"Why So Glum? The Meese-Rogoff Methodology Meets the Stock Market"

This has received quite a bit of attention already, though I did try to add something new at the end with a discussion of some recent work by Bob Flood and Andrew Rose, but in case you missed it this is Menzie Chinn on modeling exchange rates. I won't repeat the entire post, but here's part of it followed by a description of the new work by Flood and Rose (which has a very nice description of the impact of the Messe-Rogoff paper discussed below):

Modeling Exchange Rates: What Does Current Academic Thinking Have to Say about the Dollar's Future?, by Menzie Chinn: As the dollar continues its decline, I think it's useful to step away from the high frequency analysis [1],[2], to consider what the currents in academic thinking on the enterprise of predicting exchange rates are. ...

Now, as I've observed before, one of the key stylized facts regarding the empirical modeling of exchange rates is the one associated with Meese and Rogoff's 1983 paper: that it is difficult to outpredict a random walk in out of sample forecasts where the ex post values of the explanatory variables are used (what are sometimes called ex post historical simulations).

This stylized fact has been remarkably durable in its 20 year history. After some work which seemed to indicate that one could outpredict a random walk at long horizons (Mark (1995) [pdf] and Chinn and Meese (1995) [pdf]), subsequent research demonstrated that this long horizon outprediction was an artifact of sample period, at least insofar as RMSE criteria are concerned. Cheung, Chinn and Fujii (2003) [pdf] showed that at long horizons, one could find cases where the random walk was outpredicted at long horizons using interest rate parity, but not (typically) structural macro models of the type examined by Meese and Rogoff.

One path has been undertaken by Roman Frydman and Michael Goldberg, where they have dispensed with the rational expectations approach, and forwarded what they call the "imperfect knowledge expectations". In a recent paper [pdf], they explain their approach thusly:

Why do academic economists believe that short-run currency fluctuations are not connected to macroeconomic fundamentals, whereas the individuals most connected to financial markets obviously do? Our answer is that market participants and observers recognize that the relationship between the exchange rate and macroeconomic fundamentals changes at times and in ways that cannot be fully foreseen. While they may use economic theory to understand and forecast markets, they recognize that they cannot base their actions solely on a fixed model. ...

The basic premise of our approach, called "imperfect knowledge economics" (IKE), is that the search for sharp predictions of market outcomes is futile. Market participants and policy makers must cope with ever-imperfect knowledge in forecasting the future exchange rate. As a result, our knowledge and our institutions (e.g., the conduct of monetary policy) change over time. Indeed, capitalist economies provide powerful incentives for individuals to find new ways of thinking about the future and the past. In such a world, it is rather odd for economists to expect that a fixed set of economic fundamentals would matter in exactly the same way for more than 30 years, or that they could fully prespecify how this relationship might have changed over time.

It is thus not surprising that academic economists have found that their models forecast exchange rates no better than flipping a coin does. This finding still attracts much attention among academic researchers. Indeed, it is one of the main reasons why they have concluded that markets participants' irrationality, rather than macroeconomic fundamentals, moves currency markets. ...

...Given that some of my own research suggests nonlinearities in exchange rates [pdf], and changes in what factors traders consider important [pdf], I'm sympathetic to some of the ideas Frydman and Goldberg propound. At the same time, I should observe that a quite different approach to thinking about exchange rates adheres to the rational expectations view -- and indeed takes the inability of typical exchange rate determinants to predict the exchange rate as proof that the rational expectations/present value approach is correct. This approach, developed by Engel and West [pdf], was discussed in this post. [See] a paper provocatively titled Exchange Rate Models Are Not as Bad as You Think [by]... Engel, Mark, and West...

Perhaps more interesting is some recent work by Engel and West, as well as Molodtsova and Papell, suggesting that Taylor rule fundamentals (namely output and inflation gaps) can be used as predictors of exchange rates. I discussed this point in this post from January. ...

What I take from this discussion is that some of the movements in the dollar are explicable in terms of fundamentals. The fundamentals that matter differ depending upon the horizon, with perhaps Taylor rule fundamentals (and consequently revisions to expectations regarding those fundamentals) driving the exchange rate at short horizons. ...

I also think conventional monetary model fundamentals matter at longer horizons. These include money stocks, incomes, interest rates and inflation rates, and possibly the relative price of nontradables (this is where productivity trends can come into play). This predictability might not be seen in the RMSE criteria typically used, but sometimes shows up in direction of change statistics.

But, traveling full-circle, I want to stress that these factors overlay the structural factors ... that are in some sense harder to model. Will central banks change the pace of dollar acquisition...? ... What will sovereign wealth funds do? What are investors' views regarding the substitutability of dollar denominated assets versus euro or pound denominated assets? Because some of these questions pertain to infrequent, discrete, events (de-pegging from the dollar), or to relatively new phenomena (SWFs), or to imperfectly measured relationships (investor perceptions of substitutability), one should expect much greater uncertainty surrounding the effects of these structural changes.

This assessment is consistent a view I forwarded (along with others) two years ago. In a Council on Foreign Relations report [pdf], I argued that one of the implications of happily borrowing away at the Federal and national levels (the budget deficit and the current account deficit) was that, given the source of the funding, we would place the fate of the dollar and other asset prices to some extent in the hands of foreign, state, actors. Current events have, I think, vindicated that view.

Let me try to add something to Menzie's discussion. There is a recent paper by Flood and Rose that places a new interpretation on the Meese-Rogoff results. The Flood-Rose paper doesn't revive exchange rate models, but it does show that if you apply the Meese-Rogoff result to other assets, e.g. to stock prices, you get exactly the same result again and again. This suggests, and the paper verifies, that there may be something about the econometric technique that builds the Meese-Rogoff outcome into the results and, because of that, care needs to be taken in interpreting the results from the Meese-Rogoff procedure. In particular, the results appear to rely upon persistence in the model's error term:

“Why So Glum?  The Meese-Rogoff Methodology Meets the Stock Market”, by Andrew Rose and Robert Flood [PDF file]: I. Motivation In their now-classic (1983a, b) papers, Richard Meese and Kenneth Rogoff (hereafter “MR”) examined the forecasting performance of a number of then-popular exchange rate models. They found that a random walk “model” of the exchange rate consistently out-forecast the structural models, despite the latter’s being given the advantage of using actual future values of market fundamentals. The full reaction to the MR message took years to process, but was eventually devastating for the field of International Finance. Academic modeling of exchange rate determination basically ceased. The area fell into disrepute; indeed, the area is not even represented on many first-rate academic faculties. By academic standards the MR paper had a huge impact and its fallout is still felt whenever exchange rates are intelligently discussed. In the current paper we ask a simple question: What happens when the MR method is applied to assets other than foreign exchange? We consider aggregate stock market indices in Germany, Japan, the UK and the USA, countries that correspond to the bilateral exchange rates considered by MR. We carry out the same forecasting analysis as MR, over the same sample period, 1973m3 through 1981m6. Just as MR did for foreign exchange rates, we consider a number of time-series and structural models, and use a number of metrics to compare them out of sample with a random walk. Crucially, we follow MR in allowing structural models to forecast asset prices with actual future values of fundamentals (which would ordinarily be unknown). Where MR forecast exchange rates with money, income, and the like, we provide the forecaster with information about the levels and growth rates of earnings, dividends, and interest rates. It turns out that not only is our methodology similar to that of MR; so is our conclusion. Just as MR found with foreign exchange, we find that none of our models with fundamentals perform consistently and substantially better than a simple random walk model of the aggregate stock market. However, we also show that this may be an artifact of the Meese-Rogoff methodology. In particular, the technique seems to hinge inadvertently on the time-series persistence of the model’s error term.

VI. Conclusion

• International finance is in no worse shape at modeling important asset prices than domestic finance, at least over the MR sample period.
• The Meese-Rogoff methodology may not be revealing for any asset price, especially with a lot of persistence in the composite residual.
• Fundamentals may eventually seem to kick in, but not at any short horizon. Most of the finance literature is at longer horizons than one year (e.g., Fama and French). Alternatively, coefficients linking fundamentals to stock prices may not be reasonably viewed as constant at the short run. Alternatively, lots of variation in discount rates.

Comments

[hari]

The problem with current subprime crisis and ensuing credit crunch has created a totally different palying field which are being manipulated by insiders with knowledge of the derivatives market.

Politcal economy has already takenover, as I read it.

Econometric models become irrelevant, in final analysis, when the MOB takeover the market! Or?

Models will not predict devaluation of US$ down to Euro 2 or even 3...principally because it's unrealistic and may be illogical.

But markets have shown their intrinsic capacity to melt and - like tides - we may be faced with a tidal wave...

[paine]

i find the nuts of this
quite intuitively obvious
don't you ???

and since
i like logical constructions
that defy my intuitions
i find both efforts reported here
not very helpful

imagine after all
his lovely jargon hops
my beloved
mad science chinn

adds this squelcher

"But, traveling full-circle, I want to stress that these factors overlay the structural factors ... that are in some sense harder to model. Will central banks change the pace of dollar acquisition...? ... What will sovereign wealth funds do? "

looking at blah blah noticing blah
we hence can deduct blah
but
errr then of course there's the CBs.....

and that's a whole 'nother level of causations
we can't model anyway so ....

or
roseflood's hardy har har har

"In particular,
the technique (rm's)
seems to hinge inadvertently
on the time-series persistence
of the model’s error term "

we have discovered the parent hood
of the rm kibosh twins

they like lots of other dramatic seeming results
are just
the bastard kids of
the model's own f in' assumptions

but here's a news flash:

forex markets
after all and a day
are just
"security " markets

i'm underwhelmed sports fans

when models battle the randomizer
and flush out
only their design
that's not seeing faces for clouds
that's seeing clouds for faces

get back to work
you quant drunk peons !!!!!

[paine]

"Politcal economy has already takenover, as I read it."

ain't it always doin such
..great line

[Bruce Wilder]

Using a pocket calculator to check the accuracy of a network of supercomputers would certainly seem to present challenging methodological problems. I wish them luck.