From Teaching

Financial risk taking and gender in my teaching

I have just finished reading The hour between dog and wolf by John Coates on the biology of financial risk taking. As a former derivatives trading Dr John Coates has first hand experience in the neurological patterns that traders experience during financial booms and busts and how this influences P&L account volatility.

The book is based on his years of academic research after returning to Cambridge University from industry to study a PhD in neuroscience and finance. He has since published considerable evidence refuting the neo-classical economic ideal that we choose our course of behaviour after thinking things through. 

 He argues that the aristotlean idea of the body and mind interconnectedness is a more coherent explanation for modern financial risk taking than traditional neck up economic rationalism.

The board tenant of the book is that the mind and body of traders works as a dynamic feedback loop, with testosterone being the molecule of irrational exuberance and a reason that ralllies change into bubbles.

One of Coates’ clear conclusion is that more female traders are needed to moderate the large fluctuations in financial markets.  This resonates with some antecdote evidence I have from teaching my Trading Principles course on the MSc in Computational Finance and Trading.  This course is based around real world trading simulations, and students are assessed on their trading book perfomance. 

This year a third of the students where female. This cohort performed much better in their trading book cumulative NAV (measured over all 16 simulations).  Also in the Law of One Price simuations the girls achieved much higher broker interest rebates, a clear indication that they are sucessfully offseting their risks from arbitrage trading.

Next year I hope to design a more scientific method to statistically confirm this antecdotal finding.

  

Financial data analysis as an iterative feedback process

In the first few lectures in my Financial Econometrics course I emphasise that analysing financial data should be an iterative learning feedback process, where an initial idea may be modified after some statistical analysis reveals an incomplete or incorrect answer to our initial hypothesis.  It is important for my students to understand that econometrics is not about producing ‘black box’ results from statistical software but is a gradual learning pathway which leads to asking the correct question using the correct empirical design and data.  This enables the analyst to avoid what Kennedy called Type III errors; getting a statistically precise answer to the wrong question.

Here is a short video explaining this process:

The Misery of the Technical Analyst

After reading Nate Silver’s excellent “The Signal and the Noise” book recently i thought i would illustrate the difficult that technical analyst (or chartists to be more derogatory) have in identifying the real information (signal) from the noise in UK stock markets.

I have taken the FTSE 100 as an example.  Below are six prices series.  Three of these are 1000 trading days of the FTSE100 in the 1990s, 2000s, and counting back from today.  The other three are fakes, and have been generated by simply flipping a coin (actually telling STATA to pick a random series of 1s and Os).

Technical analysis is identifying the signal solely on the basis of past statistical patterns, without consideration for the historical financial characteristics of a company.  You can have some sympathy for the difficult task they face in the graphs below, its really difficult to distinguishing the signal (FTSE100 series) from the noise (the fakes or random walks).

 spot_the_FTSE

 

Click here to find out which graphs are the FTSE100 and how i used STATA to generate these graphs.

 

Model Parameter Stability

The first assumption of the classic linear regression model is that the dependent (or outcome) variable can be calculated as a linear function of a specific set of independent (or predictor) variables, plus a disturbance term1.  This statement implies that the unknown parameters of this linear function are stable or constant over the estimation period.   This assumption is particularly important when using a linear regression model to predict.

In practical terms you are assuming  the effect of your predictor(s) remains unchanged over the sample period; for relationships between financial variables this may be unrealistic in the presence of large ‘landscape changing’ events.  In econometric terms these large events are sometimes called break points.

This instructive video explains in more detail how to test for parameter stability, both when a break point is known and when we cannot clearly identify a break point

Click here for the do file, and here for a copy of the slides.

  1. See Chapter 3 of Kennedy 1998 “A Guide to Econometrics” for an excellent introduction to the five assumptions underpinning classic linear regression models

Email Policy

Emails should be used after the more traditional verbal forms of communication have been exhausted.  Giving bespoke feedback is important to me, and in my experience the best and effective feedback process is usually verbal.  Face to face interaction is a dying art in the digitalised age and in the professional workspace top employers highly value such soft skills. For example:

angry meI communicate extensively using emails, and I will respond to them quickly and efficiently.  I will also use text messaging as a means to interact with people more effectively.  I don’t like (or respond to) emails written as text messages.  Recently I received this  email from a student:

Some of the slides that you used in the lecture today aren’t in the slides up on QOL.  Are you going to put up an updated version of them ?

If you think this is the correct way to interact with a lecturer or anyone in a professional capacity, you need to think again.  Email etiquette is important, and will become more important as you move away from university into the workforce. Click here for some guidance on email etiquette.

Here’s a sample of the type of email I like to receive:

Subject line: I’d like you to do/say/write/explain something/meet me/clear something up/etc

BodyHi Barry,
I am emailing you because….

Subject:  A clear, concise and answerable query.  I will not reply to general statements that waffle on, so get to the point!

Regards

Jimmy Malinki.

There is no excuse for poorly worded emails and as such I will just NOT REPLY to any that aren’t written in a concise, respectful and professional manner.

This is my email policy.

In return, I promise to apply the same courtesy to you.

NOTE: I will not respond to queries where I am repeating myself.

The statistical dangers of standard stepwise variable selection

Yesterday I attended the first internal economics research seminar of the academic year and it got me thinking about the above issue.  Most standard financial econometrics textbooks describe stepwise regression in their assessment of multivariate regression model selection, with little regard for its fatal flaws (not true of all textbooks but common in some of the most popular).

In recent years I have been more influenced by the field of Statistics, which has known for some time of the fatal issue that such a method has.

These flaws can be summarised as follows (see Harrell (2010) for detailed proof):

  1. Standard errors are biased towards zero
  2. P-values are also biased towards zero
  3. Parameter estimates are biased away from zero
  4. F and Chi-Squared tests don’t have the desired distribution
  5. R-Squared is biased upwards
  6. Resulting models are complex with exacerbated collinearity problems

These flaws arise due to the fact that a single hypothesis test is ‘wrongly’ applied multiple times under the assumption that consecutive tests are independent.  Flom & Cassell (2007) use a nice analogy to summarise this issue:

In stepwise regression, this assumption is grossly violated in ways that are difficult to determine. For example, if you toss a coin ten times and get ten heads, then you are pretty sure that something weird is going on. You can quantify exactly how unlikely such an event is, given that the probability of heads on any one toss is 0.5. If you have 10 people each toss a coin ten times, and one of them gets 10 heads, you are less suspicious, but you can still quantify the likelihood. But if you have a bunch of friends (you don’t count them) toss coins some number of times (they don’t tell you how many) and someone gets 10 heads in a row, you don’t even know how suspicious to be. That’s stepwise.

Flom & Cassell (2007) go on to provide a number of more statistically valid solutions, my favourite being the Lasso method.

In my Financial Econometrics class I now encourage students to thinking careful when selecting variables for a  model and I encourage students to use Gelman & Hill (2006) general principles for building a model:

 

Copy of Slides:General principles for building a model

 

P. L. Flom and D. L. Cassell, (2007). Stopping stepwise: Why stepwise and similar selection methods are bad, and what you should use. NESUG 2007 Proceedings.

Harrell, F. E. (2010), Regression modeling strategies: With applications to linear models, logistic regression, and survival analysis, Springer-Verlag, New York.

A Gelman & J Hill (2006) “Data analysis using regression and multilevel/hierarchical models” , Cambridge Press, New York.

Trading Movie Classics

An excellent movie about that endangered animal, the pit trader!  It follows a group of Chicago pit traders and the effects of automation on their lives.

see http://flooredthemovie.com for more details.

Other classic trading movies that are a must see are:

Trading places (Clarence Beeks’ classic insider long position at the end of the film is brilliant!)

Wall Street

Boiler Room

Glengarry Glen Ross

(This isn’t an exhaustive list and I will update it as more come to mind)

Any suggestions message me at @baryquinn.