the same data set for both exploratory and confirmatory research as that would be cheating ourselves and would not be scientific. 

We pre-register our experiments so we can't change our minds later and claim we were always looking for what we ended up finding. This is called the garden of forking paths or researcher degrees of freedom or p hacking - You can only test 1 hypothesis, not 20 and then report only 1. Or drop one condition so you get a sig. p value of < .05. 

There are really millions of variables that can correlate significantly with each other. Which is why we get significant correlations when we generate hundreds of 10 number strings of random numbers and then compare two strings. When you compare enough variables, you will find significant results. This is noise. This is just how large data works, or data without theory, or data with a theory that is ad hoc or made up and not evidence based. This is how superstition works. You need to look beyond this, to see if any of these correlations or effects are consistent and not merely noise.

So we conduct our confirmatory research, get our results, and then replicate to see if the results hold. Replication ensures that we confirm that the effect is real and wasn't just a coincidence. Also, keep in mind that if your hypothesis was based on a solid non-noisy phenomena or theory that that you had good reason to believe existed or was true, then replication should merely help ascertain this one way or another and not be a threat to you. It should all be part of the process of good science. If your effect was made up to begin with, or was noisy, then no amount of replication is going to help falsify something that never should have been investigated in the first place. in this sense, the original experiment  bears no special status over and above the replication. They both need to be treated the same.


This then is 3 different experiments that we have conducted to find one effect. And where do p values come in? I think you can use them for confirmatory research, but only to tell you about your sample data distribution, about the probability that the data is consistent with chance, under repeated attempts. But you cannot use p values to tell you about your hypotheses. From what we've seen, p values cannot do that. They were not set up for that purpose and they don't work that way. You should be able to tell what a truly significant result is in your study without p values, or by looking at other statistics. Or maybe using Bayesian statistics.


On Happiness

I've been thinking about happiness recently, which is probably something that someone who is truly happy wouldn't do. Happy people don't think about or look for happiness. They merely live out their happy lives as normal. But over-thinking things is part of who I am, and it brings me an extreme sense of satisfaction, which I suppose is different to happiness but still important.

I meet a lot of expats in London. International working professionals here on a contract. They all come here for a change, to lead a better life, to make more money, to travel and see new places, or other reasons that they claim brings happiness. And I wonder how many of them are happy. Whether this is a useful question to ask is something I'll get to later. But lets say it is. Lets say happiness is important. Do people who move here for work end up happier than they were in their own countries? I'm not sure. A lot of them feel like they're merely chasing happiness, like they're still searching for something that they'll never find, or that they've only found temporarily until another happiness goal catches their fancy. I'm not sure.

There's this TED talk that says that happiness is the mostly the quality of our relationships with other people, and I'm inclined to agree with this from the point of view of my own personal context. I personally derive a lot of happiness from good close personal relationships and shared experiences with family and friends, though I also think that other factors help - like having low expectations about certain things, having a pragmatic view about bad things that happen to you, having a positive attitude towards everything, and not tying your ambitions and career goals to happiness. Work for money, create for love, right?

This other talk separates happiness into synthetic and real. Synthetic happiness comes from doing what you are told will bring you happiness, accepting things you cannot change, and rationalising bad things as normal and happy. Also, people like things more when they think they're going to lose them. It defines real happiness as when we get whatever we want, which is something I don't get because we never get what we want and will constantly be striving from one happiness goal to another i.e one temporary island of happiness to another temporary island of happiness. It could just be semantics, but this isn't real happiness to me, this is just temporary contentment. But I guess this is happiness to a lot of people in the western world, who feel like they need to be in control of every aspect of their lives, and that control brings happiness. I take the other view, which is that since so much is out of your control, you can only be happy by letting go of it all and just do things you enjoy without hurting people, and take everything else in your stride without imagining that the universe is conspiring against you. Which is where the synthetic happiness come in. 

Then there's 'The Geography of Bliss' by Eric Weiner. A somewhat humorous look at why people in some countries are generally happier than others. Some of Weiner's book is of course typical western narrative tropes and hyperbole - Columbus, China's greed is bad, etc., but i picked up a lot of interesting points. Weiner visits the happiest countries on Earth  to find out what makes them happy, while not confusing correlation/association with causation. Just because happy nations are characterised by certain factors doesn't mean these are causal factors, it could be the other way around. 

The happy countries - 

- The Dutch have things taken care of, and have permissive attitudes towards sex, drugs, etc.

- The Swiss are less tolerant than the Dutch, they have rules, boredom and nature. They are not ecstatic joyful, but content. They also have cleanliness, punctuality, things taken care of, they don't provoke envy in others, but suppress envy by hiding their wealth. They are surrounded by beauty and nature. They trust their neighbours, and having a sense of history and where they're from. They have fewer choices.

- The Bhutanese don't have unrealistic expectations. They don't try to be happy or try to achieve it. They don't talk about or analyse it. They don't ask themselves if they will cease to be so. Ignorance is bliss. There is also a lot of death, which gives you a different perspective on life. You develop a new way of seeing things after living with it. They are poor, but that doesn't matter. Money is only a means to an end. It is trust in people and institutions. Material wealth doesn't become so important.

- The Qataris leave everything to God. Maybe happiness come from beliefs, not necessarily religious beliefs. They belong to one tribe with many rules, that allows you to have no rules outside it because you just won a lottery and can do anything with the money. You are happy as long as you are a high ranking member of this tribe. You don't need ambition or high expectations. The money takes care of everything. If this culture-less life is to your liking, you are happy. But money isn't everything - it has diminsihing returns. You will always crave somethign else.

- The Icelanders are naive. They are free to try and to fail. They have a conection to their language. They are a small country, feel kinship to each other, protective of their well-being. Enjoy writing. Not affected by SAD. Have multiple identities, no envy of others. Suppress envy by sharing everything with others. A sense of self actualisation and the freedom to do what you want. they are free to share ideas without copyright. Self-delusion might be good - there's no one to tell you not to do somethign or express yourself. They constantly fail and create rubbish, but are happy doing so.

- The Thais have mai pen lai (never mind), jai yen (let it go), sanuk (fun). They have fun at work instead of the American work hard, play hard mentality. Their fun is interspersed throughout the day rather than regimented and taken too seriously. They don't take things too seriously. They don't think about things like happiness to much. Ignorance is bliss? They smile a lot.

The unhappy countries - 

- The Moldovans have a lot of envy, are relatively poor compared to their European neighbours - poverty breeds envy of other's riches - there's also lack of trust - if something goes wrong, it is not their responsibility to fix. There's a feeling of powerlessness, helplessness.

The somewhat happy countries - 

- The British believe in muddling through, getting by. They are reserved, not tactless, are afraid of offending people, don't hug, are a country of grumps. Does culture impede happiness? I don't think it's that simple. Having lived in England and Scotland, I think people here are definitely happy, they just don't show it (btw, don't ever introduce yourself right away in an English pub - rookie mistake). But I'm not sure why they would rank lower than the other countries. 

- The Indians are a mixed lot. The ones who are happy believe that life in an act, and don't take it too seriously. New tech cities are both the problem and the solution. People have long long work hours, poor work life balance, and then special workshops and ashrams to fix them. Calcutta's poorer are happier than America's poor - stronger family ties? (Btw, flattery can get you an interview in India, and much else). He says nothing about unhappy people in India. I guess it could be a lack on trust in your neighbour and public institutions. All the happiest people I know in India derive happiness from relationships in their communities, but not necessarily within communities. Indian diversity can be comforting, but I think people's biases and ingroup-outgroup mentality combined with their narrow-mindedness about culture can serve to increase create distrust and hate.

- The Americans are constantly searching for happiness. Their unhappiness could come from unrealistic expectations. Self help books teach them to look inwards not outwards towards relationships that really matter. Maybe you nee to commit to a place or people to be happy, you can't always have one foot out the door.

What happiness isn't - 

To quote the book, "Happiness is not feeling like you need to be somewhere else or doing something else." But I think that's your other goals, which are fleeting and constantly changing. I think it's fine to have them, we all have career and self-fulfilment goals and wants, and striving to accomplish them is fine, but our success or failure in said exercise shouldn't make a difference to our happiness, if in fact happiness is more important. 

It's not about ambition or success. Failure might happen despite your best laid plans, and while success can bring you satisfaction, I feel it's the journey, the striving for success that brings you happiness.

Knowledge doesn't necessarily make you happier, though it has other obvious advantages. So is ignorance bliss? Not necessarily, in my opinion. It's not about knowledge vs ignorance w.r.t happiness. Neither is a factor, your happiness depends on other things.

It isn't about money or material wealth. Money helps, but just a little, it doesn't guarantee lasting happiness. Law of diminishing returns.

What happiness is -  

We constantly try to synthesise happiness, we think it is something to be found. Perhaps it is more a thing to be created, or a state to be evolved into. To my understanding, it is having close personal healthy relationships with friends and family, living in a society with a lot of trust, and no envy, uncertainty or fear, and finally, having a pragmatic outlook on life, understanding that events are unpredictable, but having something to look forward to and doing your best anyway, about having a sense of not-wanting. Living among a homogenous society with reliable public institutions and like-minded people also helps. The closer knit the community the happier you are, as long as you subscribe to the cultural mores of that community. Tough luck if you don't. Perhaps that's why people move away. To me, certain environmental conditions also matter, like living in clean cool quiet surroundings with access to good food and being intellectually stimulated.


Monday, 21 December 2015

The Science of Everyday Thinking on EdX

I had the pleasure of completing 'The Science of Everyday Thinking' on EdX recently. The course deals with a lot of stuff i've been thinking about for the past few years, so I noted a lot of my thoughts.


The course begins by stressing that it is really difficult to put yourself in the shoes of others. We over estimate the abilities of others to know what we know. An example of this is when we tap out a song on a table. We expect 25% of people to guess the song correctly but in reality only 2.5% do.

We're great at pattern recognition, maybe even too good at it. Things float to the top of our minds that match our expectations, so we see real effects in noisy data, for example -  a face on toast. We sharpen things to what we expect to see - the 'expectancy effect' - and level those that we don't.

The course also stresses on how faulty memory can be. Memory is not like a video camera. Every time we remember something we reconstruct past events in our mind. I have had personal experience with this when helping one of my classmates at uni with false memory experiments. It was interesting to see how people really believed that they had seen something when they hadn't. I do this to, which is why I now write down certain events immediately after they happen so I don't get sequences of events mixed up.

We exhibit Naive Realism - we think the world is as we perceive it to be. This is wrong.

We exhibit fundamental cognitive error - we tend to underestimate the contribution of our beliefs and theories to observation and judgement, and fail to realise how many other ways that they could have been interpreted. 

Know Yourself

Planning fallacy - we are terrible at planning or judgement-making or self-assessment. Examples are driving, attractiveness & morals. Even though we fall on a bell curve for some of these, and 50% of the population falls below the median, we are incapable of accepting that we could be in the bottom half. Statistically speaking we all have to be under 50% at some point, but we will never admit it.

I've seen this first hand when planning my own goals. Many a time, I've planned out a journey assuming I'd be ready by a certain time only to find I've taken longer to get ready. I overestimate my own ability to be ready in time. It's the same with my learning goals. I keep subscribing to the belief that I am a super-fast learner and can do multiple courses at once, and I always end up struggling with too many things on my plate. I've learned to cut back and take things slower. No one can be great at everything. I've also seen this when proof-reading for foreign students au University. Students would be incredulous at the number of mistakes I found in their writing and the amount of re-writing that was required. They thought their grammar was decent, when it wasn't. Their unrealistic expectations were tied to incorrect evaluations of their own abilities.

The false-consensus effect - we overestimate the extent to which our beliefs are typical of those of others. We believe that other people generally think like us. Important to be reminded that this is not the case.

People don't even know what makes them happy. The true reasons people are happy are usually different from the reasons they provide. I need to do a separate post of happiness as I'm currently researching this. 

Job interviews are usually bad because of confirmation bias - interviewers see what they expect to see. They make up their mind about a candidate soon after they meet them and then only ask questions that confirm their beliefs. Structured interviews, where every candidate is asked the same question, are better. 

People tend to exaggerate the long term emotion effects that events have on us. In reality, emotional trauma can have bad effects on us but for the most part we tend to over-emphasise their effects.

People have a strong 'order effect' when selecting from an identical pool - they mostly pick what's on the right. And then they don't believe the reason why -  which shows that we don't know ourselves well. We don't even know why we make certain choices.

Intuition and Rationality

Kahneman differentiates between System 1 and system 2 thinking i.e intuition and rational thought.

The Anchoring Effect is powerful - but be careful of noise in the data.

The Representativeness Heuristic - the frequency or likelihood of an event by the extent to which it resembles the typical case.

But from a practical point of view, do be careful of thinking too statistically - in the Rudy the farmer  example, where there are far more farmers than lawyers, statistically it would make sense to pick farmer as the option but a bit more context would propbably point towards one of the other options like lawyer.


I really enjoyed this part of the course as I could take away more from this part than any other. Keys to learning better are to - 

Distribute practice over time - spacing helps. 
Set calendar reminders.
Use Retrieval practice - instead of merely re-reading material, cover and try to recall it.
Learn by doing - practice and discuss the content.
Vary the settings in which learning takes place.
Relate learning to your everyday experiences.

An important thing to remember is to not mistake fluency with learning. If you're finding a new topic too easy, you're probably not learning it well enough. You only think you understand it.


Beware the Gamblers Fallacy.

Apple's shuffle feature - people don't understand how randomisation works, Apple had to make their product less random so people would perceive it as being more random even though it wasn't.

Finding Things Out

Many phenomena are simply examples of Regression towards the Mean - things balance out. This is more apparent when there is more noise in measurement.

Also, Post hoc ergo propter hoc - we assume a causes b because b followed a. It's kind of like those other common biases that make us believe in superstitions, like correlation is not causation, or false premise reasoning, or circular reasoning.

Experiments show that for most competencies, there is no diff between large and small class sizes.

Six leads to opinion change -

What do you really believe anyway?
How well based is your belief?
How good is the evidence?
Does the evidence really contradict what you believe?
What would be enough to change your mind?
Is it worth finding out about?

Extraordinary Claims

There are multiple ways you can interpret things.

Question your intuitions and be willing to give them up.

People tend to accept information that is consistent with their pre-existing beliefs at face value, but critically scrutinise information that contradicts their beliefs.
Health Claims

Pseudo-scientists tend to make ambiguous statements that you can contort to your expectations.

The Placebo Effect can be a false positive response, but most are Regression to the Mean. People seek help when they are sickest.

The Availability Heuristic - if a treatment turned out negative, you would never hear about it. 

Like cures like - a diluted part of the disease can cure the disease - is a common false belief. 

Natural is not necessarily better - arsenic is not good for you, indoor plumbing is.

Clustered disease is possibly the availability heuristic. You're confusing normal randomness and noise for an actual effect. You need to create and test a hypothesis to determine if a true effect like cancer clusters exist in a population.

Always ask - what about the other 3 cells? Given that you can have true positives, true negatives, false positives and false negatives, always look at the costs and benefits of the two ways that you can be wrong.

Applied Claims

For example - facilitated communication, forensic science, conspiracy theories, gun laws, gay marriage, asylum seekers.

The Expectancy Effect affects interpretation of forensic evidence like DNA. Experts who expect or desire to see something see the evidence in ways that are consistent with what they want to see - this is in part helpful, but can be disastrous.

People tend to focus exclusively on what they consider to be the evidence.

Belief in conspiracy theories is mostly cherry picking information.

False consensus effect - everyone thinks that everyone agrees with them.

Exploiting the Situation

There is not much correlation between personality and cheating, it is more about the situation. Certain situations can encourage honesty. 

Social conformity, the bystander effect, attribution error.

We assume that the way we see the World is the only way to see the world and anyone else that sees it differently is wrong and we attribute it to their  education, personal biases, propaganda, lower intelligence.

Milgram experiment - authority factor, diffusion of responsibility factor, channel factor (increase in shocks in incremental steps), no clear exit.

Nudging changes the channel factors to induce behavioural change.

Putting it all together

Be aware of your intuitions.
Have a healthy skepticism.
Simulate your future desirable performance in the present.
Test hypotheses.
Pick a few areas where you want to change what you're doing w.r.t thinking and personal biases, and focus on those.
Just because something is portrayed confidently doesn't mean it's true.


I really enjoyed the course. I initially felt that the instructors spent way too much time on discussing personal biases and our inability to be objective and accurate with our perceptions and beliefs, and that they were repeating these points through the first half of the course, but I see now how useful and essential this was. Indeed, only good can come from these constant reminders.

Throughout the course, I was reminded of the biases people use to justify their superstitions and irrational beliefs, and why they won't change their minds even after being presented with evidence. For some reason or another, people will believe what they want to believe, and then pick and choose evidence to confirm that belief. They will see patterns where there are none because that is what they would expect of that belief. It helps if the belief is vague to begin with. This makes it easier to confuse noise for a true effect. They will assume that everyone should think this way. They will not understand that everything they see and interpret this way can be interpreted in many different ways by different people. They will not accept that their beliefs are a result of critical reasoning flaws or cognitive biases, nor be willing to test and verify their beliefs experimentally.