Output Fluctuations in the United States: What Has Changed since Early 1980's? by Margaret M. McConnell and Gabriel Perez-Quiros. Published volume 90, issue 5, pages 1464-1476 of American Economic Review, December 2000

Recent imperfect capital market theories predict the presence of asymmetries in variation small and large firms' risk over economic cycle. Small firms with little collateral should be more strongly affected by tighter credit conditions a recession state than large, better collateralized ones. This paper adopts flexible econometric model to analyze these mplications empirically. Consistent theory, display highest degree asymmetry their across expansion states, which translates into higher...

We document a structural break in the volatility of U.S. GDP growth first quarter 1984, and provide evidence that this emanates from reduction durable goods production. find no increased stability nondurables, services or structures sectors economy. In addition, other G7 country experienced contemporaneous output volatility. Finally, we show durables corresponds to decline share accounted for by inventories.

Abstract We set out a model to compute short‐term forecasts of the euro area GDP growth in real time. To allow for forecast evaluation, we construct real‐time dataset that changes each vintage date and includes exact information was available at time forecast. With this show our simple factor algorithm, which uses an easy‐to‐replicate methodology, is able as well professional forecasters who can combine best forecasting tools with possibility incorporating their own judgement. In context,...

We analyze the dynamic interactions between commodity prices and output growth of seven biggest Latin American exporters: Argentina, Brazil, Chile, Colombia, Mexico, Peru, Venezuela. Using a novel definition Markov-switching impulse response functions, we find that each country's to price shocks is time dependent, size sign dependent. The major evidence asymmetries in responses occurs when lead regime shifts. Thus, conclude design optimal countercyclical stabilization policies should...

The authors find that the composite leading index (CLI) is useful for forecasting gross national product (GNP), both in sample and an out-of-sample real-time exercise. They propose a nonlinear specification which cyclical shifts of CLI precede those GNP. However, better forecasts are provided by simple linear relation between current GNP growth rate during previous quarter along with error-correction term corresponding to quarter's logarithmic difference level Copyright 1996 University Chicago Press.

We extend the Markov-switching dynamic factor model to account for some of specifi cities day-to-day monitoring economic developments from macroeconomic indicators, such as ragged edges and mixed frequencies. examine theoretical benefi ts this extension corroborate results through several Monte Carlo simulations. Finally, we assess its empirical reliability compute real-time inferences US business cycle.

We examine the finite-sample performance of small versus large scale dynamic factor models. Our Monte Carlo analysis reveals that models out-perform in estimation and forecasting for high levels cross-correlation across idiosyncratic errors series belonging to same category, oversampled categories and, especially, persistence either common or errors. Using a panel 147 US economic indicators, which are classified into 13 categories, we show model uses one representative indicator each...

Many have argued that the Great Recession of 2008 marked end Moderation eighties and nineties. Through painstaking empirical analysis data, this paper shows is not case. Output volatility remains subdued despite turmoil created by Recession. This finding has important implications for policymaking since lower output (the hallmark Moderation) associated with weaker recoveries.

During the last crisis, developed economies' sovereign Credit Default Swap (hereafter CDS) premia have gained in importance as a tool for approximating credit risk. In this paper, we fit dynamic factor model to decompose CDS spreads of ten OECD economies into three components: common factor, second driven by European peripheral countries and an idiosyncratic component. We use decomposition propose novel methodology based on real-time estimates characterize contagion among series. Our...

This Staff Discussion Note reflects on the potential, challenges, and implications of big data for macroeconomic financial statistics.It addresses wide range stakeholders "official" statistics covers interested users producers.Good statistics, strategic elements any society economy, are essential sound policy decision making in both private public sector.By now, many companies as well national international organizations see that "big data" is no mere buzzword, but a medium-term concept...

Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI

This paper shows that the existence of deposit and lending facilities combined with an averaging provision for reserve requirement are powerful tools to stabilize overnight rate. We reach this conclusion by comparing behavior rate in Germany before after start EMU. The analysis German experience allows us isolate effects on these particular instruments monetary policy. To illustrate outcome is a general not result market, we develop theoretical model management, which able reproduce our...

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 real-time data set that changes each vintage date and includes exact information was available at time forecast. In this context, provide examples show how revisions availability affect point uncertainty.

Practitioners do not always use research findings, as the is conducted in a manner relevant to real-world practice. This survey seeks close gap between and practice respect of short-term forecasting real time. To this end, we review most recent contributions literature, examining their pros cons, take liberty proposing some avenues future research. We include bridge equations, MIDAS, VARs, factor models Markov-switching models, all allowing for mixed-frequency ragged ends. Using four...

Should rational agents take into consideration government policy announcements? A skilled agent (an econometrician) could set up a model to combine the following two pieces of information in order anticipate future course fiscal real-time: (i) ex-ante path as published/announced by government; (ii) incoming, observed data on actual degree implementation ongoing plans. We formulate and estimate empirical models for number EU countries (Germany, France, Italy Spain) show that (consumption)...

We propose a fundamentals-based econometric model for the weekly changes in euro-dollar rate with distinctive feature of mixing economic variables quoted at different frequencies. The obtains good in-sample fit and, more importantly, encouraging out-of-sample forecasting results horizons ranging from one week to month. Specifically, we obtain statistically significant improvements upon hard-to-beat random walk using traditional statistical measures error all horizons. Moreover, our improves...

Much has been written about why economists failed to predict the latest financial and real crisis. Reading recent literature, it seems that crisis was so obvious must have blind when looking at data not see coming. In this paper, we analyze whether such claims are justified by one of most cited relevant variables in analysis, now infamous credit GDP chart. We compare conclusions reached literature after with results could drawn from an ex ante analysis. show that, even though affects...

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 business cycle turning points. First, we compare performance fully non-linear multivariate specification (one-step approach) with “shortcut” using linear model obtain coincident indicator which is then compute probabilities (two-step approach). Second, examine role increasing number indicators. Our results suggest that one step...

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 business cycle turning points. First, we compare performance fully nonlinear multivariate specification (one-step approach) with 'shortcut' using linear model obtain coincident indicator, which is then compute probabilities (two-step approach). Second, examine role increasing number indicators. Our results suggest that one step...