CALL ME "SALLY"

And when it does happen, people get the punishment they deserve.

I’m tired. How about you just go to a reliable website (y’know, not one that ends in “.com” because from what I’ve learned from a technology/computers class is that anything with .com at the end doesn’t always have reliable information and essentially wants to sell you something, try one like “.gov” or “.org”) and find out yourself?

Median. 

With no specification of the degree level, what they’re specifically doing, hours worked, etc. depending on either sex.

Also, when you find the median of something, to my understanding you line it from least to greatest, and whatever’s in the middle is your median. So just think about that for a little.

It is true women earn generally less, but it’s not because of “oh we’ll just pay them less because they’re women.” If that was the case, and it’s legal, why are men even hired at all? And even if it was real, you’d think the whole of the fuckin’ US would be aware, and you’d literally have everyone protesting, and the media would be talking about it 24/7. Being paid less just because of gender would be an outrage.

Women often pursue lesser-paying jobs. From what I’ve read, apparently about 85% of teachers are women, and 75% of people in the medical field are male. Teachers obviously earn less than surgeons and doctors and such. And with this in mind along with the median thing and degrees… Yeah, you get it, right?

So your complaint with the government stats reported in that website is that they reported median income? Without a mention of degree level?

It seems that using median here is actually fine because the median is much less affected by outliers on either end of the data set. I mean, I agree with you that mean, median, and mode, along with CIs, would provide a much better sense of the distribution and skewness of the data. But overall, providing one measure of central tendency is an generally accepted practice in statistical reporting.

You don’t know the rest of the pay. For all you know, with median, the woman could earn more than the man. (Even knowing, again, that can’t necessarily happen just because of gender)

Just grabbing some middle number and saying “hey this is what we got” then going “this is proof that women get paid less” is so unreliable because, again, you don’t know what the hell the rest of the money being paid is.

When deciding which measure of central tendency is best to use to measure the “average”, you have to know what your sample data look like (because it is just a sample, albeit hopefully a good, random sample of some N sufficient enough to be considered a good representation of the population).

You can use mean to measure central tendency if your data are normally distributed:

In fact, when the data are distributed like this, the mean, median and mode are all the same, right?

But, income data are not normally distributed, and they are often skewed one way or the other. You might have a negative skew if you have many people working are paid higher on the scale for whatever reason (mode is red, mean is green, and median is blue):

Or, you might have a positive skew if you have many low paid people in your distribution:

In these cases, you cannot use mean, because they don’t represent the true average of the distribution. Instead, median is a much better representation of the average, or at least, the “central tendency” of the data. 

In general, the “mean” is the one measure that is trotted out again and again as some sort of statistical “gold standard” when in reality it’s probably misused more often than not. You have to know your data, and then pick the measure of central tendency that is appropriate for your data.

In any case, I am guessing that the Dept. of Labor actually employ statisticians to do these kinds of things; people much smarter than you and I, at least when it comes to stats and the analysis thereof. 

If you’re not willing to understand the difference between mean, median, and mode, then our conversation ends here, I guess. Horse to water and all that jazz. I would like to note, for the record, that I thought I did an excellent job ignoring your insults, and instead provided a glimpse into what civilized discourse my look like. You’ll get a lot farther if you can actually talk about the issues instead of “thick skulls”.

SLIGHTLY DAMNED’S 12TH ANNIVERSARY RAFFLE!

On March 4, 2004, I started a webcomic called Slightly Damned… and I never stopped! Slightly Damned is turning a whopping 12 years old on Monday, March 14th, 2016!

I don’t usually do anything except have some dessert with friends or draw a small picture. But this year I thought, “Aw, what the heck. I’ll hold a raffle on tumblr!”

THE PRIZES

Grand Prize: 4 plushies of your choice + 4 charms of your choice + 4 can coozies

1st Prize: 3 plushies of your choice + 3 charms of your choice + 3 can coozies

2nd Prize: 2 plushies of your choice + 2 charms of your choice + 2 can coozies

3rd Prize: 1 plushie of your choice + 1 charm of your choice + 1 can coozy

Many more photos of and detailed information about each of these items can be found on their Storenvy listings: http://chu.storenvy.com/collections/784851-slightly-damned

I will pay for the cost of shipping! I will use the United States Postal Service and cover the shipping costs ONCE.

HOW TO WIN & HOW THIS WORKS

Reblog this post by Sunday, March 13th, 2016 at 11:59 PM Arizona time. That’s it! You don’t have to “like” it or follow me; doing so will not affect your chances of winning. (But I’d appreciate it anyway!)

Anyone from any country is eligible to enter and win!

On Monday March 14th, I will take the names of the people who reblogged the post and use the Random.org “List Randomizer” to randomly put them in a numbered list. #1 will win grand prize, #2 will win first prize, #3 will win second prize, and #4 will win third prize.

I will make a public post announcing who won AND notify the winners privately using tumblr.