Congresscritters Aren't Like The Rest Of Us

This last few weeks, we've heard a lot about research conducted by Ziobrowski et. al. (see here and here) on the possibility of informed trading by Senators and Congressmen. Based on abnormal returns earned on their portfolios, it appears that they do use their "inside information" in ways that would be illegal for those not in government service. In case you haven't seen it, here's the 60 Minutes story that brought Ziobrowski's research into the public eye:


Now here's another fun fact - Congresscritters not only get to profit from material nonpublic information, they also get to reveal it to select parties too. It seems like a number of hedge funds regularly meet with members of congress to get fast track access to this information. Here's a video from the Wall Street Journal for your viewing pleasure.



And here I though our elected officials were pure of heart and above approach (sorry - I think I shouldn't have changed my meds without doctor's orders).

Journal Of Undergraduate Research In Finance

There's a new journal out geared towards undergraduate research. It's called (appropriately), The Journal of Undergraduate Research In Finance. Here's it's description:

The Journal of Undergraduate Research in Finance publishes original work written exclusively by undergraduates. Accepted articles are largely the result of the highest quality senior or honors theses. Articles come from all areas of Finance, case studies and pedagogy. All articles are subject to blind review by faculty.

The JURF exists to encourage exceptional undergraduate students to pursue high quality research in Finance, to provide these students with an outlet for their research, and to prepare these students for success in graduate school or industry. To maintain a focus on contributions made by the students, faculty involvement is limited to the guidance typically given during the writing of a senior thesis. Initial submissions must be made while the author is an undergraduate student.

The JURF is published annually.

So, if you have a student who has done some good research and who might be looking for an outlet, have them send it in - the submission deadline for this year's edition is May 15. As an added inducement, the top three articles for this year's issue will be invited to the FMA meeting in Denver to present their research, and will be considered for the annual Mark J. Bertus prize (in the amount of $1,000).

Yo Momma is a Data Miner

Having a lot of data makes research easier - we now have more data in easily readable formats than ever before, and an amazing amount of computing power on our desktops (I have far more horsepower on my desk than NASA had in total in the 1980s)..

Unfortunately, there's a flip side to that coin - we can easily find variables (or specifications) that seem to "predict" returns (or just about anything). In reality, we're often just overfitting the data.

Here's a pretty good piece on the topic titled "Yo Momma is a Data Miner", by David Leinwebber in which he fits a polynomial time-series regression to the S&P 500 with surprising (if you don;t follow what he's doing) good results - particularly since he's using things like the sheep population and Bangladesh Butter production as regressors.

Undergraduate Thesis on CDOs and the Credit Meltdown

This Harvard undergrad's senior thesis on CDOs (Collateralized Debt Obligations) and their role in the credit crisis was recently mention in Deal Journal.

It the doesn't say anything new, but it does an impressive job of marshaling facts about the CDO markets - the author hand-collected a data set on over 700 CDO deals, and provides a wealth of information.

What's more, she did it within a semester's time.

HT: Marginal Revolution

Memoir of Gene Fama

Here's a pretty good "brief" memoir Eugene Fama wrote for a journal. I say "brief" because it runs pretty long - but that's to be expected given all the work that Fama has done.

Arghhhh!

The deadline for submissions to the FMA (Financial Management Association, our national association) national conference is this Friday. I'm trying to get two papers done - one in which I do the data analysis and hand it off to my coauthor for the writeup and another where the reverse happens (she analyzes and hands off to me). Last week I thought I was in good shape.

Uh oh - I spoke too soon.

First, this weekend when no one is around, my office computer gets cut off from the Internet by the University IT department - they said I had a virus. So, for the weekend I used my laptop for interned access (some citations and work on WRDS), and kept running analysis on my desktop - it has two screens and a lot more power.

Come Monday morning my college's IT guy (who is fantastic, BTW) said he'd look at it. So, I backed up all the relevant stuff for the two papers to a portable hard drive and started working on my notebook. I figure he'd scan the hard drives and give it back to me in a day or so.

Next thing you know, my IT guy tells me that my boot drive has gone Tango Uniform (I have two hard drives in the system - one is the boot drive and the other has all my data on it). Luckily I'd backed up everything from the data drive before giving the machine to him.

It's a 4 year old system, so, it looks like I'll be getting a new system with more memory and a bigger hard drive. But in the meantime, I'm working on a laptop with a 12 inch screen.

Ah well, I'm just about done with my part of the first paper, and I just got a load of stuff from my coauthor on the second one. So it'll be a busy week until Saturday.

One of these days I'll run across this Murphy guy, and we're gonna have some words.

Talking With Practitioners

Unknown University recently had a function where they brought back a number of prominent alumni to talk about various topics. At dinner after the function, I ended up at a table with an MD from a major investment bank who manages about 10Billion overall in both traditional funds and alternative investments in the market where I'm currently doing some research. It was not by chance - I offered to lead a session that he was the main speacker for, and asked to be put at his table afterward.

So, at dinner (in between him checking his Blackberry every few minutes (dan - that is distracting), I got a chance to see whether my story about what I saw in my data passed the "sniff test" from someone who works in that market on a daily basis. Luckily, it did. Having topped that bar, we started talking about what sorts of things his firm has done in terms of research on the particular topic. So, it looks like I made a connection that could result in my getting some pretty scarce data in exchange for doing some research for the guy. It's a win-win - he gets some relatively low-cost access to eggheads, and I and my coauthor get some scarce data and access to people who can tell us far more about the markets involved than we could learn from academic articles and textbooks.

So, the bottom line is - If you're an academic who works on related topics, talk to practitioners. It's good for you.

A Brief Update

I survived the first week of the semester at Unknown University. This is my first time ever teaching three preps, and it's tougher than I expected. I'm about 1 1/2 weeks ahead in my classes, so I'm not running around playing catch up (another first, it seems). But, it's still no cake walk.

On a different note - I just got an email from a coauthor. It contained a graph with some absolutely kick-hiney (that's a technical term) results. Times like this remind me what I love about this job - finding out interesting new things. I've got great hopes for this project - not only that it'll place in a good journal but that it'll be the start of a new stream of research. Time will tell, but for now, I'm excited.

Ah well - time to give the Unknown Baby Boy his last bottle for the night, and then turn in.

updates the next day - even more good new results. Woo Hoo!

The Summer Winds Down

It's been a busy week here in Unknownville. Unknown University starts up next week (we start later than most), so we've had a rash (or is that a plague?) of meetings. I'm still juggling several papers (writing a lit review for one, doing data work for another, and some polishing/editing for a third) and sequentially disappointing my coauthors.

Ah well - them's the breaks. But I have to be nice, since coauthors on each paper read the blog. So fear not, coauthors - my parts will be done in good time.

Along those lines, I just received a bunch of results from one coauthor, some of which are pretty interesting. It's an area that I had an unsuccessful paper in several years ago, and she usues s new and difficult data set that allows us to revisit the topic in a very new way. WE've got a good story and good results, and it'll gp to the head of the pile, since we're sending the paper to an upcoming conference (the Eastern Finance Association annual meeting) for which the deadline is next week. I hope it gets accepted since the Unknown Wife and I plan on making it a little vacation (she's neve been to Miami). We're pretty confident - its a good idea,goood data, and believable results (And we know the program chair).

After all, that's potentially one of the perks of academia - you can sometimes have the university partially fund your vacations by choosing your conferences wisely.

Finally, I just got an email telling me I've won 12,841,340 Euros in an inernational lottery that I don't recall entering. I have to share it with 14,000 winners, but it'll give my students something to calculate when I cover foreign exchange rates.

UnknwonDaughter is now back in scnool and once agaion well ahead of her classmates.. And Unknown Baby boy continues t alternately make us laugh and make us gag as he exceeds manufacturers capacit on his diapers (or as we call them "Code Brown!). Ah well - the wages fo hchild rearing.

Peace

-UP

Data Analysis With Stata

The Unknown Family went to the Unknown Sister-in-Law's family's house in an adjacent state (their youngest daughter is going off to college, and Unknown Wife wanted to see her before she leaves for the Big Adventure). So, I got a couple of days to myself. Nothing very exciting - I've been grinding data during the day, and went on a couple of longish bike rides (I'm up to 25-30 miles at a time at what for me is a pretty good clip).

On the data analysis front, I finally took the plunge and started using Stata. It's a pretty amazing package of tools. I work with a lot of large and complicated data sets, and there's always a lot of data manipulation before I get to the point where I'm running statistical analyses. When it comes to moving data around (merging data, sub-setting, mean adjusting, etc...) SAS wins hands down. And I've put a lot of time getting my SAS chops, so I'd put off learning Stata for a long time.

But I now understand what so many of my friends have been telling me for so long - once you get to the point that your data is all nice and neat, Stata rocks. I was able to do many permutations of regression models (fixed effects, random effects, robust and/or clustered errors, etc...) in about a quarter of the time it would take in SAS. And while it's possible to work in batch mode by writing "do" files, you can do quick and dirty analyses with drop down menus.

I have seen the statistical light, and it reveals that I'll be doing a lot more with Stata in the future.