Video of the day

Listened to a very cool Radiolab recently about the physics of a falling slinky.

The last week, I came across an Atlantic page on the same cool topic.  I like’s it’s embedded video better:

And some explanation:

 In the video below [I didn’t embed], physicist Rod Crossexplains that the tension of the spring counters the pull of gravity (“equal and opposite forces”), holding the bottom end of the Slinky in place until it “gets the information that the tension has changed.” By the time the bottom end of the Slinky gets the memo, the top end has fallen to meet it. What’s true for Slinkies is also true in sports, including tennis rackets, according to Cross. Your hand doesn’t feel the impact of a tennis racquet hitting a ball until the ball “is well on its way.”

Photo of the day

From N&O’s day’s best yesterday:

An owl is seen during L’Eroica retro cycling race on October 7, 2012 in Gaiole in Chianti. More than 5500 competitors from all over the world, wearing vintage cycling jerseys, will take part in L’Eroica, a retro cycling race through the ‘Strade Bianche’, the gravel roads of the Chianti area of Tuscany. (GABRIEL BOUYS/AFP/GettyImages)

On winning and having fun

It’s been a great run as a coach of my son David’s U13 Rec soccer game.  This weekend we won two games in convincing fashion to go to 5-2 on the season with 4 straight wins.  Three seasons ago I coached a team that went winless– 7 losses, 1 tie.  Now this is recreational level soccer and the whole point is to have fun.  But I have to say, winning is simply a lot more fun.  The kids have a better time, the parents have a better time, and I have a better time.  It’s not like a 70 minute soccer game you lose is wasted or something you regret, but there’s little doubt that that 70 minutes is significantly more fun when you win.  I actually wish it wasn’t that way, but it is.

To that end, I make sure all my players play a good chunk of the game.  (League rules are everybody plays minimum 50%– I generally try and aim for at least 60% for everybody.  It’s usually more than that due to missing players).  But I play my best players more of the game– sometimes 100% for my best player or two.  The way I see it, the kids playing less are giving some of what would be their completely equitable playing time to our best players to enhance our odds of winning.  I’d like to think that the average player would be happy enough playing 45 minutes instead of 50 if that 5 minutes gave one of our top goal scorers an extra 5 minutes during which he scored a goal and we won.  Am I wrong?  Hope not, because I don’t plan on changing.

Still not tied

I had hardly posted that last post then I heard Cokie Robert’s analysis on NPR this morning saying “the race is tied.”  I love my Morning Edition, but damn do I hate Cokie Roberts.  She’s just the epitome of un-thinking, conventional wisdom journalism.  She even referenced the RCP average in saying the race is tied.  It’s one thing to say that you are statistically tied based on a single close poll (I can forgive that), but the whole point of the RCP average is that it is much more sensitive and a 1.3 lead is undoubtedly a small lead, but a lead nonetheless and not a tie. Throw out Rasumussen like anybody serious about polling actually would, and it’s even better.  Again, not saying this race is really close, but its pretty clear that A) many journalists don’t actually understand this polling average thing; and B) even if they did, they would really prefer a tied race because it’s a better story.

The race is not “tied”

Given Romney’s movement up the polls after the debate (just how much remains to be seen), this seems like a good idea to share Drum’s recent post on polls as “statistical ties”

The idea of a “statistical tie” is based on the theory that (a) statistical results are credible only if they are at least 95% certain to be accurate, and (b) any lead less than a poll’s margin of error is less than 95% certain.

There are two problems with this: first, 95% is not some kind of magic cutoff point, and second, the idea that the MOE represents 95% certainty is wrong anyway. A poll’s MOE does represent a 95% confidence interval for each individual’s percentage, but it doesn’t represent a 95% confidence for the difference between the two, and that’s what we’re really interested in.

In fact, what we’re really interested in is the probability that the difference is greater than zero — in other words, that one candidate is genuinely ahead of the other. But this probability isn’t a cutoff, it’s a continuum: the bigger the lead, the more likely that someone is ahead and that the result isn’t just a polling fluke. So instead of lazily reporting any result within the MOE as a “tie,” which is statistically wrong anyway, it would be more informative to just go ahead and tell us how probable it is that a candidate is really ahead. Here’s a table that gives you the answer to within a point or two:

Pretty handy, no? Most national polls have an MOE of about 3%, so you can usually just use that row. NBC, for example, puts Obama ahead of Romney right now by 49-46%. So what are the odds that Obama is really ahead, and this isn’t just a statistical fluke? Answer: 84%.

But now for the bad news: As fun as it is to haul this thing out every few years, it’s obsolete. If you want to know who’s ahead, there are now loads of sites that aggregate multiple polls in various ways to provide estimates with far less margin of error than any single poll. If Pollster or RCP says that Obama is ahead by three points, then the odds are that he really is ahead by three points. There’s still plenty of room for various kinds of error in these poll-of-polls averages, but pure sample error isn’t really one of them any more.

We’re probably likely to see more polls where the difference is within the margin of error in coming days.  As long as Obama is ahead in the poll, he probably is ahead.  We just can’t be sure of it with 95% confidence.

%d bloggers like this: