Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Hey, wait – is employee performance Gaussian distributed?

timdellinger.substack.com

Post reply on HN
Print view View original

31–40 of 341 posts

Re: Hey, wait – is employee performance Gaussian distributed?

#31

Post by sokoloff »

iambateman wrote: post #21

As employees, our expectations for performance management come from the system of giving grades in school. What's interesting is that school grades often doesn't follow a normal distribution, especially for easier classes. I suspect that getting an "A" was possible for 95%+ of students in my gym class and only 5-10% of the students in my organic chemistry class. In the same way, some jobs are much easier to do well t…

Would “doing all of the tasks they were asked to do” really be “exceptional”? What could be exceptional about that? I would think it would be “meets expectations” at most.

Re: Hey, wait – is employee performance Gaussian distributed?

#32

Post by doctorpangloss »

This article: "Wouldn't it be cool if when you measure employee performance, it turned out to fit a Pareto distribution better than a Gaussian?"

Would that be cool? We could posit the implications of all sorts of improbabilities. But I feel more strongly about how cool it would be that P = NP.

All this aside, being laid off sucks - being pushed out, even when you're a high performer, sucks even more. The truth is that "data science" does not help you process grief the way reading Dostoevsky does, so maybe getting an A in your liberal arts education is valuable even when you are working as a software developer.

Re: Hey, wait – is employee performance Gaussian distributed?

#33

Post by kurthr »

nightski wrote: post #23
iambateman wrote: post #21

As employees, our expectations for performance management come from the system of giving grades in school. What's interesting is that school grades often doesn't follow a normal distribution, especially for easier classes. I suspect that getting an "A" was possible for 95%+ of students in my gym class and only 5-10% of the students in my organic chemistry class. In the same way, some jobs are much easier to do well t…

Having a shifted mean doesn't mean they aren't a normal distribution. Not saying they are necessarily, but the anecdote you are providing isn't convincing.

Perhaps, but due to the sampling of the distribution you would likely never know. If 95% of your samples fit in the top 3 bins, you can’t say much at all with certainty. Poisson, Gaussian, binomial, Boltzmann, gamma…

Re: Hey, wait – is employee performance Gaussian distributed?

#34

Post by marian_ivanco »

nightski wrote: post #23
iambateman wrote: post #21

As employees, our expectations for performance management come from the system of giving grades in school. What's interesting is that school grades often doesn't follow a normal distribution, especially for easier classes. I suspect that getting an "A" was possible for 95%+ of students in my gym class and only 5-10% of the students in my organic chemistry class. In the same way, some jobs are much easier to do well t…

Having a shifted mean doesn't mean they aren't a normal distribution. Not saying they are necessarily, but the anecdote you are providing isn't convincing.

That is not IMHO what he is trying to say, you don't shift the distribution, you measure if somebody passed a test. I the test is "passable" then one side of "distribution" is at least cut off. E.g. it's normal (and sometimes expected) that the whole class will pass without issues.

Re: Hey, wait – is employee performance Gaussian distributed?

#35

Post by drcwpl »

bhouston wrote: post #30

I would feel better if this was derived from empirical data rather than just rhetoric. This seems super testable, no? There is probably a ton of data already in different industries with regards to productivity. Even if human talent have a Pareto distribution (which is not clear), the people employed by a company are a selected sub-set of that population, which would likely have a different distribution depending on…

Agree with you - although, rhetorically speaking, I have come across many instances which the author refers to "of low performers are 3x as common as high performers." This is unfortunate as I always think do your best, and as Tyler Cowen states - Average is Over. So agree it would have been way better to use empirical data to back up this claim especially.

Re: Hey, wait – is employee performance Gaussian distributed?

#36

Post by dowager_dan99 »

nightski wrote: post #23
iambateman wrote: post #21

As employees, our expectations for performance management come from the system of giving grades in school. What's interesting is that school grades often doesn't follow a normal distribution, especially for easier classes. I suspect that getting an "A" was possible for 95%+ of students in my gym class and only 5-10% of the students in my organic chemistry class. In the same way, some jobs are much easier to do well t…

Having a shifted mean doesn't mean they aren't a normal distribution. Not saying they are necessarily, but the anecdote you are providing isn't convincing.

if your scale doesn't have the atomic values at the top end to differentiate the data it's not a normal, it's Pareto or Zipf or some other power law.

Re: Hey, wait – is employee performance Gaussian distributed?

#38

Post by dowager_dan99 »

sokoloff wrote: post #31
iambateman wrote: post #21

As employees, our expectations for performance management come from the system of giving grades in school. What's interesting is that school grades often doesn't follow a normal distribution, especially for easier classes. I suspect that getting an "A" was possible for 95%+ of students in my gym class and only 5-10% of the students in my organic chemistry class. In the same way, some jobs are much easier to do well t…

Would “doing all of the tasks they were asked to do” really be “exceptional”? What could be exceptional about that? I would think it would be “meets expectations” at most.

You don't really need a distribution to measure tasks that are binary in nature though, why bother with a Likert scale when you can just use a yes/no checklist? I suspect there's also a high correlation between the jobs/roles and the likelihood of being displaced by machine or otherwise, as measuring success is a key problem to be solved when "dehumaning" these jobs.

Re: Hey, wait – is employee performance Gaussian distributed?

#39

Post by atoav »

iambateman wrote: post #21

As employees, our expectations for performance management come from the system of giving grades in school. What's interesting is that school grades often doesn't follow a normal distribution, especially for easier classes. I suspect that getting an "A" was possible for 95%+ of students in my gym class and only 5-10% of the students in my organic chemistry class. In the same way, some jobs are much easier to do well t…

One thing where this analogy stops to work, is that more so than in school your performance in a company can be highly dependent on how well and/or timely others do their job. Your managers performance metric may or may not catch that. E.g. imagine you are assigned a project where you have to interact a lot with department X and now department X is running at/over capacity, so you are performing worse, because their part isn't done in time and each back and forth takes half a week. Now you spend half your time not being productive with no fault of your own and the others are 110% productive while setting the whole shop on fire. Based on that metric they should fire you and hire more people for department X, when in fact they should probably just hire more for them (or reorganize the department).

Another example where this analogy stops working is that in school the students usually get the same/comparable assignments, that is somewhat the point of those. As the goto hard-problem-person at my current workplace I am pretty sure that it is absolutely impossible to compare my work to the work of my collegue who just deals with the bread and butter problems, it isn't even the same sport. How would you even start doing a productivity comparison here, especially if you understand 0 about the problem space

Post reply on HN