statistics

Statistical study offers evidence of warning signs before Neolithic community collapse

A trio of researchers, two with the University of Maryland and the other with University College London has found that early Neolithic communities exhibited warning signs before collapsing. In their paper published in Proceedings of the National Academy of Sciences, Sean Downey, W. Randall Haas, Jr. and Stephen Shennan describe the statistical analysis they conducted on data that has been collected through prior efforts from Neolithic communities that existed approximately 9,000 years ago and what they learned as a result.

Knowing when a given community, town or city is about to collapse could prove useful in the future as the planet continues to warm—how such communities responded to stresses that have occurred in the past, the researchers found, may offer clues to the robustness of modern communities. Read more.

anonymous asked:

What's the typical amount artists earn at a convention? Do most people manage to make a decent profit or is it the norm to just break even (unless you're a well-established artist)? What counts as "doing well"? I know this probably depends on many factors. The only con I've ever tabled at is Otakon, for reference.

Kiriska: Sounds like this report may be useful to you. Here’s a sampling of the sort of data in the report:

I don’t think it’s very helpful to make sweeping claims about what constitutes “average” without taking into consideration the multitude of factors that contribute to artist revenue at conventions, which is one of the reasons I started this survey and subsequent reports.

What counts as “doing well” is going to vary between every single person you talk to. My personal “doing well” threshold is different from my friends’, and is highly dependent on the expenses, travel, and stress tied to a given con, and fluctuates even between very similar cons. The “doing well” threshold also changes a lot depending on if the artist is a hobbyist or a professional trying to make their living this way, and yes, many do make their livings this way.

Money is not the only thing artists get out of conventions, so that’s important to keep in mind too. Some conventions aren’t great for profit, but people go to see friends and make friends, to network, to share their work with a different audience in a different region, etc. These are benefits that are difficult to measure, but they’re worth counting too. 

Latest numbers: Business R&D up 5.6 percent

You probably knew that research and development is a major area of focus for businesses, but did you have any idea how much R&D they perform? Businesses spent $341 billion on R&D performed in the United States in 2014 – that’s a 5.6 percent increase over the previous year, according to a new report from the National Center for Science and Engineering Statistics (NCSES).

For more information, including R&D performance numbers for all states and a breakdown of spending by different business sectors, read the full report.

Some ways that statistics can lie to you without ever falsifying their data:

  • Reframing a small absolute difference as a large relative difference. For example, it’s technically correct to describe an increase from 0.01% to 0.04% as a 300% increase - but is a +0.03% bump what you’d assume to be the case if you heard the phrase “300% increase”?
  • Using one type of average while implying that you’re talking about a different type of average. For example, if a company has nine employees who make $10/hour and one manager who makes $60/hour, you can take the mean average and state with technical truthfulness that the average wage is $15/hour, even though no actual person makes that.
  • Reporting accuracy in terms of the absence of false negatives without considering the presence of false positives. A test that returns a positive result 95% of the time when what it’s looking for is present may sound reasonably accurate - but what if I told you that it also returns a positive result 30% of the time when what it’s looking for isn’t present?
Statistics, Shipping, and Smut

Yesterday I was wondering about the distribution of fanfiction categories vs. ratings in, so I decided to run some statistics to satisfy my curiosity. I chose Fire Emblem: Fates for two reasons: because I’m familiar with the fandom, and because there is a roughly equal distribution of male and female characters.

Then, when someone in the Sin Bin linked me to this post about the hyper-sexualization of mlm in fandom circles, I decided that this is the sort of thing that I should share (and I encourage you to as well). My results are far from perfect, as they don’t account for overlap in category tagging, but they do, I think, a fairly adequate job of getting the point across.

Works rated M or E are shown in red; all others are shown in grey.

As of 8/14/2016, there were 2510 total works on AO3 under the Fire Emblem: Fates fandom tag. Of these 2510 total works:

  • 681 (27.1% of all works) were rated M or E
  • 909 (36.2% of all works) were categorized as F/M, 268 of which were rated M or E (29.5% of the category)
  • 907 (36.1% of all works) were categorized as M/M, 328 of which were rated M or E (36.2% of the category)
  • 377 (15.0% of all works) were categorized as F/F, 106 of which were rated M or E (28.1% of the category)

In the remainder of this post, I break down the percentages of M+ rated works (or “theoretical smut”) in each category, as well as in the three most popular pairings for each category.

More detailed statistics, graphs, and rating analysis below the cut.

Keep reading

youtube

These points are relevant to science research as well! To get to the “truth” is not an easy thing.

Our nine-point guide to spotting a dodgy statistic

Every statistician is familiar with the tedious “Lies, damned lies, and statistics” gibe, but the economist, writer and presenter of Radio 4’s More or Less, Tim Harford, has identified the habit of some politicians as not so much lying – to lie means having some knowledge of the truth – as “bullshitting”: a carefree disregard of whether the number is appropriate or not.

So here, with some help from the UK fact-checking organisation Full Fact, is a nine-point guide to what’s really going on.

  1. Use a real number, but change its meaning
  2. Make the number look big (but not too big)
  3. Casually imply causation from correlation
  4. Choose your definitions carefully
  5. Use total numbers rather than proportions (or whichever way suits your argument)
  6. Don’t provide any relevant context
  7. Exaggerate the importance of a possibly illusory change
  8. Prematurely announce the success of a policy initiative using unofficial selected data
  9. If all else fails, just make the numbers up

anonymous asked:

Isn't your point of Naive Diversification defeated simply by the existence and success of the Dark Souls series? In that series you can put your points in to anything you want and build however you want. You have total freedom. But people don't just throw their points in to "every category." They have optimized builds for the style they want to play.

Are you seriously trying to tell me that the series whose community mantra is “Git Gud” doesn’t have a lot of bad players in it? That a large number of players don’t constantly make all sorts of mistakes with their builds and play? Who do you think “Git Gud” is directed at, a minority or a majority of the players?

Don’t mistake sales numbers for a gauge of community skill or ability. The larger the game’s player base, the worse the average player tends to be, because the player base approaches approximating the overall average gamer… and the average gamer is not very good. Remember, around 80% of the average game’s player base never even looks online for information about that game, and only about 5% of them will actually ever post. This group is the hardest of the hard core and they are self-selecting, making them non-representative of the overall player base.