Fix MMR range for Toss and Zerg

[llllllllllll-12402]

@Eliwan-1354

Simpson’s paradox is a phenomenon in probability and statistics in which a trend appears in several groups of data but disappears or reverses when the groups are combined.

Read and understand the article. This is the first sentence in the damn thing. Do you see this language it uses?

@Eliwan-1354

@Eliwan-1354

The gap here came about because a huge number of women applied for locations with limited seats - for example, no matter how many applicants the college gets, it can only accept, say, 500 applicants in each department.

If you can take 500 applicants whether you get 1000 or 10,000; then the huge number of applicants that are rejected washes away a lot of the other data when you look at the data at a different angle.

The example you used about male and female heights is a good example as well, since in that example we would not observe the dramatic difference.

Yes… So? You’re stating that there are other factors we could stratify them by. A Multi-varied analysis. We’ve already done so based on the 3 variables we had. There’s hundreds of other variables we don’t. That’s not the same as stratifying by the variable you’re looking to measure and drawing conclusions from that.

Read:
The entire data showed total of 4 out of 85 departments to be significantly biased against women, while 6 to be significantly biased against men (not all present in the ‘six largest departments’ table above). Notably, the numbers of biased departments were not the basis for the conclusion, but rather it was the gender admissions pooled across all departments, while weighing by each department’s rejection rate across all of its applicants.

They are, in this case, stratifying based upon the department. Not stratifying based on performance.