Wednesday, July 31, 2013

Context? There's an app for that

Or at least a chrome extension.

The Dictionary of Numbers is a browser add on that gives context to the numbers people throw out there.  Apparently it will add in line context to numbers it encounters (ie 8 million people = about the population of NYC), and also provides a search function when that doesn't work.

I'm going to try this out and see how I like it.  Intentionally or not, people are always throwing out big numbers without proper context, and something like this could really help mollify that.

I'll be reporting back.

Sunday, July 28, 2013

Boy or girl...the choice is yours!

Apparently I am enjoying my summer a bit too much, or just the right amount, depending on how you're measuring.  I have an interesting backlog of articles to get to, just so you know I haven't forgotten about you all.

The one that's been bugging me the most is this article, titled "3 mammals that "choose" their babies sex".  Now to be fair, the article does pretty quickly clarify that there's likely no "choosing" going on...but there is proof that the gender ratio at birth changes based on circumstance.  I got interested in this because the last mammal on the list is human beings.

This conclusion is based on two studies.  The first one found that the 400 billionaires in the US were more likely to have sons than daughters (60% sons, 40% daughters).  This study got some press around the last presidential election, where it was noted that Romney had 5 sons, and Obama had 2 daughters.  Apparently the higher son ratio existed irrespective of whether the wealth was fully inherited, "actively grown" or earned from scratch.  This only existed for the male billionaires however...when it was the woman who had the money, she had a more even ratio of children (52% sons, 48% daughters).  One of the theories behind this is that men with lots of resources have more children, whereas it appears women with lots of resources do not.  This means there would be a genetic advantage to having more sons if you were at this level.

Now that's interesting to me, but I'm sort of curious what would have happened if you cross-referenced this with when the children were born in relation to the earning of the money.  This whole notion is precipitated on the woman somehow knowing the resources were there first...and yet if you look at many billionaire bios, it seems that some children were born prior to any wealth (as was the case with Romney's first three sons).  The study authors said that because the ratio is no different for inherited vs earned wealth, it is clearly not a quality of the males that influences the ratio (such as more testosterone = more male babies AND more financial success) , but I'm not so sure.  This could be easily tested by seeing if the gender ratio shifts once money is made (could be even more interesting if the men involved had second families with different women once they made their money...would the first wife or second wife be more likely to have boys?)  Also, the study authors mention they found these sex ratios by googling the billionaires....is it totally out there to think male children might be mentioned more often than female children?  Especially due to last name issues?

Now, I was going to leave it at that originally, but then I was googling a bit myself, and I found this paper.  It turns out someone had thought of my critiques already, and decided to go back and redo this research to try to amend for timing of earned wealth and also to get more meticulous about the counting.  It turns out male children ARE more likely to be mentioned in Wikipedia pages, and that the real ratio is 52% sons/48% daughters (general population is 51%/49%).  It also turns out that those with inherited wealth are more likely to have more sons than daughters (57%/43%), and those who worked for it are slightly (but not statistically significantly) more likely to have sons than daughters.

Now I don't think it's too hard to figure out why sons come up more in google searches than daughters...my guess is more sons take an active part in the family business and more daughters change their last names so they may appear to be unassociated with the father.  I think this whole thing highlights how important raw data source is when trying to study something.  I mean, the authors of the first paper did multiple regressions, but they didn't bother to spend much time making sure that Wikipedia was accurate????  My guess is far fewer people know about the refutation of this paper than the original.

Anyway, it's an interesting case of researchers confirming their own expectations.  No one went back to check the crazy ratio of sons/daughters, because they expected a skew.  It also shows how weirdly people use evolution at times...essentially the first paper argued that (for some) there was a selection effect happening before the event that should have skewed things actually occurred.  Timing is important, not just outcomes.  It's not that sex selection doesn't occur, but I would be hesitant to assign a specific mechanism without more data.


Wednesday, July 3, 2013

Wednesday Brain Teaser 7-3-13

Not a true brain teaser, but I figure people may be away for the looooong weekend.

I saw an article today complaining about how much new research gets left out of books about the Revolutionary War.  I'm not a history buff, but in my skimming of the article it seems his primary complaint is that books tend to go for narrative over ambiguous but accurate portrayals of events.  No kidding.

This got me thinking though, of a question for this week:

What historical fallacy, commonly taught in schools or repeated in the press, is most annoying to you?

Feel free to define "historical fallacy" as you see fit...I have no agenda here...I'm just genuinely curious.  

Happy 4th of July everyone!

Tuesday, July 2, 2013

A false positive nightmare

Once upon a time, I took an International Public Health class.  As part of this class, the professor was teaching us about false positives and false negatives (false positives = test results that say you have something when you do not, false negatives = test results that say you don't have something when you do), and he asked which one we'd prefer in an initial screening test for disease.  Most of the class said false positives...better to initially believe you have something and be told later you don't, right?  He agreed that we were likely right...in the US at least.  However, he explained, in other countries this may not be the case.  In some areas, even an initial suggestion that you had something like HIV could lead to some major fallout...spouse leaving, getting let go from your job, etc...that may not be easy to correct even once the final results were in. The problem is not always what a patient will do with information, but rather what others might do with the information.

I thought of this today when I read this story about a new mom in Pennsylvania who got her 3 day old baby taken away because she had eaten a bagel before going in to labor.  Yeah, you read that right.  The bagel happened to contain poppy seeds, and it turns out this caused her to test positive for opiates, which caused the hospital to report her, which caused her to have her daughter ripped out of her hands right after she got home.  Now, this story didn't make a tremendous amount of sense to me, so I read through the whole lawsuit (the hospital settled).  A few details that fill in some of the blanks:

  • This hospital has mandatory drug testing for all moms in labor.  This is actually not standard practice...my hospital for example only did this if there was cause.  No behavior on the part of the mother triggered this.
  • The cutoff used for the initial screening test is low...100 nanograms/uL.  In contrast the cutoff for say, Olympic athletes is 1000 nanograms/uL.  For federal drug testing, it's 2000 nanograms/uL for codeine, and 4000 for morphine.  The mother's levels were 300 nanograms/uL on the initial test, and 500 on the confirmatory test.  
  • The doctor who saw the mom and baby thought they were fine, so didn't even tell them about the test results.  She assumed they were a false negative.
  • The hospital reported these positive tests to state, whose policy states that two positive drug tests are all that's needed to take the child away.  They did no other investigation prior to removing the child.
Now based on the fact that the hospital and state social services have both paid money and changed their policy, I'm going to assume most of what's said above is true.  Given that, this is a scary real world case of people not understanding the ramifications of a false positive.  

Now truly, in the real world, is it better that a (known to be healthy) 3 day old baby spend two extra days in the care of a mother who uses opiates while an investigation can be done, or is it better that new parents have their baby taken away for several days for no reason?  The answer depends heavily on how often are they happening relative to one another.  Is it worth it if they happen at equal rates?  More false positives than false negatives?  More false negatives than false positives?

This is why it's so critical that people in many professions understand statistics.  As part of the lawsuit, it was explicitly mentioned that the training of the case worker failed to properly advise them that this could happen and to conduct themselves accordingly.  The judge who granted the ex parte petition also seemed to not know/not care about the false positive issue. 

Obviously we'd love to get the right information all the time, but the false positive/false negative debate is really about choosing which type of bad information you'd rather get.  This is a difficult choice, but the way to mitigate that is to remember that numbers are harder to misinterpret when you take them in the whole context, rather than just as stand alone facts.  In this case, the numbers are neutral...it's the standards set around them that cause the problems.

Monday, July 1, 2013

Single vs Married at Work

Sorry for the impromptu hiatus.  I wish I had a good reason, but it's really a few random personal issues combined with being totally obsessed with finishing the Games of Thrones books.  I decided I needed to put them down when I unironically called someone "craven".

Anyway, I've had a story up in my browser for a bit now that I've been meaning to comment on.  It's this Slate story about how "family-friendly" workplaces are discriminating against those who don't have kids, by making those without kids cover for those with them.

*Bias alert*  I have a great deal of sympathy for the argument that kids should not be the only acceptable reason for people to leave the office early on a regular basis.  If people are able to leave to get to soccer games for their kids, it should be just as valid if it's your own rec league soccer game.  Obviously people with kids will likely have more emergency calls, but I believe that too should apply to kids as well as parents needing a caretaker, aunts, uncles, nieces, nephews, pets etc.  If you're a caretaker for someone, you have my support...as long as you're getting your job done or taking available leave as allowed.  OTOH, there are some highly competitive or otherwise inflexible jobs that just don't allow this sort of thing, and I know that sucks.  When I've worked in environments like that (example: where you had to work on major holidays) there were generally blanket rules for everyone to keep things fair (work 2 out of 3 of Thanksgiving/Christmas/New Years)   Either way, I'm not a fan of having two sets of rules based on personal life choices.  *End alert*

Given that I'm inherently sympathetic to the viewpoint expressed, I was interested to find that I got really annoyed at what I was perceiving as a bit of a bait and switch within the article...as exemplified by this quote:

When almost half of the people in the U.S. are single, why do companies continue to cater to their employees who are married with children?" 
This quote came from an author of a book about discrimination against single people.  What irks me is that she's moving the goalposts around...are people being asked to do more work because they're single or because they're childless?  Yes, half of the population may be single, but as best I can tell nearly 80% of women have a biological child by age 44*.   That doesn't count step kids or adoptions, by the way.

Now there may be some data somewhere that shows married people with no kids get asked to do less than single people with no kids, but if it exists it was not included in the article.  At least anecdotally though, I think single people with kids actually tend to get more sympathy than married people with kids when it comes to time off.  That's absolutely fine with me...not having a back up must suck...but at least some of the single people she cited above will be singles with children getting more breaks than singles without children.

I guess it's just strange to me that we can all suffer through endless headlines about how many children are being born to unwed mothers and then turn around and imply that single = childless.  Additionally, the number of people checking "single" who are living with someone has been growing as well.  As family structures change, binary categories are less and less meaningful.  I don't doubt that some workplaces could get better at this, but we have to accurately identify the problem before we can agree on solutions.