Publications - Tom Engsted

Statistisk evaluering af finansielle modeller: Den bayesianske tilgang

Engsted, T. — Mon, 01 Feb 2021 11:17:44 +0100

Er der virkelig 400+ risikofaktorer i aktiemarkedet?

Engsted, T. — Wed, 01 Jan 2020 11:17:44 +0100

Frekvensbaserede vs. bayesianske metoder i empirisk økonomi

Engsted, T. — Wed, 01 Jan 2020 11:17:44 +0100

Likelihoodprincippet og den klassiske p-værdi

Engsted, T. — Wed, 01 Jan 2020 11:17:44 +0100

The Yield Spread and Bond Return Predictability in Expansions and Recessions

Andreasen, M. M., Engsted, T., Møller, S. V., Jensen, M. D. S. — Tue, 01 Jun 2021 11:17:44 +0200

This paper uncovers that expected excess bond returns display a positive correlation with the slope of the yield curve (i.e., yield spread) in expansions but a negative correlation in recessions. We use a macro-finance term structure model with different market prices of risk in expansions and recessions to show that a very accommodating monetary policy in recessions is a key driver of this switch in return predictability.

Bayesianske hypotesetest

Engsted, T. — Tue, 01 Jan 2019 11:17:44 +0100

Disappearing money illusion

Engsted, T., Pedersen, T. Q. — Tue, 21 Aug 2018 11:17:44 +0200

In long-term US stock market data the price-dividend ratio strongly predicts future inflation with a positive slope coefficient up to the mid 1970s. Thereafter, the predictability turns negative. We argue that this phenomenon reflects money illusion that disappears during the 1970s. We develop a consumption-based asset pricing model with recursive preferences and either money illusion or inflation non-neutrality that can explain the predictive patterns. The model is also consistent with a structural shift around the mid 1970s in the real interest rate - inflation relationship, thus supporting the hypothesis of disappearing money illusion at that time.

Frekvensbaserede versus bayesianske metoder i empirisk økonomi

Engsted, T. — Mon, 20 Aug 2018 11:17:44 +0200

Indenfor økonomi og samfundsvidenskab har den klassiske frekvens-baserede analysemetode traditionelt været fremherskende, men de senere år er flere samfundsforskere begyndt at anvende bayesianske metoder i empirisk modellering. I denne artikel beskrives og sammenlignes de to metoder. Der argumenteres for, at vi i højere grad bør anvende den bayesianske tilgang. Den klassiske metode giver sandsynligheden for data, givet modellen (nulhypotesen), mens den bayesianske metode giver sandsynligheden for modellen, givet data. Anvendelse af "p-værdien"i det klassiske hypotesetest fører til for mange "falsk positive" resultater. Den bayesianske metode er mere velegnet end den klassiske til analyse af de hypoteser økonomer arbejder med, hvor en model ikke tilstræbes at være "sand", men i stedet opfattes som en grov approksimation til virkeligheden.

Sådan stopper man højfrekvent handel

Engsted, T., Tanggaard, C. — Sat, 18 Mar 2017 11:17:44 +0100

Bond Market Asymmetries across Recessions and Expansions: New Evidence on Risk Premia

Andreasen, M. M., Engsted, T., Møller, S. V., Jensen, M. D. S. — Mon, 05 Sep 2016 11:17:44 +0200

This paper provides new evidence on bond risk premia by conditioning the classic Campbell-Shiller regressions on the business cycle. In expansions, we find mostly positive intercepts and negative regression slopes, but the results are completely reversed in recessions with negative intercepts and positive regression slopes. We reproduce these coefficients in a term structure model with business cycle dependent loadings in the market price of risk. This model also predicts excess returns in the right direction during expansions and recessions, whereas the Gaussian affine term structure model predicts excess returns for medium- and long-term bonds with the wrong sign during recessions.

The predictive power of dividend yields for future inflation: Money illusion or rational causes?

Engsted, T., Pedersen, T. Q. — Tue, 26 Apr 2016 11:17:44 +0200

In long-term US data the stock market dividend yield is a strong predictor of long-horizon inflation with a negative slope coefficient. This finding is puzzling in light of the traditional Modigliani-Cohn money illusion hypothesis according to which the dividend yield varies positively with expected inflation. To rationalize the finding we develop a consumption-based model with recursive preferences and money illusion. The model with reasonable values of risk aversion and intertemporal elasticity of substitution, and either rational or adaptive expectations, implies significantly negative slope coefficients that increase numerically with the horizon in regressions of future inflation onto the dividend yield, in accordance with the data. A purely rational version of the model with no money illusion, but with a link from expected inflation to real consumption growth, also generates a negative inflation-dividend yield relationship.

Bankpakkernes succes er stærkt forskønnet

Engsted, T. — Fri, 08 Apr 2016 11:17:44 +0200

Morningstar-rapport er fri fantasi

Engsted, T., Tanggaard, C. — Sun, 24 Jan 2016 11:17:44 +0100

Gav EU grønt lys til at fusionere to usunde banker?

Engsted, T., Raaballe, J. — Mon, 14 Dec 2015 11:17:44 +0100

Supplerende pensionsopsparing

Engsted, T., Møller, M., Steffensen, M. — Thu, 01 Jan 2015 11:17:44 +0100

Forord

Engsted, T. — Thu, 01 Jan 2015 11:17:44 +0100

Explosive bubbles in house prices? Evidence from the OECD countries

Engsted, T., Hviid, S. J., Pedersen, T. Q. — Fri, 01 Jan 2016 11:17:44 +0100

We conduct an econometric analysis of bubbles in housing markets in the OECD area, using quarterly OECD data for 18 countries from 1970 to 2013. We pay special attention to the explosive nature of bubbles and use econometric methods that explicitly allow for explosiveness. First, we apply the univariate right-tailed unit root test procedure of Phillips et al. (2015) on the individual countries' price-rent ratio. Next, we use Engsted and Nielsen's (2012) co-explosive VAR framework to test for bubbles. We find evidence of explosiveness in many housing markets, thus supporting the bubble hypothesis. However, we also find interesting differences in the conclusions across the two test procedures. We attribute these differences to how the two test procedures control for cointegration between house prices and rent.

Bobler

Engsted, T. — Fri, 22 May 2015 11:17:44 +0200

Cross-sectional consumption-based asset pricing: A reappraisal

Engsted, T., Møller, S. V. — Thu, 01 Jan 2015 11:17:44 +0100

Predicting returns and rent growth in the housing market using the rent-price ratio: Evidence from the OECD countries

Engsted, T., Pedersen, T. Q. — Thu, 01 Jan 2015 11:17:44 +0100

Fama on Bubbles

Engsted, T. — Fri, 01 Jan 2016 11:17:44 +0100

While Eugene Fama has repeatedly expressed his discontent with the notion of an “irrational bubble,” he has never publicly expressed his opinion on “rational bubbles.” On empirical grounds Fama rejects bubbles by referring to the lack of reliable evidence that price declines are predictable. However, this argument cannot be used to rule out rational bubbles because such bubbles do not necessarily imply return predictability, and return predictability of the kind documented by Fama does not rule out rational bubbles. On data samples that include the 1990s, there is evidence of an explosive component in stock market valuation ratios, consistent with a rational bubble.

Explosive bubbles in house prices? Evidence from the OECD countries

Engsted, T., Hviid, S. J., Pedersen, T. Q. — Tue, 13 Jan 2015 11:17:44 +0100

We conduct an econometric analysis of bubbles in housing markets in the OECD area, using quarterly OECD data for 18 countries from 1970 to 2013. We pay special attention to the explosive nature of bubbles and use econometric methods that explicitly allow for explosiveness. First, we apply the univariate right-tailed unit root test procedure of Phillips et al. (2012) on the individual countries price-rent ratio. Next, we use Engsted and Nielsen's (2012) co-explosive VAR framework to test for bubbles. We find evidence of explosiveness in many housing markets, thus supporting the bubble hypothesis. However, we also find interesting differences in the conclusions across the two test procedures. We attribute these differences to how the two test procedures control for cointegration between house prices and rent.

Aktiv forvaltning er en dødssejler

Tanggaard, C., Engsted, T. — Wed, 29 Oct 2014 11:17:44 +0100

Housing market volatility in the OECD area

Engsted, T., Pedersen, T. Q. — Wed, 01 Jan 2014 11:17:44 +0100

Vector-autoregressive models are used to decompose housing returns in 18 OECD countries into cash flow (rent) news and discount rate (return) news over the period 1970-2011. For the jajority of countries news about future returns is the main driver, and both real interest rates and risk-premia play an important role in accounting for housing market volatility. Bivariate cross-country correlations and principal components analyses indicate that part of the return movements have a common factor among the majority of countries. We explain the results in terms of global changes in credit constraints and transations costs as well as changes in monetary policy over this period. Among other things, our results shed new light on wheather excessively low interest rates by the monetary authorities was a major cause for the housing boom up to 2006.

Fama on bubbles

Engsted, T. — Tue, 02 Sep 2014 11:17:44 +0200

Eugene Fama has repeatedly expressed his discontent with the notion of an irrational bubble. However, he has never publicly expressed his opinion on rational bubbles. This is peculiar since such bubbles build naturally from the rational efficient markets paradigm that Fama strongly adheres to. On empirical grounds Fama rejects bubbles by referring to the lack of reliable evidence that price declines are predictable. However, this argument cannot be used to rule out rational bubbles because such bubbles do not necessarily imply return predictability. On data samples that include the 1990s, there is evidence of an explosive component in stock market valuation ratios, consistent with a rational bubble.

Den finansielle krise i Danmark

Engsted, T., Raaballe, J. — Wed, 01 Jan 2014 11:17:44 +0100

Den finansielle krise i Danmark

Engsted, T., Raaballe, J. — Tue, 10 Jun 2014 11:17:44 +0200

I Finans/Invest nr. 1/14 replicerede Jesper Rangvid på vores indlæg i Finans/Invest nr. 8/13, hvor vi diskuterede udvalgte dele af rapporten fra Udvalget om årsagerne til finanskrisen. Desværre adresserer Rangvid kun enkelte af de spørgsmål, vi stillede i vores første indlæg. Der er fortsat mange uafklarede punkter, som det efter vores opfattelse er nødvendigt at få opklaret, hvis man vil have en dybere forståelse af krisen, som den udfoldede sig i Danmark.

Bias-correction in vector autoregressive models

Engsted, T., Pedersen, T. Q. — Wed, 01 Jan 2014 11:17:44 +0100

We analyze the properties of various methods for bias-correcting parameter
estimates in both stationary and non-stationary vector autoregressive models. First, we show that two analytical bias formulas from the existing literature are in fact identical. Next, based on a detailed simulation study, we show that when the model is stationary this simple bias formula compares very favorably to bootstrap bias-correction, both in terms of bias and mean squared error. In non-stationary models, the analytical bias formula performs noticeably
worse than bootstrapping. Both methods yield a notable improvement over ordinary least squares. We pay special attention to the risk of pushing an otherwise stationary model into the non-stationary region of the parameter space when correcting for bias. Finally, we consider a recently proposed reduced-bias weighted least squares estimator, and we find that
it compares very favorably in non-stationary models.

Anders Grosen - redaktør og samfundsdebattør

Balling, M., Engsted, T., Jakobsen, S., Møller, M., Tanggaard, C. — Wed, 01 Jan 2014 11:17:44 +0100

Nobelprisen i økonomi 2013: Eugene F. Fama, Robert J. Shiller og Lars Peter Hansen

Engsted, T. — Sun, 01 Dec 2013 11:17:44 +0100

Den finansielle krise i Danmark

Engsted, T., Raaballe, J. — Fri, 06 Dec 2013 11:17:44 +0100

Den finansielle krise i Danmark:

Engsted, T., Raaballe, J. — Fri, 06 Dec 2013 11:17:44 +0100

Vi diskuterer finanskriseudvalgets rapport. Der er mange nyttige
informationer i rapporten, og en god beskrivelse/analyse stiller lige så
mange spørgsmål, som den besvarer. Som følge heraf, og i betragtning
af rapportens omfang, har vi i vor diskussion valgt at fokusere på de
områder, der ikke belyses/besvares, og de områder, hvor vi ikke kan
finde et empirisk og/eller logisk belæg for rapportens påstande.

Detailregulering er opskriften på nye kriser

Engsted, T. — Mon, 23 Sep 2013 11:17:44 +0200

Det finansielle system og krisen

Engsted, T., Tanggaard, C., Balling, M. — Tue, 01 Jan 2013 11:17:44 +0100

Malurt i bægeret

Engsted, T., Tanggaard, C. — Thu, 25 Apr 2013 11:17:44 +0200

Bond return predictability in expansions and recessions

Engsted, T., Møller, S. V., Jensen, M. D. S. — Thu, 25 Apr 2013 11:17:44 +0200

We document that over the period 1953-2011 US bond returns are predictable in expansionary periods but unpredictable during recessions. This result holds in both in-sample and out-of-sample analyses and using both univariate regressions and combination forecasting techniques. A simulation study shows that our tests have power to reject unpredictability in both expansions and recessions. To judge the economic significance of the results we compute utility gains for a meanvariance investor who takes the predictability patterns into account and show that utility gains are positive in expansions but negative in recessions. The results are also consistent with tests showing that the expectations hypothesis of the term structure holds in recessions but not in expansions. However, the results for bonds are in sharp contrast to results for stocks showing that stock returns are predictable in recessions but not in expansions. Thus, our results indicate that there is not a common predictive pattern of stock and bond returns associated with the state of the economy.

Housing market volatility in the OECD area: Evidence from VAR based return decompositions

Engsted, T., Pedersen, T. Q. — Thu, 28 Feb 2013 11:17:44 +0100

Vector-autoregressive models are used to decompose housing returns in 18 OECD countries into cash ‡ow (rent) news and discount rate (return) news. Only for two countries - Germany and Ireland - do changing expectations of future rents play a dominating role in explaining housing return volatility. For the majority of countries news about future returns is the main driver, and both real interest rates and risk premia play an important role in accounting for housing market volatility. Bivariate cross-country correlations and principal components analyses indicate that part of the return movements have a common factor among the majority of countries. However, in a minority of countries (Germany, Japan, and the Netherlands) return movements have been basically unrelated to return movements
in other countries.

Derfor skyder økonomerne forbi

Engsted, T. — Wed, 30 Jan 2013 11:17:44 +0100

Predicting returns and rent growth in the housing market using the rent-to-price ratio: Evidence from the OECD countries

Engsted, T., Pedersen, T. Q. — Mon, 17 Dec 2012 11:17:44 +0100

We investigate the predictive power of the rent-to-price ratio for future real estate returns and rent growth in 18 OECD countries over the period 1970 to 2011. First, we document that in most countries returns are signi…cantly predictable by the rent-price ratio. An increase (decrease) in the ratio signals a future increase (decrease) in returns. Second, there are large cross-country di¤erences in how the rent-price ratio predicts rent growth. For some countries the direction of predictability is negative, for other countries it is positive. Third, the predictive patterns are highly dependent on whether returns and rents are measured in nominal or real terms. Finally, there is some evidence of sub-sample instability in the predictive patterns, especially wrt. rent growth predictability. The predictability tests are conducted within a restricted VAR framework based on the dynamic Gordon growth model.This model implies restrictions across the VAR parameters that can be used to construct powerful tests of predictability.

Return predictability and intertemporal asset allocation: Evidence from a bias-adjusted VAR model

Engsted, T., Pedersen, T. Q. — Sun, 01 Jan 2012 11:17:44 +0100

Aktiv vs. passiv forvaltning, held eller dygtighed, og måling af porteføljeforvalteres performance

Engsted, T. — Sun, 01 Jan 2012 11:17:44 +0100

En pengemaskine for bankerne

Engsted, T. — Fri, 17 Jun 2011 11:17:44 +0200

Testing for rational bubbles in a coexplosive vector autoregression

Engsted, T., Nielsen, B. — Sun, 01 Jan 2012 11:17:44 +0100

Pitfalls in VAR based return decompositions: A clarification

Engsted, T., Pedersen, T. Q., Tanggaard, C. — Sun, 01 Jan 2012 11:17:44 +0100

Anbefalinger til den 'almindelige forbruger' om aktieinvesteringer

Engsted, T., Møller, M. — Sat, 01 Jan 2011 11:17:44 +0100

Cross-sectional consumption-based asset pricing: The importance of consumption timing and the inclusion of severe crises

Engsted, T., Møller, S. V. — Sat, 01 Jan 2011 11:17:44 +0100

By using a beginning-of-period timing convention for consumption, and by including the Great Depression years in the analysis, we show that on annual data from 1926 to 2009 a standard contemporaneous consumption risk model goes a long way in explaining the size and value premiums in cross-sectional data that include both the Fama-French portfolios and industry portfolios. A long run consumption risk variant of the model also produces a high cross-sectional …t. In addition, the equity premium puzzle is signi…cantly reduced in the models. We argue that in evaluating consumption based models, it is important to include both boom and crises periods, i.e. periods with severe consumption declines as well as periods with strong growth, and that the standard post-war data sample may not be well suited in this respect.

Bias-correction in vector autoregressive models: A simulation study

Engsted, T., Pedersen, T. Q. — Fri, 13 May 2011 11:17:44 +0200

We analyze and compare the properties of various methods for bias-correcting parameter estimates in vector autoregressions. First, we show that two analytical bias formulas from the existing literature are in fact identical. Next, based on a detailed simulation study, we show that this simple and easy-to-use analytical bias formula compares very favorably to the more standard but also more computer intensive bootstrap bias-correction method, both in terms of bias and mean squared error. Both methods yield a notable improvement over both OLS and a recently proposed WLS estimator. We also investigate the properties of an iterative scheme when applying the analytical bias formula, and we …find that this can imply slightly better fi…nite-sample properties for very small sample sizes while for larger sample sizes there is no gain by iterating. Finally, we also pay special attention to the risk of pushing an otherwise stationary model into the non-stationary region of the parameter space during the process of correcting for bias.

Anbefalinger om aktieinvestering

Engsted, T., Larsen, B. G., Møller, M. — Sat, 08 Jan 2011 11:17:44 +0100

The Log-Linear Return Approximation, Bubbles, and Predictability

Engsted, T., Pedersen, T. Q., Tanggaard, C. — Sun, 01 Jan 2012 11:17:44 +0100

We study in detail the log-linear return approximation introduced by Campbell
and Shiller (1988a). First, we derive an upper bound for the mean approximation
error, given stationarity of the log dividend-price ratio. Next, we simulate various
rational bubbles which have explosive conditional expectation, and we investigate
the magnitude of the approximation error in those cases. We …nd that surprisingly
the Campbell-Shiller approximation is very accurate even in the presence of large
explosive bubbles. Only in very large samples do we …nd evidence that bubbles
generate large approximation errors. Finally, we show that a bubble model in which
expected returns are constant can explain the predictability of stock returns from
the dividend-price ratio that many previous studies have documented.

Spekulative bobler: Kan de identificeres, og hvad skal vi gøre ved dem?

Engsted, T. — Fri, 01 Jan 2010 11:17:44 +0100

Udgivelsesdato: August