Matt Nolan

The issue of assumptions

/in , , /by

In a recent post, James recently raised an essential, and fascinating, point on assumptions.  To borrow his own words:

Assumptions are often made for tractability, rather than realism, yet still influence our conclusions. It isn’t possible to control for the unrealistic assumptions; if it were we wouldn’t have made them. That means our conclusions will be biased by assumptions we’ve made only for convenience and we need to bear that in mind when considering the policy implications of our models.

This reminded me of an essay by Maki which can be found in “New Directions in Economic Methodology“.  The essay was title “Reorienting the assumptions issue“.

In this essay, Maki does a number of interesting things – but in terms of this specific issue his key insight was to differentiate between “core” and “peripheral” assumptions.  This is an insight we have borrowed many times when talking here on the blog.

A core assumption “constitutes the theory” while a peripheral assumption does not.  What does this mean?  Well it means that the “core” makes up the central set of necessary assumptions required to achieve a certain result!

It is these core assumptions that need to be “realistic” in some sense of the word – while peripheral assumptions are merely there to increase tractability, or make a result easier to interpret.  Fundamentally, our core result should only rely on our core assumptions.

Core assumptions in econometrics

For those who are statistically inclined, this also fits neatly inside our view of econometric theory.  Fundamentally, the assumptions we make about error terms in a regression in econometrics are akin to checks regarding whether we have all the appropriate “core” assumptions for the econometric model and the question we are asking with that model.

For example, we may be trying to explain some independent variable (y) with a set of (presumed to be) exogenous dependent variables (x).  However, it turns out one of these x’s turns out to be correlated the error term – so that this variable is “endogenous“!  If we wanted to estimate the impact of this dependent variable on our independent variable through typical OLS, our estimate will be biased (this is the justification for instrumental variables).  In this case, the model is likely underspecified in some way – such as having missing “core” variables (omitted variable bias), or a missing “causal relationship” (reverse causation between the independent and dependent variables).

A conclusion

As the above example hopefully showed, what dictates a “core” assumption in a model depends strong on what question we are trying to answer with the model!  An analysis of what constitutes “core” assumptions for our analysis, and then a discussion regarding whether these core assumptions correspond to a realistic set of assumptions, should be an essential component of all model building exercises in economics.

jamesz

Does macroeconomics have a right-wing bias?

/14 Comments/in , /by

Noahpinion:

…it’s really hard to make a DSGE model in which government policy plays a useful role in stabilizing the business cycle. By contrast, it’s pretty easy to make a DSGE model in which government plays no useful role, and can only mess things up. So what ends up happening? You guessed it: a macro literature where most papers have only a very limited role for government. …Thus, the conservative slant of modern macro comes not from the weight of evidence, but from the combination of publication bias and the inherent unwieldiness of the DSGE framework.

Update: The comments below make it clear that I should have explained what I think is interesting about this quote, and it’s got nothing to do with DSGE in particular. It is the general point that assumptions are often made for tractability, rather than realism, yet still influence our conclusions. It isn’t possible to control for the unrealistic assumptions; if it were we wouldn’t have made them. That means our conclusions will be biased by assumptions we’ve made only for convenience and we need to bear that in mind when considering the policy implications of our models. For example, if our model assumes perfect competition and our conclusions rely on prices adjusting then we might need to be a little sceptical.

jamesz

The tyranny of positivism

/4 Comments/in , /by

McCloskey:

Anyone who is not a positivist before 25 has no brain; anyone who is still a positivist after age 40 has no heart.
…
[Positivists promote] the tyranny of the lonely genius, seeking by contemplation in his warm room a universal system to impose upon us all.

Read more

jamesz

There is no such thing as an economic historian

/2 Comments/in , /by

Economists often get criticised for trying to emulate physicists by arriving at a set of equations that describe human behaviour. There have been innumerable critiques of that approach and the predictive power of economic models is notoriously poor. This article was written in 1986 but feels as if it could have been written yesterday.

…economics, in view of what it is rather than what it claims to be, is a proper subset of history. …[Economists] are trying to do the same thing as historians, namely, to tell plausible stories about the past. …When done well it has the air of good history written by someone who has taken Differential Equations 152.

Which isn’t to say that we can’t learn from the past. In fact, when you read Matt’s posts about the role of economic forecasters he characterises them as story-tellers rather than oracles. The numbers are inevitably wrong but that is not the economist’s forte and shouldn’t be seen as the useful output of the profession. It is to the detriment of all economists that some members of the profession promulgate the view that we are fortune tellers. As McCloskey says, “if economists go on indulging the misapprehensions of their customers, issuing predictions about next month’s exchange rate of next spring’s interest rate, the loss of reputation when the customers catch on will be large, and richly deserved.”

Matt Nolan

Tarotnomics: Part 1 – The cards

/9 Comments/in , /by

While enjoying the economics at the NZAE conference this year, I felt that, in 2013, I should really submit something.  After a few beers I worked out that my comparative advantage likely lies outside the core of economics – and so I decided that a paper on the economics of tarot card reading was in order.

Now I have written on this issue briefly before, and I have even given the economy a tarot card reading at one point.

With the idea in mind, and motivated by the suggestion at NZAE from Berk Ozler that crowd sourcing papers was a good idea – I’m going to put together the concepts on the blog.  The way I see it, I’m doing the paper in my spare time, and I do the blog in my spare time, so why not mix the two.

As a starting point I want to do something pretty simple – I want to explain broadly what the actual tarot cards are.  Once we have that, we can move on to thinking about readings, and then get an idea of how a tarot card reading represents a type of “model”.  With that in mind, we can work out what attributes of a model this reading has.

Once we’ve then listed down what an economic model is, we can compare and contrast – through this process, we can hopefully shine a light on what economic models represent, how they are useful, the things we have to keep an eye on, and the possible pitfalls.

Note:  If there is anyone around with knowledge about analytical tarot card reading then comments would be much appreciated – especially if you are also well versed in economic methodology, given that’s the direction I’m coming from here.

Read more

Matt Nolan

Clarifying my question on habits

/6 Comments/in , , /by

I was glad that James discussed a bunch of the literature that uses habits and habit persistence yesterday.  I have run into the idea of habit persistence in consumption before while doing macroeconomic modeling, and it was good to see him bring it back to the observed phenomenon of reference dependence in individuals – as I stated, I wasn’t looking for ideas of how to model it directly, more an understanding of “what a habit is in the choice theoretic context”.

Reference dependence does explain a lot of the “why” I was looking for, as does “limited cognitive capacity”.  I think we still need to ask exactly how these processes work though.

And that is why reference dependence does not quite fully cover it off for me – undoubtedly because I am being fussy.  And this comes back to the logic behind why I decided to suggest “a choice of investment in a stock of habit” rather than just suggesting “that habits are described by a state variable that is a function of past action”.

What I really want to know is three-fold:

  1. What is the initial endowment of human habits,
  2. Can choices now relate to habits in the future in a purposeful way,
  3. The Lucas critique – but applied to habits.

Treating a habit like a preference (which is what much of the literature implicitly does) might be sufficient – but I do not believe so.  And that is because I think that many people “choose” to build habits and rules of thumb explicitly, given the underlying endowments and social situation around them.

This is a very important issue when we actually come to look at policy, for example:

  1. If habit formation adjusts to monetary policy settings that assume it, and we have put it in as a constant (eg rule of thumb consumer) then our settings will be inappropriate.
  2. In terms of time inconsistency, the development of habits can be seen as investment into an optimal “time consistent” path to improve outcomes.

My question isn’t “do habits exist” or “do we model habits”.  It is “are we currently modeling the development of habits in a way that is consistent with methodological individualism – that is consistent with individuals that make choice”.  Merely assuming an exogenous preference, doesn’t do this.