Hand waving, model making, and variable lags

I would suggest that anyone who is interested in economic models reads this post, namely because I agree with it wholeheartedly 🙂

While it might seem cool to run some regressions and get a result that you believe will tell you the future it is important to realise what your implicit assumptions are.  If you add a variable to you model and it is significant but you don’t know what it has to do with anything you should be careful.  This is how using a lag functions.

You need to ask yourself why is this lag significant? what is the process behind it? Data can only really be used when you can frame it with a model of how the world works.

Personally, I hate using too many lags unless I have an understanding of why the lag matters.  When you do an empirical model it isn’t just the “significance of the variables” that matters – it is the believability of the implicit model that it represents.

Americans growing more tolerant of gay marriage

After the sadness of California passing Proposition 8 banning gay marriage last year, there have been a couple of recent victories for civil rights campaigners in Vermont and Iowa. That motivated Nate Silver to work the numbers and ask when we might expect the rest of the US to reject a ban on gay marriage. The outcome is shown in the following diagram from The Map Scroll:

Rejection of ban on gay marriage

Rejection of ban on gay marriage

Read more

Stats to ponder

I’m lucky enough to be flicking through the latest Review of Economics and Statistics so I thought I might sum up a couple of interesting tidbits while I’m reading: Read more

This proof’s a lemon

I couldn’t resist posting this chart linked byMegan McArdle. It is just SO appropriate given Matt’s recent post. If using graphs like this counted as proving a scientific fact then the world would be a whole lot easier to explain 🙂

Homecoming Queen still on top

For all the nerds and geeks who cursed the popular people at high school but comforted themselves with the thought that future success would be theirs… Steven Levitt has bad news:

…each extra close friend in high school is associated with earnings that are 2 percent higher later in life after controlling for other factors. While not a huge effect, it does suggest that either that a) the same factors that make you popular in high school help you in a job setting, or b) that high-school friends can do you favors later in life that will earn you higher wages.

Read more

Real income, poverty, and a tiered CPI

According to a recent book by Christian Broda and David E. Weinstein (Prices, Poverty, and Inequality: Why Americans are Better Off Than You Think) (ht Marginal Revolution) growth in income inequality was less pronounced in the US because of changes to the quality and cost of goods that “poor” people purchased.

This indicates to me that a tiered consumer price index could be a useful thing.  Currently the household economic survey (HES) provides an annual tiered income measure (where we see the average income of different income deciles).  However, this nominal measure is not particularly useful if the change in prices experienced by different groups are very diverse.

As a result, a similarly tiered CPI measure (so a CPI for each income decile) would actually give us a much better way to figure out change in “real income” and thereby a fairer measure of the distribution of real income – which is something we care about.

Surely the HES has a measure of purchases by different income groups.  As the CPI is broken down into different products it should be possible to take these weights and come up with a loose set of indicies that represent the price inflation faced by different income declines shouldn’t it?