|
on Econometrics |
| By: | Stauskas, Ovidijus (Department of Economics, Lund University) |
| Abstract: | In this paper we re-visit a recent theoretical idea introduced by Phillips and Lee (2015). They examine an empirically relevant situation when multiple time series under consideration exhibit different degrees of non-stationarity. By bridging the asymptotic theory of the local to unity and mildly explosive processes, they construct a Wald test for the commonality of the long-run behavior of two series. Therefore, a vector autoregressive (VAR) setup is natural. However, inference is complicated by the fact that the statistic is degenerate under the null and divergent under the alternative. This is true if the parameters of the data generating process are known and re-normalizing function can be constructed. If the parameters are unknown, as is in practice, the test statistic may be divergent even under the null. We solve this problem by converting the original setting of one vector time series in a panel setting with N individual vector series. We consider asymptotics with fixed N and large T and extend the results to sequential asymptotics when T passes to infinity before N. We show that the Wald test statistic converges to nuisance parameter-free Chi-squared distribution under the null hypothesis. |
| Keywords: | Local to unity; mildly explosive; panel; weak dependence; Wald test |
| JEL: | C12 C32 C33 |
| Date: | 2019–01–14 |
| URL: | http://d.repec.org/n?u=RePEc:hhs:lunewp:2019_002&r=all |
| By: | José M.R. Murteira (CeBER, Faculdade de Economia da Universidade de Coimbra, and CEMAPRE) |
| Abstract: | This paper addresses measurement error (ME) of double bounded variables, of which fractional variables, defined on the interval [0,1], constitute a prominent example. The text discusses consequences of ME and suggests a specification test sensitive to ME of such variables. Given the latter’s bounded support, ME is not independent of the original error-free variate, a fact that invalidates classical ME assumptions as a framework for the test. This is circumvented with a score test of independence between the error-free variate and ME, under which the latter becomes degenerate at zero and their joint distribution, specified as a copula function, reduces to the original variable’s distribution. This procedure yields a specification test of the distribution of the error-free variable, valid under mild assumptions on the marginal distribution of ME and under departures from the specified copula. The test’s finite-sample behaviour is also evaluated through a set of simulation experiments. |
| Keywords: | Copula; Fractional variable; Maximum likelihood; Measurement error; Probability integral transform; Score test. |
| JEL: | C12 C25 |
| Date: | 2018–12 |
| URL: | http://d.repec.org/n?u=RePEc:gmf:papers:2018-13&r=all |
| By: | Gordon V. Chavez |
| Abstract: | We propose a family of stochastic volatility models that enable direct estimation of time-varying extreme event probabilities in time series with nonlinear dependence and power law tails. The models are a white noise process with conditionally log-Laplace stochastic volatility. In contrast to other, similar stochastic volatility formalisms, this process has an explicit, closed-form expression for its conditional probability density function, which enables straightforward estimation of dynamically changing extreme event probabilities. The process and volatility are conditionally Pareto-tailed, with tail exponent given by the reciprocal of the log-volatility's mean absolute innovation. These models thus can accommodate conditional power law-tail behavior ranging from very weakly non-Gaussian to Cauchy-like tails. Closed-form expressions for the models' conditional polynomial moments also allows for volatility modeling. We provide a straightforward, probabilistic method-of-moments estimation procedure that uses an asymptotic result for the process' conditional large deviation probabilities. We demonstrate the estimator's usefulness with a simulation study. We then give empirical applications to financial time series data, which show that this simple modeling method can be effectively used for dynamic tail inference in nonlinear, heavy-tailed time series. |
| Date: | 2019–01 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:1901.02419&r=all |
| By: | Aknouche, Abdelhakim; Francq, Christian |
| Abstract: | We consider a positive-valued time series whose conditional distribution has a time-varying mean, which may depend on exogenous variables. The main applications concern count or duration data. Under a contraction condition on the mean function, it is shown that stationarity and ergodicity hold when the mean and stochastic orders of the conditional distribution are the same. The latter condition holds for the exponential family parametrized by the mean, but also for many other distributions. We also provide conditions for the existence of marginal moments and for the geometric decay of the beta-mixing coefficients. Simulation experiments and illustrations on series of stock market volumes and of greenhouse gas concentrations show that the multiplicative-error form of usual duration models deserves to be relaxed, as allowed in the present paper. |
| Keywords: | Absolute regularity, Autoregressive Conditional Duration, Count time series models, Distance covariance test, Ergodicity, Integer GARCH |
| JEL: | C18 C5 C58 |
| Date: | 2018–11–11 |
| URL: | http://d.repec.org/n?u=RePEc:pra:mprapa:90838&r=all |
| By: | Alexis Akira Toda; Yulong Wang |
| Abstract: | We propose an efficient estimation method for the income Pareto exponent when only certain top income shares are observable. Our estimator is based on the asymptotic theory of weighted sums of order statistics and the efficient minimum distance estimator. Simulations show that our estimator has excellent finite sample properties. We apply our estimation method to the U.S. top income share data and find that the Pareto exponent has been stable at around 1.5 since 1985, suggesting that the rise in inequality during the last three decades is mainly driven by redistribution between the rich and poor, not among the rich. |
| Date: | 2019–01 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:1901.02471&r=all |
| By: | George Kapetanios; M. Hashem Pesaran; Simon Reese |
| Abstract: | The importance of units with pervasive impacts on a large number of other units in a network has become increasingly recognized in the literature. In this paper we propose a new method to detect such influential or dominant units by basing our analysis on unit-specific residual error variances in the context of a standard factor model, subject to suitable adjustments due to multiple testing. Our proposed method allows us to estimate and identify the dominant units without the a priori knowledge of the interconnections amongst the units, or using a short list of potential dominant units. It is applicable even if the cross section dimension exceeds the time dimension, and most importantly it could end up with none of the units selected as dominant when this is in fact the case. The sequential multiple testing procedure proposed exhibits satisfactory small-sample performance in Monte Carlo simulations and compares well relative to existing approaches. We apply the proposed detection method to sectoral indices of US industrial production, US house price changes by states, and the rates of change of real GDP and real equity prices across the world’s largest economies. |
| Keywords: | dominant units, factor models, systemic risk, cross-sectional dependence, networks |
| JEL: | C18 C23 |
| Date: | 2018 |
| URL: | http://d.repec.org/n?u=RePEc:ces:ceswps:_7401&r=all |
| By: | Francisco Blasques; Vladim\'ir Hol\'y; Petra Tomanov\'a |
| Abstract: | In finance, durations between successive transactions are usually modeled by the autoregressive conditional duration model based on a continuous distribution omitting frequent zero values. Zero durations can be caused by either split transactions or independent transactions. We propose a discrete model allowing for excessive zero values based on the zero-inflated negative binomial distribution with score dynamics. We establish the invertibility of the score filter. Additionally, we derive sufficient conditions for the consistency and asymptotic normality of the maximum likelihood of the model parameters. In an empirical study of DJIA stocks, we find that split transactions cause on average 63% of zero values. Furthermore, the loss of decimal places in the proposed model is less severe than incorrect treatment of zero values in continuous models. |
| Date: | 2018–12 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:1812.07318&r=all |
| By: | Luisa Bisaglia; Matteo Grigoletto |
| Abstract: | In this work we propose a new class of long-memory models with time-varying fractional parameter. In particular, the dynamics of the long-memory coefficient, $d$, is specified through a stochastic recurrence equation driven by the score of the predictive likelihood, as suggested by Creal et al. (2013) and Harvey (2013). We demonstrate the validity of the proposed model by a Monte Carlo experiment and an application to two real time series. |
| Date: | 2018–12 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:1812.07295&r=all |
| By: | Kellie Ottoboni; Jason Poulos |
| Abstract: | This paper extends a method of estimating population average treatment effects to settings with noncompliance. Simulations show the proposed compliance-adjusted estimator performs better than its unadjusted counterpart when compliance is relatively low and can be predicted by observed covariates. We apply the proposed estimator to measure the effect of Medicaid coverage on health care use for a target population of adults who may benefit from expansions to the Medicaid program. We draw randomized control trial data from a large-scale health insurance experiment in which a small subset of those randomly selected to receive Medicaid benefits actually enrolled. |
| Date: | 2019–01 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:1901.02991&r=all |
| By: | Eric Ghysels (Department of Economics and Kenan-Flagler Business School, University of North Carolina Chapel Hill and CEPR.); Leonardo Iania (Louvain School of Management and IMMAQ (CORE and LFIN), Universite catholique de Louvain.); Jonas Striaukas (Universite catholique de Louvain. Research Fellow at F.R.S. - FNRS) |
| Abstract: | This paper proposes a new approach to extract quantile-based in ation risk mea- sures using Quantile Autoregressive Distributed Lag Mixed-Frequency Data Sampling (QADL-MIDAS) regression models. We compare our models to a standard Quantile Auto-Regression (QAR) model and show that it delivers better quantile forecasts at several forecasting horizons. We use the QADL-MIDAS model to construct in ation risk measures proxying for uncertainty, third-moment dynamics and the risk of ex- treme in ation realizations. We nd that these risk measures are linked to the future evolution of in ation and changes in the e ective federal funds rate. |
| Keywords: | regression quantiles, in ation risk, quantile forecasting |
| JEL: | C53 C54 E37 |
| Date: | 2018–10 |
| URL: | http://d.repec.org/n?u=RePEc:nbb:reswpp:201810-349&r=all |
| By: | Yoici Arai; Taisuke Otsu; Myung Hwan Seo |
| Date: | 2019–01 |
| URL: | http://d.repec.org/n?u=RePEc:cep:stiecm:601&r=all |
| By: | Leeb, Hannes; Pötscher, Benedikt M.; Kivaranovic, Danijel |
| Abstract: | This is a comment on the article mentioned in the title |
| Keywords: | Model selection |
| JEL: | C10 C20 |
| Date: | 2018–07 |
| URL: | http://d.repec.org/n?u=RePEc:pra:mprapa:90655&r=all |