Yield Curves: Bridging the P-Q Modeling Divide

Check it out:

"Bridging the P-Q Modeling Divide with the Factor-HJM Modeling Framework"
by
Andrei Lyashenko and Yevgeny Goncharov.

https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3995533

Really nice work.

I chuckled when I noticed that it characterizes a significant part of its contribution as solving the "mystery behind the very peculiar form of the mean reversion matrices" used to produce the arbitrage-free Nelson-Siegel (AFNS) yield-curve model of Christensen, Diebold and Rudebusch (CDR:  2009, 2011).  Of course the CDR mean reversion matrices are not "peculiar" in any negative sense, but they are definitely special, delivering precisely what is needed to enforce absence of arbitrage.  Admittedly, we may have presented them as if pulled from a hat.  In fact we arrived at them by reverse engineering, that is, by the venerable (and iterative) strategy of "guess and verify".  

The new Lyashenko-Goncharovnew paper arrives at the CDR mean reversion matrices in a more constructive fashion, in an impressively broad and unifying framework that bridges dynamic factor yield curve models, Heath-Jarrow-Morton forward curve models, and Duffie-Kan affine arbitrage-free models.  In so doing, it further cements the central status of AFNS, now transcending sub-disciplines.

An RCT for the new year

Happy New Year to all!  Let's kick it off with some humor.  Here's some great RCT reading:

"Parachute use to prevent death and major trauma related to gravitational challenge: systematic review of randomised controlled trials"

Abstract

Objectives To determine whether parachutes are effective in preventing major trauma related to gravitational challenge.

Design Systematic review of randomised controlled trials.

Data sources: Medline, Web of Science, Embase, and the Cochrane Library databases; appropriate internet sites and citation lists.

Study selection: Studies showing the effects of using a parachute during free fall.

Main outcome measure Death or major trauma, defined as an injury severity score > 15.

Results We were unable to identify any randomised controlled trials of parachute intervention.

Conclusions As with many interventions intended to prevent ill health, the effectiveness of parachutes has not been subjected to rigorous evaluation by using randomised controlled trials. Advocates of evidence based medicine have criticised the adoption of interventions evaluated by using only observational data. We think that everyone might benefit if the most radical protagonists of evidence based medicine organised and participated in a double blind, randomised, placebo controlled, crossover trial of the parachute.

• Gordon C S Smith, Jill P Pell
•  https://doi.org/10.1136/bmj.327.7429.1459
• 
  

Glenn Rudebusch Leaves FRBSF

So now it's public.  Glenn Rudebusch, arguably the best researcher in a 25-year span at the Federal Reserve Bank of San Francisco (FRBSF), and indeed in the entire Federal Reserve System, is "leaving".  (Check him out on Google Scholar.)  A year and a half ago FRBSF was sponsoring a conference in his honor, yet now, inexplicably, he is departing.  Not sure what happened in the interim, except his founding and leading FRBSF's highly-influential Virtual Seminar on Climate Economics and related urgently-needed climate initiatives.  Perhaps the seminar, and his path-breaking climate research more generally, were too hot for some to handle (also see here).  I’m certain that Glenn will do more great research as a visiting scholar somewhere, continuing to integrate issues related to climate change into macroeconomics, finance, and policy.

Improved Forecasts from Imperfect Models

 Better the Devil You Know: Improved Forecasts from Imperfect Models

by Dong Hwan Oh and Andrew J. Patton

Cool paper from Oh and Patton.  https://www.federalreserve.gov/econres/feds/files/2021071pap.pdf

Interesting to me in part because, when I consider how I would approach their problem, I have some ideas that might work well, but my ideas differ from theirs (it seems).  So the paper made me think a lot, which is good.

Not unrelated, the paper introduced me to the stat literature on local likelihood, like:

Fan, J. Y. Wu and Y. Feng, 2009, Local quasi-likelihood with a parametric guide, Annals of Statistics, 37(6B), 4153-4183

         Fan, J., M. Farmen and I. Gijbels, 1998, Local maximum likelihood estimation and inference,                 Journal of the Royal Statistical Society, Series B, 60(3), 591-608

Hu, F. and J. V. Zidek, 2002, The weighted likelihood, Canadian Journal of Statistics, 30(3), 347-371

Tibshirani, R. and T. Hastie, 1987, Local likelihood estimation, Journal of the American Statistical Association, 82(398), 559-567,

which feeds into the paper's key econometrics ancestors like:

Dendramis, Y., G. Kapetanios and M. Marcellino, 2020, A similarity-based approach for macroeconomic forecasting, Journal of the Royal Statistical Society, Series A, 183(3), 801-827

Kristensen, D. and A. Mele, 2011, Adding and subtracting Black-Scholes: A new approach toapproximating derivative prices in continuous-time models, Journal of Financial Economics,102, 390-415.

Ed George Conference

Last weekend's "Ed George Conference", Perspectives in Statistical Modeling and Inference, not only celebrated Ed's myriad contributions, but also showcased some really interesting new research results.  My favorite talks were Dean Foster's and Jun Liu's.  See "Schedule" at https://jh-cai.com/edgeorge70.