Sunday, March 25, 2012

You've got to look out for the lags

Another attempt at an econometrics poem - this one to end my lecture introducing distributed lags and dynamic models


You asked me for some comments
On the models you have tried
Some instantaneous feedback
On what you've specified

My immediate conclusion
Is you should have tried some lags
Your perspective's far too static
You've got to look out for the lags

You've got to look out for the lags
You've got to look out for the lags
Don't want to be over dramatic
But you've got to look out for the lags

Yes you've made a big assumption
That all adjustments will be fast
Come in the current period
Nothing left there from the past

But responses may be spread out
So think about some lags
Your perspective's far too static
You've got to look out for the lags

You've got to look out for the lags
You've got to look out for the lags
Guess I must be quite emphatic
You've got to look out for the lags

When expectations are allowed for
And agents plan ahead
Adaptively or rational
It's just as I have said

Disequilibrium adjustments
Error feedback to include
Your perspective's far too static
You've got to look out for the lags

You've got to look out for the lags
You've got to look out for the lags
More dynamic than instamatic
You've got to look out for the lags

With general to specific
Please test rather than impose
The restrictions you consider
Appropriate to propose

When using time series data
You have to try some lags
Just be a bit pragmatic
And look out for the lags

You've got to look out for the lags
You've got to look out for the lags
If you do I'll be ecstatic
You've got to look out for the lags


Thursday, March 15, 2012

I'm a serial correlator (a poem for the end of my autocorrelation lecture)

I'm a serial correlator
I'm so affected by my past
Every time I move forward
I feel the effect of what happened last

Track me over time and you will see
The past is always hanging over me
By Durbin-Watson or Breusch-Godfrey
It's all shown up statistically

Am I AR(1) or AR(2)?
I'll have to  leave that up to you
Rhos by any other name will be
Different from zero when you look at me


Monday, March 12, 2012

iMetrics - an econometrician's dream


I don’t know if it was because I was watching the Secret Policeman’s Ball on Channel 4 on Friday night, or because I had viewed a video clip on the web about the new iPad, or because I was worried about the progress that one of my Independent Study Unit groups is making. Or maybe it was just because I had drunk a bit too much red wine that evening. But I had a very vivid dream on Friday night and I could still remember most of it when I woke up. It went something along the following lines:

I had in front of me a tablet computer. On the screen was a little graphic with a picture that looked rather like Eddie Izzard. I tapped it. The image got bigger and started to talk. “Hi Guy, this is Ray your R.A. What can I do for you today?” 

I spoke. “I need you to get some data on patents in the pharmaceutical industry – recent applications and any info on other patents they cite and patent applications that cite them. There is a paper by a guy called Chaudry, I think. He did some work on US patents and how they affected the firms’ stock market prices. So can you do the same kind of thing for me please with UK data?” 

“Yep! No problemmo” came the reply.  For a brief interlude the screen was filled with Coldplay performing “The Scientist”.

Then back came Ray.  “Hey Guy. The dude you want is Chauhan. Had something out in 2009 about patent ownership and stock market valuation.  I looked at his paper and figured out the data you need for a UK study. I can get the patent stuff from the IPO – the Intellectual Property Office, and the stock market prices from Bl0omberg. Do you want me to go ahead?”

“Sounds great to me” I replied. “On you go”

Ray’s face disappeared and this time I watched a video clip of 10cc’s Wall Street Shuffle.

Then Ray appeared again. “Look Guy, I have all the data. But don’t you want a kinda comparative study where you can see if there are differences between industries? I can get the same stuff for hi-tech industries or software code.”

“A great idea Ray – go ahead”

“Well, like, I have already done it” replied Ray. “I guessed you would wanna move that way. And I done some panel data unit root tests. And a whole bunch of regressions. Do you wanna see the summary results and charts I done for you?”

“Wow, yes that would be great. Can you summarise the findings in a few sentences for me please?” “Oh, and Ray. I hope your written English is better than the way you speak it. You know I like working with you Ray – I really do prefer an Open Source R.A. But all this discussion of patents makes me wonder if I shouldn’t invest in the proprietary Scientific Academy Research Assistant, SARA ©.”

“Hey Guy, don’t be like that. We make a great team. And actually I have already prepared a draft paper for you in the style needed for the Journal of Finance. I think there might also be a paper for the Journal of Econometrics because I had to, like, develop some new recursive heteroskedastic consistent standard errors for the unbalanced panel data models I done for you”

And then I woke up. It was only a dream. Or was it a glimpse into the future?