2024. Forecasting recessions after the Covid-19 pandemic (with Salvador Ramallo, and Manuel Ruiz). In Oxford Bulletin of Economics and Statistics, forthcoming. Download the paper. Download the R codes that replicate the results. | Abstract.
Due to the economic recession of the COVID-19 pandemic, industrialized
economies recorded in 2020 the biggest quarterly fall and the largest
quarterly rebound in GDP since records began. As a result, the
traditional parametric techniques used to forecast recession
probabilities from GDP data become unsettled by these few but highly
influential observations. This paper proposes a new approach to compute
predictive probabilities of future recessions that is robust to
influential data and other data irregularities. In sum, the method
consists on simulating forecasts of GDP from all the past vectors of
observations of given size, which are embedded into a symbolic space to
weight the forecasts by the probability of the symbols. Using data of
GDP for the G7 countries, we show that our nonparametric proposal
outperforms other linear and nonlinear parametric approaches as
classifiers of future national business cycle phases |
2024. Quantifying the impact: Are coastal areas impoverished by marine pollution? (with Genoveva Aparicio and Mariluz Mate). In Ecological Economics 221: 108213. Download the paper. Download the R codes that replicate the results. | Abstract. We
propose a methodological framework to assess the causal impact of
Harmful Algal Bloom (HAB) events on economic indicators at a
territorial level, with epecial consideration for spatial effects.
Using the Mar Menor region in Spain as a case study, we empirically
apply our framework. Our findings indicate a significantly negative
causal effect of marine pollution resulting from HAB events on income
per capita at the census section level. We observe that this effect is
exacerbated by spatial interactions among neighboring census sections
adjacent to those directly affected by seawater degradation. These
results underscore the importance of implementing effective
environmental regulations to mitigate seawater pollution and proactive
measures to safeguard the well-being of local populations. Our research
provides valuable insights for future studies in similar coastal
regions. |
2024. Does tourism reduce income inequality? (with M.Carmen Ramos-Herrera). In Tourism Economics, forthcoming. Download the paper. | Abstract. We employ a panel Autoregressive Distributed Lag (ARDL)
modeling to address the key question of whether short- and long-run
income distribution equality can be fostered by tourism, conditioning
on a standard set of socio-economic control variables. The Pooled Mean Group (PMG)
estimation on a panel of 120 countries from 1995 to 2020 indicates a
positive impact of tourism on income inequality, leading to increased
inequality in both the long and short run. Interestingly, when we
examine the impact on developed and developing countries separately,
divergent patterns emerge. In the long run, tourism is linked to
reduced inequality in developed countries but increased inequality in
developing countries. In the short run, this effect is positive
regardless of the country type. These results hold true across various
standard measures of income inequality, such as the Gini index, Theil index, Palma ratio, and Atkinson index |
2024. An inquiry into the drivers of an entrepreneurial economy: A Bayesian clustering approach (with Emilio Congregado and Ana Rodríguez-Santiago). In Journal of Evolutionary Economics, forthcoming. Download the paper. | Abstract.
Understanding the worldwide drivers of qualified entrepreneurship is a
key issue in economic policy design. To help policy decisions exert
their intended impact, we aim to cluster a wide range of countries on
the basis of their levels and trends in self-employment productivity
using a finite mixture model applied to a new large dataset of 121
countries covering the period of 1991-2019. Our results point to three
groups of high-, medium-, and low-productive means and tendencies, the
geographical distribution of which suggests that they can be
reinterpreted using the three stages of economic development, namely,
innovation-, efficiency-, and factor-driven economies. Notably, we find
that widespread digitalization and low unemployment enhance the
probability of transitioning into a highly productive cluster. However,
we failed to find that industry weight or employment protection
legislation strictness serve as determinants in the transition between
groups. Suggestive rationales for these results and implications for
the entrepreneurship policy agenda are also provided. |
2023. Econometric methods for business cycle dating (with Lola Gadea). In Oxford Research Encyclopedia of Economics and Finance December 2023: 1-43. Download the paper. Download the codes to replicate the results. | Abstract. Business
cycle dating helps in developing economic analysis and is useful for
economic agents whether they be policy makers, investors or academics.
This paper reviews old and recent research on dating the reference
cycle turning points and is intended as a guide to the applied
researcher. All these methods provide a statistical alternative to
cycle dating committees, although full automatism and researcher’s art
could be complements rather than substitutes in some dating scenarios.
Our survey divides the dating literature into two groups with different
approaches to dating the business cycle from a set of coincident
economic indicators: averagethen-date or date-then average. In both
cases, the dating techniques can be divided into nonparametric and
parametric. The paper shows the theoretical foundations of both types
of techniques and describes in detail the algorithms or estimation
methods necessary for their implementation. Finally, the paper
describes empirical applications of the different methods with data of
different frequencies, trying to show how they work in practice and
pointing out their advantages and disadvantages. This empirical
illustrations include a compilation of the codes in different languages
(R, Matlab or Gauss). In our opinion, future research should focus on
developing methods that are robust to changes in volatility or large
outliers and on exploring the usefulness of big data sources and the
classification ability offered by machine learning methods. |
2023. A dynamic factor model to predict homicides with firearm in the United States (with Maurizio Porfiri, Salvador Ramallo, and Manuel Ruiz). In Journal of Criminal Justice 86: 102051. Download the paper. All data and codes are available at Github. Media coverage: PHSORG. | Abstract. This
study establises a reliable statistical tool to predict homicides with
firearm at a monthly resolution, combining official data and
easy-to-access explanatory variables. Specifically, we propose a
dynamic factor model to predict homicides with firearm from 1999 to
2020 using official monthly data released yearly by the Centers for
Disease Control and Prevention, provisional quarterly data from the
same agencies, media output from newspapers, and crowdsourced
information from the Guns Violence Archive. Our statistical findings
demonstrate that the dynamic factor model outperforms state-of-the-art
techniques (AI and classical autoregressive models). The dynamic factor
model offers improved ability to backcast, nowcast, and forecast
homicides with firearm, and can anticipate sudden changes in the
time-series. |
2023. What drives industrial energy prices? (with Angela Caro and Daniel Peña). In Economic Modelling 120: 106158. Download the paper. Download Matlab codes to replicate the results. | Abstract. Understanding
whether the drivers of industrial energy prices are worldwide,
group-specific or country-specific is a key issue in economics. This
requires flexible econometric models to examine large data sets
containing a significant variety of industrial sectors in different
countries. To this end, we propose an extension of a dynamic factor
model with group structure to account for observable country-specific
explanatory variables and develop Monte Carlo simulations to show its
good finite sample performance. Using data from 12 industrial sectors
in 30 countries during the period from 1995 to 2015, we find three
drivers of energy prices: (i) a common factor, the main driving force,
captures the worldwide dynamics; (ii) country-specific variables,
mainly related to inflation and the use of renewable and waste
resources; and (iii) group-specific factors, which are more related to
country affiliation than to sector classification. |
2023. Factor models for large and incomplete data sets with unknown group structure (with German Lopez-Buenache). In International Journal of Forecasting, 39: 1205-1220. Download the paper. Download R codes to replicate the results. | Abstract.
Most economic applications rely on a large number of time series, which
are typically drawn with a remarkable clustering structure and
available over different spans. To handle these databases, this paper
combines the Expectation-Maximization (EM) algorithm outlined by Stock
and Watson (2002) and the estimation algorithm for large factor models
with an unknown number of group structures and unknown membership
advocated by Ando and Bai (2016, 2017). Several Monte Carlo experiments
are used to show the good performance of the proposal to determine the
correct number of clusters, to provide the right number of
group-specific factors, to identify error-free group membership and to
perform accurate estimates of the unobserved missing data. In addition,
we find that our proposal substantially outperforms the standard EM
algorithm when the data exhibit grouped factor structure. Using
the Federal Reserve Economic Data FRED-QD, our procedure detects two
distinct groups of macroeconomic indicators: the real activity
indicators and the nominal indicators. We illustrate the usefulness of
our group-specific factor model for the study of business cycle
chronology and for forecasting purposes. |
2023. Tourism and GDP short-run causality revisited: a Symbolic Transfer Entropy approach (with Andres Romeu). In Tourism Economics 29: 235-247. Download the paper. Download Matlab codes to replicate the results. | Abstract. We
employ a symbolic transfer entropy panel data test in a large-scale
data set to provide new insights on the worldwide short-term causality
relations between growth and inbound tourists. Using a large data set
on 145 countries from the World Bank Open Data website, we show that,
despite the evidently strong correlation between these two magnitudes,
claiming that the increases in inbound tourists Granger-cause
positive shocks in GDP is not supported by the data. By contrast, the
data seem to point out in the direction of a reverse causality in that
it is GDP growth what drives international inbound tourists in the
short run. |
2022. A new approach to dating the reference cycle. (with Lola Gadea and Ana Gomez-Loscos). In Journal of Business and Economic Statistics 40: 66-81. Working paper n. 1914 at the Central
Bank of Spain series. Download the paper. Download Matlab codes to replicate the results of the US empirical analysis. Download Matlab codes for an application to Spain. | Abstract.
This paper proposes a new approach to the analysis of the reference
cycle turning points, defined on the basis of the specific turning
points of a broad set of coincident economic indicators. Each
individual pair of specific peaks and troughs from these indicators is
viewed as a realization of a mixture of an unspecified number of
separate bivariate Gaussian distributions whose different means are the
reference turning points. These dates break the sample into separate
reference cycle phases, whose shifts are modeled by a hidden Markov
chain. The transition probability matrix is constrained so that the
specification is equivalent to a multiple changepoint model. Bayesian
estimation of finite Markov mixture modeling techniques is suggested to
estimate the model. Several Monte Carlo experiments are used to show
the accuracy of the model to date reference cycles that suffer from
short phases, uncertain turning points, small samples and asymmetric
cycles. In the empirical section, we show the high performance of our
approach to identifying the US reference cycle, with little difference
from the timing of the turning point dates established by the NBER. In
a pseudo real-time analysis, we also show the good performance of this
methodology in terms of accuracy and speed of detection of turning
point dates. |
2021. Evaluating OECD’s main economic indicators at anticipating recessions (with Gonzalo Palmieri). In Journal of Forecasting 40: 80-93. Download the paper. | Abstract.
Using Receiver Operating Characteristic (ROC) techniques, we evaluate
the predictive content of the monthly OECD's main economic indicators
for predicting both growth-cycle and business-cycle recessions at
different horizons. From a sample that covers the 35 OECD countries as
well as for Brazil, China, India, Indonesia, Russian Federation and
South Africa, our results suggest that the indicators perform better at
anticipating business cycles than growth cycles. Although the
performance for OECD and non OECD members is similar in terms of
timeliness, the indicators are more accurate to anticipating recessions
for OECD members. inally, we find that single indicators, such as
interest rates, spreads and credit indicators, perform better than the
compositeeading indicators. |
2021. Symbolic transfer entropy test for causality in longitudinal data (with Andres Romeu and Manuel Ruiz). In Economic Modelling, 94: 649-661. Download the paper. Download Matlab codes to replicate GDP-Expenditures analysis, Firm productivity-size analysis, and Fitch-growth and Fitch-interest rate analyses. | Abstract.
In this paper, we use multiple-unit symbolic dynamics and the concept
of transfer entropy to develop a non-parametric Granger causality test
procedure for longitudinal data. Monte Carlo simulations show that our
test displays the correct size and large power in situations where
linear panel data causality tests fail such as when the linearity
assumption breaks down, when the data generating process is
heterogeneous across the cross-section units or presents structural
breaks, when there are extreme observations in some of the
cross-section units, when the process displays causal dependence in the
conditional variance and when the analysis involves qualitative data.
We illustrate the usefulness of our proposal with the analysis of the
dynamic causal relationships between public expenditure and GDP,
between firm productivity and firm size in US manufacturing sectors,
and among sovereign credit rating, growth and interest rates. |
2021. Price and spatial distribution office rental in Madrid: a decision tree analysis (with Salvador Ramallo and Manuel Ruiz). In Economia 44: 20-40. Download the paper. | Abstract. In
this paper, we assess the drivers office rental prices in the
municipality of Madrid with a sample of 4,721 offices in March, 2020. The
estimation was performed using the decision tree approach, which was
built with a random forest algorithm. This technique allows us to
capture the strong nonlinear component in the relation between price
and its drivers, mainly geospatial location. Through a stratified
analysis, we find that the willingness to pay high rent in the center of
Madrid is a feature of particular relevance to medium-sized offices. For
different reasons, we also find some office clusters located far from the
city center with high rent for both large and small offices. |
2020. The two-speed Europe in business cycle synchronization. (with Angela Caro and German Lopez-Buenache). Download the paper. In Empirical
Economics 59: 1069-1084. Download GAUSS codes to replicate the results. | Abstract.
This paper examines the effect of the financial and sovereign debt
crises on the evolution of the business cycle synchronization among all
the Euro Area members. Combining dynamic factor models with
Markov-switching methodologies, we find that the Euro Area countries
have recovered the level of business cycle synchronization exhibited
before the Great Recession. However, we detect significant differences
across countries in the required time to recover those levels. |
2019. Inference on filtered and smoothed probabilities in Markov-switching autoregressive models. (with Rocio Alvarez and Manuel Ruiz). In Journal of Business and Economic Statistics 37: 484-495. Download the paper. Download Matlab codes to replicate in-sample business cycle analysis, real-time business cycle analysis, and interest rate analysis. | Abstract.
We derive a statistical theory that provides useful asymptotic
approximations to the distributions of the single inferences of
filtered and smoothed probabilities, derived from time series
characterized by Markov-switching dynamics. We show that the
uncertainty in these probabilities diminishes when the states are
separated, the variance of the shocks is low, and the time series or
the regimes are persistent. As empirical illustrations of our approach,
we analyze the U.S. GDP growth rates and the U.S. real interest rates.
For both models, we illustrate the usefulness of the confidence
intervals when identifying the business cycle phases and the interest rate regimes. |
2019. Do economic recessions cause inequality to rise? (with Gonzalo Palmieri). In Journal of Applied Economics 22: 304-320. Download the paper. Download GAUSS codes to replicate the results. | Abstract.
We use a local projection approach to analyze the effect of economic
recessions on income inequality in a comprehensive sample of 43
countries from 1960 to 2016. Although we consider both business-cycle
and growth-cycle recessions, we fail to find evidence of significant
positive impacts of economic downturns on income distribution, once
controls are added to the model. However, we do find important
differences across countries, which mainly depend on the degree of
economic development. |
2019. The propagation of industrial business cycles. (with Danilo Leiva Leon). In Macroeconomic Dynamics 23: 144-177. Working paper n. 2014-48 at the Central
Bank of Canada series Download the paper. Watch media files. | Abstract.
This paper examines the business cycle linkages that propagate
industry-specific business cycle shocks throughout the economy in a way
that (sometimes) generate aggregated cycles. The transmission of
sectorial business cycles is modelled through a multivariate
Markov-switching model, which is estimated by Gibbs sampling. Based on
nonparametric density estimation approaches, we find that the number
and location of modes in the distribution of industrial dissimilarities
change over the business cycle. There is a relatively stable trimodal
pattern during expansionary and recessionary phases characterized by
highly, moderately and lowly synchronized industries. However, during
phase changes, the density mass spreads out from the central part to
the higher end of lowly synchronized industries. |
2019. Inducing Non-Orthogonal and Non-Linear Decision Boundaries in Decision Trees via Interactive Basis Functions (with Antonio Paez, Fernando López, and Manuel Ruiz). In Expert Systems with Applications 122: 183-206. Download the paper. | Abstract.
We use a local projection approach to analyze the effect of economic
recessions on income inequality in a comprehensive sample of 43
countries from 1960 to 2016. Although we consider both business-cycle
and growth-cycle recessions, we fail to find evidence of significant
positive impacts of economic downturns on income distribution, once
controls are added to the model. However, we do find important
differences across countries, which mainly depend on the degree of
economic development. |
2018. Markov-switching dynamic factor models in real time. (with Gabriel
Perez Quiros and Pilar Poncela). In International Journal of Forecasting 34: 598-611. Working paper n. 1205 at the Central
Bank of Spain series and n. 8866 at the CEPR series. Download the paper. Download GAUSS codes to replicate the results. | Abstract.
We extend the Markov-switching dynamic factor model to account for some
of the specificities of the day-to-day monitoring of economic
developments from macroeconomic indicators, such as mixed-sampling
frequency and ragged-edge data. First, we evaluate the theoretical
gains of using promptly available data to compute probabilities of
recession in real time. Second, we show how to estimate the model that
deals with unbalanced panels of data and mixed frequencies and examine
the benefits of this extension through several Monte Carlo simulations.
Finally, we assess its empirical reliability to compute real-time
inferences of the US business cycle and compare it with the alternative
method of forecasting the probabilities of recession from balanced
panels. |
2018. Forecasting travelers in Spain with Google queries. (with Matias Pacce). In Tourism Economics 24: 434-448. Working paper n. 16/21 at BBVA Research. Download the paper | Abstract.
We examine whether Google query trends helps economic agents with
predictions about the checking in and overnight stays of travelers in
Spain in real time. Using a dynamic factor approach and a real-time
database of vintages that reproduces the exact information that was
available to a forecaster at each particular point in time, we show
that the models including query trends outperform models that exclude
these leading indicators. In this way, we aim to contribute to the
literature on the link between the Internet and the tourismmarkets. |
2018. The Great Recession. Worse than ever? (with Lola Gadea and Gabriel
Perez Quiros). In Revista de Economia Aplicada 76: 73:100. Download the paper. Download the MATLAB codes that replicate the results. | Abstract. We
develop an international comparative assessment of the Great Recession,
in terms of the features that characterize the form of the recession
phases, namely length, depth and shape. The potential unobserved
heterogeneity in the international recession characteristics is modeled
by a finite mixture model. Using Bayesian inference via Gibbs sampling,
the model classiffies the Great Recession suffered by a large number of
countries into dfferent clusters, determining its severity in cross
section and time series and dimensions. Our results suggest that the
business cycle features of the Great Recession are not dfferent from
others in an international perspective. By contrast, we show that the
only distinctive feature of the Great Recession wasits unprecedented degree of synchronicity. |
2018. Regional business cycle phases in Spain. (with Matias Pacce and Camilo Ulloa). In Estudios de Economia Aplicada 36: 875–896. Working paper n. 17/20 at BBVA Research. Download the paper. Download media files. | Abstract.
We characterize regional business cycles for Spain using monthly Social
Security affiliations. Based on a set of Markov-switching models, we
find substantial synchronization of regional business cycles, which has
increased since the Great Recession. We do however evidence a regional
leading and lagging performance that repeats itself across the
different recessions. Typically, earlier signals of national recessions
appear in the Islands and Valencia, and are propagated from the
periphery to the center. Moreover, north-western regions tend to start
the regional recoveries with a significant lag. |
2017. Plasticity in leader–follower roles in human teams. (with Maurizio Porfiri, Manuel Ruiz, and Shinnosuke Nakayama. In Scientific Reports 7: Article number 14562. Download the paper | Abstract.
In humans, emergence of leaders and followers is key to group
performance, but little is known about the whys and hows of leadership.
A particularly elusive question entails behavioral plasticity in
leadership across social contexts. Addressing this question requires to
eliminate social feedback between focal individuals and their partners
in experiments that could illuminate the spontaneous emergence of
social roles. We investigated plasticity in leader–follower roles in
cooperation, where members choose the task toward a shared goal, and
coordination, where members adjust their actions in real time based on
social responsiveness. Through a computer-programmed virtual partner,
we demonstrate adaptive plasticity in eader–follower roles. Humans
increased their followership to cooperate when the partner led more in
the choice of the task, whereas they showed only weak leadership when
the partner followed more. We leveraged the information-theoretic
notion of transfer entropy to quantify leadership and followership in
coordination from their movements. When exhibiting stronger
followership in task cooperation, humans coordinated more with the
partner’s movement, with greater information being transferred from the
partner to humans. The evidence of behavioral plasticity suggests that
humans are capable of adapting their leader–follower roles to their
social environments, in both cooperation and coordination.
|
2017. Latin American cycles: What has changed after the Great Recession?. (with Gonzalo Palmieri). In Emerging Markets Finance and Trade 53: 1170–1183. Download the paper. | Abstract.
This paper analyzes the evolution of growth cycles and business cycles
in Latin America from 1980 to 2013 by using monthly industrial
production. Focusing on both synchronization and other cyclical
features, we find evidence of significant cyclical links between the
countries of the region, which seem to be highly integrated in this
period. Notably, we find that the Great Recession did not lead to any
significant impact on the pre-existing Latin American cyclical linkages. |
2016. Aggregate versus disaggregate information in dynamic factor models. (with Rocio Alvarez and Gabriel
Perez Quiros). In International Journal of Forecasting 32: 680-694. Working paper n. 1204 at the Central
Bank of Spain series and
n. 8867 at the CEPR series. Download the paper. Download the electronic appendix. | Abstract.
We examine the finite-sample performance of dynamic factor models that
use aggregate and disaggregate data, when the latter rely on finer
disaggregations of the headline concepts of a small set of economic
categories. Our Monte Carlo analysis reveals that using the series with
largest averaged within-category correlation outperforms using
disaggregate data in factor estimation and forecasting in several
cases. This occurs for high level of cross-correlation across the
idiosyncratic errors of series that belong to the same category, for
oversampled categories, and especially for high persistence either in
the common factor or in the idiosyncratic errors. However, the gains in
forecasting mitigate considerably when the target series are
persistent. This could potentially explain why, using the constituent
balanced panel of the Stock-Watson factor model, whose US data are
classified into 13 economic categories, there is no clear ranking
between the aggregate and disaggregate approaches. |
2016. Country shocks, monetary policy expectations and ECB decisions. A dynamic non-linear approach. (with Danilo Leiva-Leon and Gabriel
Perez Quiros). In Advances in Econometrics 35: 283-316. Working paper n. 1523 at the Central
Bank of Spain series and
n. 10828 at the CEPR series. Download the paper. See voxeu discussion. | Abstract. Previous
studies have shown that the e¤ectiveness of monetary policy depends, to
a large extent, on the market expectations of its future actions. This
paper proposes an econometric framework to address the e¤ect of the
current state of the economy on monetary policy expectations.
Specifically, we study the e¤ect of contractionary (or expansionary)
demand (or supply) shocks hitting the euro area countries on the
expectations of the ECB's monetary policy in two stages. In the first
stage, we construct indexes of real activity and ination dynamics for
each country, based on soft and hard indicators. In the second stage,
we use those indexes to provide assessments on the type of aggregate
shock hitting each country and assess its effect on monetary policy
expectations at different horizons. Our results indicate that
expectations are responsive to aggregate contractionary shocks, but not
to expansionary shocks. Particularly, contractionary demand shocks have
a negative e¤ect on short term monetary policy expectations, while
contractionary supply shocks have negative effect on medium and long
term expectations. Moreover, shocks to different economies do not have
significantly different effects on expectations, although some differences
across countries arise.
|
2015. Extracting nonlinear signals from
several economic indicators. (with Gabriel
Perez Quiros and Pilar Poncela). In Journal of Applied Econometrics 30: 1073-1089. Working paper n. 1202 at the Central
Bank of Spain series and
n. 8865 at the CEPR series. Download the paper. Download the electronic appendix. Download GAUSS codes. | Abstract. We develop a twofold analysis of how the
information provided by several economic indicators can be used in
Markov-switching dynamic factor models to identify the business cycle
turning points. First, we compare the performance of a fully non-linear
multivariate specification (one-step approach) with the "shortcut" of
using a linear factor model to obtain a coincident indicator which is
then used to compute the Markov-switching probabilities (two-step
approach). Second, we examine the role of increasing the number of
indicators. Our results suggest that one step is generally preferred to
two steps, although its marginal gains diminish as the quality of the
indicators increases and as more indicators are used to identify the
non-linear signal. Using the four constituent series of the
Stock-Watson coincident index, we illustrate these results for US data. |
2015. Monitoring the world business cycle. (with Jaime Martinez-Martin). In Economic Modelling 51: 617-625. Working paper n. 15/06 at BBVA Research. Download the paper and n. 228/2015 at Federal Reserve Bank of Dallas. | Abstract.
We propose a Markov-switching dynamic factor model to construct an
index of global business cycle conditions, to perform short-term
forecasts of world GDP quarterly growth in real time and to compute
real-time business cycle probabilities. To overcome the real-time
forecasting challenges, the model accounts for mixed frequencies, for
asynchronous data publication and for leading indicators. Our pseudo
real-time results show that this approach provides reliable and timely
inferences of the world quarterly growth and of the world state of the
business cycle on a monthly basis. |
2015. Toward a more reliable picture of the economic activity: An application to Argentina. (with Marcos dal Bianco and Jaime Martinez-Martin). In Economics Letters 132: 129-132. Download the paper. | Abstract.
We advocate a dynamic factor model to provide alternative measures of
output data using indirect information from economic indicators.
Notably, the method is valid regardless of the length and the frequency
of the indicators used in the analysis. We apply the method to show
evidence of a significant gap between estimated and officialmeasures of Argentine GDP since 2007. |
2015. Can we use seasonally adjusted indicators in dynamic factor models? (with Yuliya Lovcha and Gabriel
Perez Quiros). In Studies in Nonlinear Dynamics and Econometrics 19: 377-391. Working paper n. 1235 at the Central
Bank of Spain series and
n. 9191 at the CEPR series. Download the paper. | Abstract. We examine the short-term performance of
two alternative approaches of forecasting from dynamic factor models.
The first approach extracts the seasonal component of the individual
indicators before estimating the dynamic factor model, while the
alternative uses the non seasonally adjusted data in a model that
endogenously accounts for seasonal adjustment. Our Monte Carlo analysis
reveals that the performance of the former is always comparable to or
even better than that of the latter in all the simulated scenarios. Our
results have important implications for the factor models literature
because they show the that the common practice of using seasonally
adjusted data in this type of models is very accurate in terms of
forecasting ability. Using five coincident indicators, we illustrate
this result for US data. |
2015. Short-Run Forecasting of Argentine GDP Growth (with Marcos dal Bianco and Jaime Martinez-Martin). In Emerging Markets Finance and Trade 51: 473-485. Working paper n. 13/14 at the BBVA Research
Department. Download the paper. | Abstract. We propose a small-scale dynamic factor
model for monitoring Argentine GDP in real time using economic data at
mixed frequencies (monthly and quarterly) which are published with
different time lags. Our model not only produces a coincident index of
the Argentine business cycle in striking accordance with professional
consensus and the history of the Argentine business cycle, but also
generates accurate short-run forecasts of the highly volatile Argentine
GDP growth. By using a pseudo real-time empirical evaluation, we show
that our model produces reliable backcasts, nowcasts and forecasts well
before the official data is released. |
2014. Green shoots and double dips in the Euro area. A real time measure. (with Gabriel
Perez Quiros and Pilar Poncela). In International Journal of Forecasting 30: 520-535. Working
paper n. 1026 at the Central Bank of Spain series and n. 8896 at the
CEPR series. Download the paper. See voxeu discussion. | Abstract. We show that an extension of the
Markov-switching dynamic factor models that accounts for the
specificities of the day to day monitoring of economic developments
such as ragged edges, mixed frequencies and data revisions is a good
tool to forecast the Euro area recessions in real time. We provide
examples that show the nonlinear nature of the relations between data
revisions, point forecasts and forecast uncertainty. According to our
empirical results, we think that the real time probabilities of
recession are an appropriate statistic to capture what the press call
green shoots. | 2014. Real-time forecasting US GDP from
small-scale factor models (with Jaime Martinez-Martin). In Empirical
Economics, 47:347-364. Working paper n. 12/10 at the BBVA Research
Department. Download the paper. | Abstract.
We show that the single-index dynamic factor model developed by Aruoba
and Diebold (AD, 2010) to construct an index of the US business cycle
conditions is also very useful to forecast US GDP growth in real time.
In addition, we adapt the model to include survey data and financial
indicators. We find that our extension is unequivocally the preferred
alternative to compute backcasts. In nowcasting and forecasting, our
model is able to forecast growth as well as AD and better than several
baseline alternatives. Finally, we show that our extension could also
be used to infer the US business cycles very precisely. | 2014. Commodity prices and the business cycle in Latin America: Living and dying by commodities. (with Gabriel
Perez Quiros). In Emerging Markets Finance and Trade 50: 111–137. Working
paper n. 1304 at the Central Bank of Spain series and n. 9367 at the
CEPR series. Download the paper. | Abstract. We analyze the dynamic interactions between
commodity prices and output growth of the seven greatest exporters
Latin American countries: Argentina, Brazil, Colombia, Chile, Mexico,
Peru and Venezuela. Using Markov-switching impulse response functions,
we find that the responses of their respective output growths to
commodity price shocks are time dependent, size dependent and sign
dependent. Overall, the major evidence of asymmetries in output growth
responses occurs when commodity price shocks lead to regime shifts.
Accordingly, the design of optimal counter-cyclical stabilization
policies in this region should take into account that the reactions of
the economic activity vary considerably across business cycle regimes. |
2014. The Euro-Sting revisited: the usefulness of financial indicators to obtain euro area GDP (with Agustin Garcia-Serrador). In Journal of Forecasting 33: 186-197. Working paper n. 11/20 at the BBVA Research
Department. Download the paper. | Abstract. This paper uses an extension of the
Euro-Sting single-index dynamic factor model to construct short-term
forecasts of quarterly GDP growth for the euro area, as also including
financial variables as leading indicators. From a simulated real-time
exercise, the model is used to investigate the forecasting accuracy
across the different phases of the business cycle. In addition, the
model is used to evaluate the relative forecasting ability of the two
most watched business cycle surveys for the eurozone, the PMI and the
ESI. We show that the latter produces more accurate GDP forecasts than
the former. Finally, the proposed model is also characterized by its
great ability to capture the European business cycle, as well as the
probabilities of expansion and/or contraction periods.
|
2013. Short-term forecasting for empirical economists. A survey of the recently proposed algorithms (with Gabriel
Perez Quiros and Pilar Poncela). In Foundations and Trends in Econometrics 6: 101-161. Working
paper n. 1318 at the Central Bank of Spain series. Download the paper. | Abstract. Practitioners do not always use research
findings, sometimes because the research is not always conducted in a
manner relevant to real-world practice. This survey seeks to close the
gap between research and practice on short-term forecasting in real
time. Towards this end, we review the most relevant recent
contributions to the literature, examine their pros and cons, and we
take the liberty of proposing some lines of future research. Among
these models, we include bridge equations, MIDAS, VARs, factor models
and Markov-switching factor models, all allowing for mixed-frequency
and ragged ends. Using the four constituent monthly series of the
Stock-Watson coincident index, industrial production, employment,
income and sales, we evaluate their empirical performance to forecast
quarterly US GDP growth rates in real time. Finally, we review the main
results regarding the number of predictors in factor based forecasts
and how the selection of the more informative or representative
variables can be made.
|
2013. Mixed-frequency VAR models with Markov-switching dynamics. In Economics Letters 121: 369–373. Download the paper. Download GAUSS codes. | Abstract. This paper extends the Markov-switching
vector autoregressive models to accommodate both the typical lack of
synchronicity that characterizes the real-time daily flow of
macroeconomic information and economic indicators sampled at different
frequencies. The results of the empirical application suggest that the
model is able to capture the features of the NBER business cycle
chronology very accurately. |
2012. Short-run forecasting of the euro-dollar exchange rates with economic fundamentals (with Marcos dal Bianco and Gabriel
Perez Quiros). In Journal of International Money and Finance 31: 377-396. Working
paper n. 1203 at the Central Bank of Spain series. Download the paper. | Abstract. We propose a fundamentals-based econometric
model for the weekly changes in the euro-dollar rate with the
distinctive feature of mixing economic variables quoted at different
frequencies. The model obtains good in-sample fit and, more
importantly, encouraging out-of-sample forecasting results at horizons
ranging from one-week to one-month. Specifically, we obtain
statistically significant improvements upon the hard-to-beat random
walk model using traditional statistical measures of forecasting error
at all horizons. Moreover, our model obtains a great improvement with
the direction of change metric, which has more economic relevance. With
this measure, our model performs much better at all forecasting
horizons than a naive model that predicts the exchange rate as an equal
chance to go up or down, these being statistically significant
improvements. |
2012. MICA-BBVA: A factor model of economic and financial indicators for short-term GDP forecasting (with Rafael Domenech). In Journal of the Spanish Economic Association 3: 475-497. Working paper n. 10/21 at the BBVA Research
Department. Download the paper. | Abstract. In this paper we extend the Stock and
Watson’s (1991) single-index dynamic factor model in an econometric
framework that has the advantage of combining information from real and
financial indicators published at different frequencies and delays with
respect to the period to which they refer. We find that the common
factor reflects the behaviour of the Spanish business cycle well and
helps to estimate with high precision the regime-switching
probabilities in line with business cycle phases. We also show that
financial indicators are useful for forecasting output growth,
particularly when certain financial variables lead the common factor.
Finally, we provide a simulated real-time exercise and prove that the
model is a very useful tool for the short-term analysis of the Spanish
Economy.
|
2011. High-growth recoveries, inventories and the Great Moderation (with Gabriel
Perez Quiros and Hugo Rodríguez Mendizabal). In Journal of Economic Dynamics and Control 35: 1322-1339. Working
paper n. 1304 at the Central Bank of Spain series and n. 9367 at the UFAE and IAE series. Download the paper. | Abstract. We present evidence about the loss of the
so-called “plucking effect”, that is, a high-growth phase of the cycle
typically observed at the end of recessions. This result matches the
popular belief, presented informally by different authors, that the
current recession will have permanent effects, or that the current
recession will have an L shape versus the old-time recessions that have
always had a V shape. Furthermore, we show that the loss of the
“plucking effect” can explain part of th eGreat Moderation. We
postulate that these two phenomena may be due to changes in inventory
management brought about by improvements in information and
communications technologies.
|
2011. Spain-STING: Spain Short Term INdicator of Growth (with Gabriel
Perez Quiros). In The Manchester School 79: 594-616. Working
paper n. 0912 at the Central Bank of Spain series. Download the paper. | Abstract. We develop a dynamic factor model to
compute short term forecasts of the Spanish GDP growth in real time.
With this model, we compute a business cycle index which works well as
an indicator of the business cycle conditions in Spain. To examine its
real time forecasting accuracy, we use real-time data vintages from
2008.02 through 2009.01. We conclude that the model exhibits good
forecasting performance in anticipating the recent and sudden downturn.
|
2011. Markov-switching models and the unit root hypothesis in real U.S. GDP. In Economics Letters 112: 161-164. Download the paper. Download GAUSS codes. | Abstract. In this paper, I find that real U.S. GDP is
better characterized as a trend stationary Markov-switching process
than as having a (regime-dependent) unit root. I examine the effects of
both assumptions on the analysis of business cycle features and their
implications for the persistence of the dynamic response of output to a
random disturbance.
|
2010. Introducing the EURO-STING: Short Term INdicator of Euro Area Growth (with Gabriel
Perez Quiros). In Journal of Applied Econometrics 25: 663-694. Working
paper n. 0807 at the Central Bank of Spain series and n. 7343 at the CEPR series. Download the paper. | Abstract. We propose a model to compute short-term
forecasts of the Euro area GDP growth in real time. To allow for
forecast evaluation, we construct a real-time data set that changes for
each vintage date and includes the exact information that was available
at the time of each forecast. In this context, we provide examples that
show how data revisions and data availability affect point forecasts
and forecast uncertainty.
|
2009. Income distribution changes across the 1990s expansion: the role of taxes and transfers (with Aida Galiano). In Economics Bulletin 29: 3177-3185. Download the paper. | Abstract. We analyze the redistributive impact of the
1990s expansion in US, UK, France, Germany, Italy, and Spain by
evaluating the income distribution changes over the trough-peak years
that determine the expansionary period in these countries. Our
empirical strategy separates between market-driven changes affecting
income distribution and the role of government interventions through
taxes and transfer payments. Overall, the Euro-area tax and transfer
system plays a crucial role in offsetting the market-driven poverty and
inequality evolutions. However, government interventions reduce the
equalitarian effect of the market in UK, and aggravate the
market-driven inequality in US.
|
2008. Do European business cycles look like one? (with Gabriel
Perez Quiros and Lorena Saiz). In Journal of Economic Dynamics and Control 32: 2165-2190. Working
paper n. 0518 at the Central Bank of Spain series. Download the paper. | Abstract. This paper provides a comprehensive
framework to analyze business cycle features other than
synchronization. We use stationary bootstrap and model-based clustering
methods to analyze similarities and differences among the European
cycles. We find evidence that the length, deep and shape of cycles
differ across European countries and that these differences are not
decreasing over time. Finally, even though we find some correlation
between business cycle synchronization and characteristics, there is
important information in the characteristics that is not captured by
the synchronization measures.
|
2008. TAR panel unit root tests and real convergence: an application to the EU enlargement process (with Arielle Beyaert). In Review of Development Economics 12: 668-681. Download the paper. Download GAUSS codes. | Abstract.
We propose a new panel data methodology to test real convergence in a
non-linear framework. It extends the existing methods by combining
three approaches: the threshold model, the panel data unit root tests
and the computation of critical values by bootstrap simulation. We
apply our methodology on the per-capita outputs of a total of fifteen
European countries, including some of the East-European countries that
have recently joined.
|
2008. Determinants of Japanese Yen Interest Rate Swap Spreads: Evidence from a Smooth Transition Vector Autoregressive Model (with Carl R. Chen and Ying Huang). In Journal of Futures Markets 28: 82-107. Download the paper. | Abstract. This paper investigates the determinants of
variations in the yield spreads between Japanese yen interest rate
swaps and Japan government bonds for a period from 1997 to 2005. A
smooth transition vector autoregressive (STVAR) model and generalized
impulse response functions are used to analyze the impact of various
economic shocks on swap spreads. The volatility based on a GARCH model
of the government bond rate is identified as the transition variable
that controls the smooth transition from high volatility regime to low
volatility regime. The break point of the regime shift occurs around
the end of the Japanese banking crisis. The impact of economic shocks
on swap spreads varies across the maturity of swap spreads as well as
regimes. Overall, swap spreads are more responsive to the economic
shocks in the high volatility regime. Moreover, volatility shock has
profound effects on shorter maturity spreads, while the term structure
shock plays an important role in impacting longer maturity spreads. Our
results also show noticeable differences between the non-linear and
linear impulse response functions.
|
2007. Jump-and-rest effect of U.S. business cycles (with Gabriel
Perez Quiros). In Studies in Nonlinear Dynamics and Econometrics Vol. 11: No. 4, Article 3. Working
paper n. 0507 at the Central Bank of Spain series and n. 4975 at the CEPR series. Download the paper. | Abstract. One of the most familiar empirical stylized
facts about output dynamics in the United States is the positive
autocorrelation of output growth. This paper shows that positive
autocorrelation can be better captured by shifts between business cycle
states rather than by the standard view of autoregressive coefficients.
The result is extremely robust to different nonlinear alternative
models and applies not only to output but also to the most relevant
macroeconomic variables.
|
2006. Are European business cycles close enough to be just one? (with Gabriel
Perez Quiros and Lorena Saiz). In Journal of Economic Dynamics and Control 30: 1687-1706. Working
paper n. 0408 at the Central Bank of Spain series and n. 4824 at the CEPR series. Download the paper. | Abstract. We propose a comprehensive methodology to
characterize the business cycle comovements across European economies
and some industrialized countries, without imposing any given model but
trying to "leave the data speak". We develop a novel method to show
that there is no evidence of a "European economy" that acts as an
attractor to the other economies of the area. We show that the
establishment of the Monetary Union has not significantly increased the
level of comovements across Euro-area economies. Finally, we are able
to explain an important proportion of the distances across their
business cycles using macro-variables related to the structure of the
economy, to the directions of trade, and to the size of the public
sector. |
2006. A useful tool for forecasting the Euro-area business cycle phases (with Pilar Bengoechea and Gabriel
Perez Quiros). In International Journal of Forecasting 22: 735-749. Download the paper. Download GAUSS codes. | Abstract. Based on a novel extension of existing
multivariate Markov-switching models, we provide the reader with a
useful tool to analyze current business conditions and to make
predictions about the future state of the Euro-area economy in real
time. Apart from the Industrial Production Index, we find that the
European Commission Industrial Confidence Indicator, that is issued
with no delay, is very useful to construct the real-time predictions. |
2006. A new framework to analyze business cycle synchronization (with Gabriel
Perez Quiros). In: Milas, C., Rothman, P., and van Dijk,
D. Nonlinear Time Series Analysis of Business Cycles. Elsevier's
Contributions to Economic Analysis series. Chapter 5 (pp. 133-149). Elsevier, Amsterdam. Download the paper . Download GAUSS codes. | Abstract. In this paper, we propose a new framework
to analyze pairwise business cycle synchronization across a given set
of countries. We show that our approach, that is based on multivariate
Markov-switching procedures, lead to more confident results than other
popular approaches developed in the literature. According to recent
findings, we show that the G7 countries seem to exhibit two
differentiated "Euro-zone" and "English-speaking" business cycles
dynamics. |
2005. Markov-switching stochastic trends and economic fluctuations. In Journal of Economic Dynamics and Control 29: 135-158. Download the paper. Download GAUSS codes. Download GAUSS codes for linear common trends (Warne, 1993) | Abstract. I investigate cointegrating relationships
such that, even though the long-run attractors are assumed to be
linear, the dynamics of the equilibrium errors depends on the business
cycle. I postulate a Markov-switching stochastic trends model to study
both the short-run responses to permanent shocks and the effects of
severe recessions in the long-run growth. I apply these findings to
explore the short-run and long-run asymmetric relationships among
output, consumption and investment. |
2004. Vector Smooth Transition Regression Models for US GDP and the Composite index of Leading Indicators. In Journal of Forecasting 23: 173-196. Download the paper. Download GAUSS codes. | Abstract. In this paper, I extend to a
multiple-equation context the linearity, model selection, and model
adequacy tests recently proposed for univariate Smooth Transition
Regression models. Using this result, I examine the nonlinear
forecasting power of the Conference Board Composite index of Leading
Indicators to predict both output growth and the business-cycle phases
of the U.S. economy in real time. | 2003. Spanish diffusion indexes (with Israel Sancho). In Spanish Economic Review 5: 173-203. Download the paper. Download the data and the GAUSS codes. | Abstract. We use the Stock-Watson diffusion index
methodology to summarize the information contained ina wide set of
monthly series (published in the Statistical Bulletin of the Bank of
Spain) by menas of a reduced number of facors. We find that the first
two factors may be used as indicators of the core inflation and the
business cycle dynamics of the Spanish economy, respectively. In
addition, we study the effects of incorporating large information sets
for the analysis of monetary policy. Finally, we show that forecasting
prices and output with our factors outperforms other standard
alternative forecasting procedures.
|
2002. This is what the leading indicators lead (with Gabriel
Perez Quiros). In Journal of Applied Econometrics 17: 61-80. Working
paper n. 27 at the European Central Bank series. Download the paper. Download GAUSS codes. See Economist's view discussion. | Abstract. We propose an optimal filter to transform
the Conference Board Composite Leading Index (CLI) into recession
probabilities in the US economy. We also analyze the CLI's accuracy at
anticipating US output growth. We compare the predictive performance of
linear, VAR extensions of smooth transition regression and switching
regimes, probit, nonparametric models and conclude that a combination
of the switching regimes and nonparametric forecasts is the best
strategy at predicting both the NBER business cycle schedule and GDP
growth. This confirms the usefulness of CLI, even in a real-time
analysis. |
|