Comment by s_q_b | Hacker News Reader

Comment by s_q_b | Hacker News Reader

Parent Full thread

"What is worse, Goldstein and I found that a high number of data scientists (many with PhDs) also get confused in real life."

Wow. Just wow.

Some of people are calling themselves "Data Scientists" who don't know the difference between σ and MAD?

I don't care how many letters are after your name. If you don't know the absolute most basic types of summary statistics, you have no business calling yourself a Data Scientist.

---

To the phonies, please stop. Most of us work hard to stay at the bleeding edge, lest we fall behind, as I'm sure all HN devs strive to do. You're essentially defrauding people, and if you're working on anything important, the cascading effects can hurt a lot of real live actual human beings.

It's one thing to play around with data science to satiate your curiosity. It's an entirely different matter to declare it your profession. For example, I play around with KSP. That does not make me an Aerospace Engineer.

---

Edit in reply @tgb: Actually I think you and I are on the same page about what Taleb means. In fact, MAD is probably the more intuitive summary statistic for most people.

I just find the number amongst Data Scientists surprisingly high, since half the job is spotting these kinds of misinterpretations.

I don't know what Taleb is referring to, but I assumed it was something related to this line:

>In fact, whenever people make decisions after being supplied with the standard deviation number, they act as if it were the expected mean deviation.

That is, I suspect he means that if you gave them equations or data and asked them to run some computations on them, they wouldn't mess up the two. But if you were to then say, "okay, what does this result tell you to do when you're buying groceries at the super market?" they would then make that decision incorrectly.

This isn't to dismiss the problem. Just I don't think he's saying it's quite what you think he's saying. Too bad Taleb didn't write more on either of these two lines. (Well, chances are he did, but I just don't know where.)

Even worse there are people (utter frauds of course) who confuse MAD and MAD! In all seriousness, there is much confusion between Median Absolute Deviation and Mean Absolute Deviation out there. Ironically the MAD in this article is still not a robust measure of variation in data as it will break for the many distributions that have undefined/infinite mean (Cauchy and Levy as examples).

Even then many summary statistics rely on a well-defined PDF which is also not true for many real life cases. I think most data scientists out there are very familiar with quantiles, which are often more useful as all random variables have a CDF (and the quantile is just the inverse CDF).

I quite enjoy Taleb's writing (I tend to find his ego a bit amusing) but I think even he is guilty of Jaynes' "Mind Projection Fallacy"[0] in regards searching for more meaning than exists in Fat-tailed distributions. When we model our data with infinite/undefined mean and variance distributions we're just saying "I don't know". No amount of cleverness with summary statistics, or understanding of pathological distributions will create information where there is none.

The overall point being: there are many, many ways of viewing statistics and it's pretty trivial to find a perspective that allows you to call someone a "fraud". Sure there are actual frauds in data science, but one of the biggest strengths in this trend is bringing quantitative people from a wide range of backgrounds to gain refreshing insights. It is much more useful to encourage cross-discipline exploration than to simply say "you don't belong here".

[0] https://en.wikipedia.org/wiki/Mind_projection_fallacy

Doesn't seem like he's seeing more meaning than exists, check this book out & this field.

http://www.amazon.com/Modelling-Extremal-Events-Stochastic-P...

https://fernandonogueiracosta.files.wordpress.com/2014/07/ta...

Also Jaynes, made the mistake of thinking only Guassian's matter(The mistake he criticizes).

Sarcasm doesn't work that well on the internet. I suggest you speak more plainly in text.

MAD is about as simple as it gets, but it is not "the absolute most basic type of summary statistic." In many statistics courses, it is not taught at all, so it's perfectly possible for someone to know how multiple regression and random forests work but to have never before heard of quantifying spread in any other way than with squared deviations.

Just because someone doesn't know something that you do know doesn't make them stupid.

I'm an undergraduate engineer who has taken stats and I've never even heard of MAD before. I've thought about it [mean(abs(x)) ] but I've always assumed it would behave similarly . Which also seems to be case (apparently MAD is better though I don't really see why, as I understood it his argument is practically the same as when arguing about using median vs mean), which is why I'm not really understanding what the problem is. It's just a rescaling, as long as one sticks with one measurement type what's the problem?

Minimizing root-mean-squared error fits to the average (over-emphasizing the outliers). Minimizing mean-absolute-error fits to the median.

> Some of people are calling themselves "Data Scientists" who don't know the difference between σ and MAD?

Uh, that's just terminology. Data science is quite diverse and people have different backgrounds and work in different domains. Many mathematically/CS/EE-trained data scientists probably just look at the whole thing in terms of norms without explicitly using the term, MAD.

What about all the programmers who can't code simple things in interviews I see mentioned here?

Are they really programmers then ?

A mix, some people really can't code on a whiteboard, others freeze in an interview. Overall, I find FuzBuzz fairly useless and it was originally just a question if you knew the modular symbol, but it's gained ridiculous status.

there you go, pulling us off our high horse.

They sometimes hold Master's in CS degrees, but can't do FizzBuzz.

Trust but verify.

Can verify. I have worked with people with Masters in CS that can't FizzBuzz. It's rare, but it does exist.

And if the degree starts with "Cyber", send it to the circular file.

The modern day "professional", they may hold degrees, may sound impressive, probably read a few books on the topic from O'Reilly, but basically are not that good. Same with programmers, most are not that good. Same with decorators, or writers, or any field really. There will be the few who like it, learn it, practise it, aim to get better at it, but the vast majority, no.

Reply on news.ycombinator.com