HIP, RIP, and the Robustness of Empirical Earnings Processes
Florian Hoffmann
Quantitative Economics,
Nr. 3,
2019
Abstract
The dispersion of individual returns to experience, often referred to as heterogeneity of income profiles (HIP), is a key parameter in empirical human capital models, in studies of life‐cycle income inequality, and in heterogeneous agent models of life‐cycle labor market dynamics. It is commonly estimated from age variation in the covariance structure of earnings. In this study, I show that this approach is invalid and tends to deliver estimates of HIP that are biased upward. The reason is that any age variation in covariance structures can be rationalized by age‐dependent heteroscedasticity in the distribution of earnings shocks. Once one models such age effects flexibly the remaining identifying variation for HIP is the shape of the tails of lag profiles. Credible estimation of HIP thus imposes strong demands on the data since one requires many earnings observations per individual and a low rate of sample attrition. To investigate empirically whether the bias in estimates of HIP from omitting age effects is quantitatively important, I thus rely on administrative data from Germany on quarterly earnings that follow workers from labor market entry until 27 years into their career. To strengthen external validity, I focus my analysis on an education group that displays a covariance structure with qualitatively similar properties like its North American counterpart. I find that a HIP model with age effects in transitory, persistent and permanent shocks fits the covariance structure almost perfectly and delivers small and insignificant estimates for the HIP component. In sharp contrast, once I estimate a standard HIP model without age‐effects the estimated slope heterogeneity increases by a factor of thirteen and becomes highly significant, with a dramatic deterioration of model fit. I reach the same conclusions from estimating the two models on a different covariance structure and from conducting a Monte Carlo analysis, suggesting that my quantitative results are not an artifact of one particular sample.
Artikel Lesen
Effects of Incorrect Specification on the Finite Sample Properties of Full and Limited Information Estimators in DSGE Models
Sebastian Giesen, Rolf Scheufele
Journal of Macroeconomics,
June
2016
Abstract
In this paper we analyze the small sample properties of full information and limited information estimators in a potentially misspecified DSGE model. Therefore, we conduct a simulation study based on a standard New Keynesian model including price and wage rigidities. We then study the effects of omitted variable problems on the structural parameter estimates of the model. We find that FIML performs superior when the model is correctly specified. In cases where some of the model characteristics are omitted, the performance of FIML is highly unreliable, whereas GMM estimates remain approximately unbiased and significance tests are mostly reliable.
Artikel Lesen
Is More Finance Better? Disentangling Intermediation and Size Effects of Financial Systems
Thorsten Beck, Hans Degryse, Christiane Kneer
Journal of Financial Stability,
2014
Abstract
Financial systems all over the world have grown dramatically over recent decades. But is more finance necessarily better? And what concept of financial system – a focus on its size, including both intermediation and other auxiliary “non-intermediation” activities, or a focus on traditional intermediation activity – is relevant for its impact on real sector outcomes? This paper assesses the relationship between the size of the financial system and intermediation, on the one hand, and GDP per capita growth and growth volatility, on the other hand. Based on a sample of 77 countries for the period 1980–2007, we find that intermediation activities increase growth and reduce volatility in the long run. An expansion of the financial sectors along other dimensions has no long-run effect on real sector outcomes. Over shorter time horizons a large financial sector stimulates growth at the cost of higher volatility in high-income countries. Intermediation activities stabilize the economy in the medium run especially in low-income countries. As this is an initial exploration of the link between financial system indicators and growth and volatility, we focus on OLS regressions, leaving issues of endogeneity and omitted variable biases for future research.
Artikel Lesen
Estimating Monetary Policy Rules when the Zero Lower Bound on Nominal Interest Rates is Approached
Konstantin Kiesel, M. H. Wolters
Kiel Working Papers, No. 1898,
2014
Abstract
Monetary policy rule parameters estimated with conventional estimation techniques can be severely biased if the estimation sample includes periods of low interest rates. Nominal interest rates cannot be negative, so that censored regression methods like Tobit estimation have to be used to achieve unbiased estimates. We use IV-Tobit regression to estimate monetary policy responses for Japan, the US and the Euro area. The estimation results show that the bias of conventional estimation methods is sizeable for the inflation response parameter, while it is very small for the output gap response and the interest rate smoothing parameter. We demonstrate how IV-Tobit estimation can be used to study how policy responses change when the zero lower bound is approached. Further, we show how one can use the IV-Tobit approach to distinguish between desired policy responses, that the central bank would implement if there was no zero lower bound, and the actual ones and provide estimates of both.
Artikel Lesen
Effects of Incorrect Specification on the Finite Sample Properties of Full and Limited Information Estimators in DSGE Models
Sebastian Giesen, Rolf Scheufele
Abstract
In this paper we analyze the small sample properties of full information and limited information estimators in a potentially misspecified DSGE model. Therefore, we conduct a simulation study based on a standard New Keynesian model including price and wage rigidities. We then study the effects of omitted variable problems on the structural parameters estimates of the model. We find that FIML performs superior when the model is correctly specified. In cases where some of the model characteristics are omitted, the performance of FIML is highly unreliable, whereas GMM estimates remain approximately unbiased and significance tests are mostly reliable.
Artikel Lesen
Has the Euro Increased International Price Elasticities?
Oliver Holtemöller, Götz Zeddies
Empirica,
Nr. 1,
2013
Abstract
The introduction of the Euro has been accompanied by the hope that international competition between EMU member states would increase due to higher price transparency. This paper contributes to the literature by analyzing price elasticities in international trade flows between Germany and France and between Germany and the United Kingdom before and after the introduction of the Euro. Using disaggregated Eurostat trade statistics, we adopt a heterogeneous dynamic panel framework for the estimation of price elasticities. We suggest a Kalman-filter approach to control for unobservable quality changes which otherwise would bias estimates of price elasticities. We divide the complete sample, which ranges from 1995 to 2008, into two sub-samples and show that price elasticities in trade between EMU members did not change substantially after the introduction of the Euro. Hence, we do not find evidence for an increase in international price competition resulting from EMU.
Artikel Lesen
Evaluation of Further Training Programmes with an Optimal Matching Algorithm
Eva Reinowski, Birgit Schultz, Jürgen Wiemers
IWH Discussion Papers,
Nr. 188,
2004
Abstract
This study evaluates the effects of further training on the individual unemployment duration of different groups of persons representing individual characteristics and some aspects of the economic environment. The Micro Census Saxony enables us to include additional information about a person's employment history to eliminate the bias resulting from unobservable characteristics and to avoid Ashenfelter's Dip. In order to solve the sample selection problem we employ an optimal full matching assignment, the Hungarian algorithm. The impact of participation in further training is evaluated by comparing the unemployment duration between participants and non-participants using the Kaplan-Meier-estimator. Overall, we find empirical evidence that participation in further training programmes results in even longer unemployment duration.
Artikel Lesen
A macroeconometric model for the Euro economy
Christian Dreger
IWH Discussion Papers,
Nr. 181,
2003
Abstract
In this paper a structural macroeconometric model for the Eurozone is presented. In opposite to the multi country modelling approach, the model relies on aggregate data on the supra-national level. Due to nonstationarity, all equations are estimated in an error correction form. The cointegrating relations are derived jointly with the short-run dynamics, avoiding the finite sample bias of the two step Engle Granger procedure. The validity of the aggregated approach is confirmed by out-of-sample forecasts and two simulation exercises. In particular the implications of a lower economic recovery in the US and a shock in the nominal Euro area interest rate are discussed.
Artikel Lesen
