|
on Econometrics |
| By: | James G. MacKinnon (Queen's University) |
| Abstract: | Confidence intervals based on cluster-robust covariance matrices can be constructed in many ways. In addition to conventional intervals obtained by inverting Wald (t) tests, the paper studies intervals obtained by inverting LM tests, studentized bootstrap intervals based on the wild cluster bootstrap, and restricted bootstrap intervals obtained by inverting bootstrap Wald and LM tests. It also studies the choice of an auxiliary distribution for the wild bootstrap, a modified covariance matrix based on transforming the residuals, which was proposed previously, and modified wild bootstrap procedures based on the same idea, which are new. Some procedures perform extraordinarily well even with the number of clusters is small. |
| Keywords: | wild bootstrap, auxiliary distribution, CRVE, cluster-robust inference, studentized bootstrap |
| JEL: | C15 C21 C23 |
| Date: | 2014–08 |
| URL: | http://d.repec.org/n?u=RePEc:qed:wpaper:1329&r=ecm |
| By: | Anton Skrobotov (Gaidar Institute for Economic Policy) |
| Abstract: | In this paper a modification of the Busetti and Harvey (2001) test with structural break at unknown time is proposed. As the stationarity test with a super-consistent break date estimator is effective under large breaks and the infimum-test is effective under small breaks, although it has serious size distortions under large breaks, we propose a simple decision rule based on pre-testing for the presence of a break. The proposed modification shows good size properties. Also, an extension for the case of multiple structural breaks is proposed |
| Keywords: | KPSS test, in mum test, size distortion, power, pre-testing, structural breaks |
| JEL: | C12 C22 |
| Date: | 2014 |
| URL: | http://d.repec.org/n?u=RePEc:gai:wpaper:0102&r=ecm |
| By: | Francisco Javier Eransus (Departamento de Economía Cuantitativa (Department of Quantitative Economics), Facultad de Ciencias Económicas y Empresariales (Faculty of Economics and Business), Universidad Complutense de Madrid); Alfonso Novales Cinca (Departamento de Economía Cuantitativa (Department of Quantitative Economics), Facultad de Ciencias Económicas y Empresariales (Faculty of Economics and Business), Universidad Complutense de Madrid) |
| Abstract: | We analyze the effect of parameter estimation error on the size of unconditional population level tests of predictive ability when they are implemented under a class of loss functions we refer to as ‘discrete functions’. The analysis is restricted to linear models in stationary variables. We obtain analytical results for no nested models guaranteeing asymptotic irrelevance of parameter estimation error under a plausible predictive environment and three subsets of discrete loss functions that seem quite appropriate for many economic applications. For nested models, we provide some Monte Carlo evidence suggesting that the asymptotic distribution of the Diebold and Mariano (1995) test is relatively robust to parameter estimation error in many cases if it is implemented under discrete loss functions, unlike what happens under the squared forecast error or the absolute value error loss functions. |
| Keywords: | Parameter uncertainty; Forecast accuracy; Discrete loss function. |
| JEL: | C53 C52 C12 |
| Date: | 2014 |
| URL: | http://d.repec.org/n?u=RePEc:ucm:doicae:1422&r=ecm |
| By: | Spyridon D. Symeondes; Yiannis Karavias; Elias Tzavalis |
| Abstract: | Refined asymptotic methods are used to produce degrees-of-freedom adjusted Edgeworth and Cornish-Fisher size corrections of the t and F testing procedures for the parameters of a S.U.R. model with serially correlated errors. The corrected tests follow the Student-t and F distributions, respectively, with an approximation error of order O(\tau^3), where \tau = 1/sqrt(T) and T is the number of time observations. Monte Carlo simulatitions provide evidence that the size corrections suggested hereby have better finite sample properties, compared to the asymptotc testing procedures (either standard or Edgeworth corrected), which do not adjust for the degrees of freedom. |
| Keywords: | Linear regression; S.U.R. models; stochastic expansions;asymptotic approximations; AR(1) errors. JEL classification: C10, C12, D24. |
| URL: | http://d.repec.org/n?u=RePEc:not:notgts:14/01&r=ecm |
| By: | van den Berg, Gerard J. (University of Mannheim); Janys, Lena (University of Mannheim); Mammen, Enno (University of Mannheim); Nielsen, Jens P. (Cass Business School) |
| Abstract: | We examine a new general class of hazard rate models for survival data, containing a parametric and a nonparametric component. Both can be a mix of a time effect and (possibly time-dependent) marker or covariate effects. A number of well-known models are special cases. In a counting process framework, a general profile likelihood estimator is developed and the parametric component of the model is shown to be asymptotically normal and efficient. The analysis improves on earlier results for special cases. Finite sample properties are investigated in simulations. The estimator is shown to work well under realistic empirical conditions. The estimator is applied to investigate the long-run relationship between birth weight and later-life mortality using data from the Uppsala Birth Cohort Study of individuals born in 1915-1929. The results suggest a relationship that is difficult to capture with simple parametric specifications. Moreover, its shape at higher birth weights differs across gender. |
| Keywords: | asymptotic distribution, local linear estimation, survival analysis, covariate effects, birth weight, mortality, social class |
| JEL: | C41 C14 I12 J13 |
| Date: | 2014–07 |
| URL: | http://d.repec.org/n?u=RePEc:iza:izadps:dp8339&r=ecm |
| By: | Michal Bernard Pietrzak (Nicolaus Copernicus University, Poland) |
| Abstract: | The main purpose of the article is to consider a important issue of spatial econometrics which is a proper interpretation of structural parameters of econometric models with spatial autoregression. The problem will be considered based on the example of the spatial SAR model. Another purpose of the article is to make an overview of measures of average spatial impact proposed by the subject literature (see Lesage and Pace 2009). The analysis will include such measures as Average Total Impact to an Observation, Average Total Impact from an Observation, Average Indirect Impact to an Observation, Average Indirect Impact from an Observation and Average Direct Impact. Having considered the above issues, I will introduce a set of three original measures that allow interpretation of the strength of the impact of the explanatory processes within the spatial SAR model which take the forms of average direct impact, average indirect impact and average induced impact. The use of this set of measures will be illustrated with the example of the analysis of the unemployment rate in Poland. It must be emphasized that the presented set of measures may also be designated for other spatial models. With the knowledge of the empirical form of the model and of the spatial weight matrix, the set of measures introduced simplifies significantly the complex procedure of the interpretation of the structural parameters for spatial models to the use of merely three values. |
| Keywords: | spatial econometrics, measures of average impact, SAR model, SDM model, spatial autocorrelation |
| JEL: | C21 R11 R23 |
| Date: | 2013–02 |
| URL: | http://d.repec.org/n?u=RePEc:pes:wpaper:2013:no32&r=ecm |
| By: | Roger Bivand (Norwegian School of Econonomics); Gianfranco Piras (Regional Research Institute, West Virginia University) |
| Abstract: | Recent advances in the implementation of spatial econometrics model estimation techniques have made it desirable to compare results, which should correspond between implementations across software applications for the same data. These model estimation techniques are associated with methods for estimating impacts (emanating effects), which are also presented and compared. This review constitutes an up to date comparison of generalized method of moments (GMM) and maximum likelihood (ML) implementations now available. The comparison uses the cross sectional US county data set provided by Drukker, Prucha, and Raciborski (2011c, pp. 6-7). The comparisons will be cast in the context of alternatives using the MATLAB Spatial Econometrics toolbox, Stata, Python with PySAL (GMM) and R packages including sped, sphet and McSpatial. |
| Keywords: | spatial econometrics, maximum likelihood, generalized method of moments, estimation, R, Stata, Python, MATLAB |
| JEL: | C21 C4 C5 |
| Date: | 2013–01 |
| URL: | http://d.repec.org/n?u=RePEc:rri:wpaper:201301&r=ecm |
| By: | Christian Kleiber; Achim Zeileis |
| Abstract: | We show how the rootogram - a graphical tool associated with the work of J. W. Tukey and originally used for assessing goodness of fit of univariate distributions - can help to diagnose and treat issues such as overdispersion and/or excess zeros in regression models for count data. Two empirical illustrations, from ethology and from public health, are included. The former employs a negative binomial hurdle regression, the latter a two-component finite mixture of negative binomial models for which weighted versions of rootograms are utilized. |
| Keywords: | rootogram, visualization, goodness of fit, count data, Poisson regression, negative binomial regression, hurdle model, finite mixture |
| JEL: | C25 C52 C87 |
| Date: | 2014–07 |
| URL: | http://d.repec.org/n?u=RePEc:inn:wpaper:2014-20&r=ecm |
| By: | Young H. Lee (Department of Economics, Sogang University, Seoul) |
| Abstract: | This paper discusses the use of ten different GAUSS programs for various stochastic frontier models. SFM_MLE_cross-section provides maximum likelihood estimates (MLE) for four different stochastic frontier models with cross-sectional data: those of Aigner, Lovell, and Schmidt (1977), Stevenson (1980), Almanidis, Qian, and Sickles (2014), and Lee and Lee (2014). There are two programs for panel data stochastic frontier models with the time-invariant efficiency assumption. SFM_BC88_MLE provides the MLE of Battese and Coelli (1988) and SFM_SS presents the within and generalized least squared estimates of Schmidt and Sickles (1984). Finally, seven programs allow the use of different stochastic frontier models with time-varying efficiency: SFM_BC92 for Battese and Coelli (1992), SFM_Kum for Kumbhakar (1991), SFM_CSS for Cornwell, Schmidt, and Sickles (1990), SFM_LS for Lee and Schmidt (1993), SFM_GrLS for Lee (2006), SFM_GrBC for Lee (2010), and SFM_ALS07 for Ahn, Lee, and Schmidt (2007). A noteworthy feature is that all seven programs estimate production function parameters by adopting the fixed effect treatment. |
| Date: | 2014 |
| URL: | http://d.repec.org/n?u=RePEc:sgo:wpaper:1403&r=ecm |