Christophe Croux t K.U. LeuvenThe presence of outlying observations in panel data can affect the classical estimates in a dramatic way. Nevertheless the common practice seems to disregard the problem. The aim of this work is to study robust regression techniques in the fixed effects linear panel data framework. Robustness of the procedures is investigated by means of breakdown point computations and simulation experiments. A distinction between outlying blocks and cells in a panel is made. To show the potential of robust panel data methods an empirical example on the response of the private sector behavior to fiscal policy is presented.

Abstract. Southern Pakistan (Sindh) is one of the hottest regions in the world and is highly vulnerable to temperature extremes. In order to improve rural and urban planning, it is useful to gather information about the recurrence of temperature extremes. In this work, return levels of the daily maximum temperature T max are estimated, as well as the daily maximum wet-bulb temperature TW max extremes. We adopt the peaks over threshold (POT) method, which has not yet been used for similar studies in this region. Two main datasets are analyzed: temperatures observed at nine meteorological stations in southern Pakistan from 1980 to 2013, and the ERA-Interim (ECMWF reanalysis) data for the nearest corresponding locations. The analysis provides the 2-, 5-, 10-, 25-, 50-, and 100-year return levels (RLs) of temperature extremes. The 90 % quantile is found to be a suitable threshold for all stations. We find that the RLs of the observed T max are above 50 • C at northern stations and above 45 • C at the southern stations. The RLs of the observed TW max exceed 35 • C in the region, which is considered as a limit of survivability. The RLs estimated from the ERA-Interim data are lower by 3 to 5 • C than the RLs assessed for the nine meteorological stations. A simple bias correction applied to ERA-Interim data improves the RLs remarkably, yet discrepancies are still present. The results have potential implications for the risk assessment of extreme temperatures in Sindh.

The Policy Research Working Paper Series disseminates the findings of work in progress to encourage the exchange of ideas about development issues. An objective of the series is to get the findings out quickly, even if the presentations are less than fully polished. The papers carry the names of the authors and should be cited accordingly. The findings, interpretations, and conclusions expressed in this paper are entirely those of the authors. They do not necessarily represent the views of the International Bank for Reconstruction and Development/World Bank and its affiliated organizations, or those of the Executive Directors of the World Bank or the governments they represent.

We investigate the effect of domestic market competition on firmlevel export intensity. We employ a comprehensive dataset of Belgian firms from [2005][2006][2007][2008], when the fall in the number of firms engaged in trade was accompanied by a growing amount of transactions. The resulting increase in the domestic concentration of Belgian firms has sparked numerous debates, since the direction of causality between domestic market structure and export performance is unclear. We apply the fractional logit estimator and control for both self selection and simultaneity bias. We find that a positive linkage exists between the level of competition and export intensity.JEL Classification: C23, F14, L16, L40.

No abstract