[ceis_seminars_phd] 16 September 2014 Seminars: Francesca Dominici and Andrey L. Vasnev

["Barbara Piazzi" < >]

CEIS-Tor Vergata is pleased to inform you that, on Tuesday September 16^th, 2014 Francesca Dominici and Andrey L. Vasnev will present:

at 11.00am,

FRANCESCA DOMINICI (Harvard School of Public Health)

 

“The Public Health Impact of Air Pollution and Climate Change”

 

Over the next century, climate change is expected to lead to an increase in the intensity and frequency of extreme weather events such as heat waves.  Climate change is also expected to impact air pollution, such as ozone and particulate matter. The public health impact of climate change is poorly understood, in part because of numerous factors exhibiting a wide range of uncertainty that underlies estimates of future health risk. To mitigate the public health consequences of climate change we need a comprehensive understanding of how changes in all of the environmental exposures will affect vulnerability in a changing climate. 
In this talk, I will review statistical modeling for estimating the public health impact of air pollution and extreme heat both using historical data and climate change future projections. We will link and analyze massive data sets on weather, air pollution, health, and socio-demographic characteristics that are collected at different spatial and temporal resolution.. We will also present ongoing statistical modeling approaches to address the following challenges; 1) ambient air pollution levels (e.g., ozone and particulate matter) will change in response to the altered meteorological conditions arising from climate change; and 2) the health effects of combined exposure to degraded air quality and heat could be more severe than expected based on the individual exposures (i.e., synergism).​

 

at 12.15am,

ANDREY L. VASNEV (University of Sydney)

 

“The Forecast Combination Puzzle: A Simple Theoretical Explanation”

 

This papers offers a theoretical explanation for the stylized fact that forecast combinations with estimated optimal weights often perform poorly in applications. The properties of the forecast combination are typically derived under the assumption that the weights are fixed, while in practice they need to be estimated. If the fact that the weights are random rather than fixed is taken into account during the optimality derivation, then the forecast combination will be biased (even when the original forecasts are unbiased) and its variance is larger than in the fixed-weights case. In particular, there is no guarantee that the ‘optimal’ forecast combination will be better than the equal-weights case or even improve on the original forecasts. We provide the underlying theory, some special cases and an application in the context of model selection. ​

 

The Seminar will be held at the Faculty of Economics, University of Rome "Tor Vergata", B-building, 1° floor, room B                    

 

Please, go to www.ceistorvergata.it for the complete list of seminars and events at CEIS.

 

How to reach us: http://web.uniroma2.it/mobilita/index.html  http://www.economia.uniroma2.it/area.asp?a=867  

 

 

Barbara Piazzi
CEIS-Tor Vergata
Facoltà di Economia
Università di Roma Tor Vergata
via Columbia, 2
00133 Roma
tel +39.06.7259.5652
fax +39.06.2020687

__________ Informazioni da ESET NOD32 Antivirus, versione del database delle firme digitali 10384 (20140908) __________

Il messaggio è stato controllato da ESET NOD32 Antivirus.

www.nod32.it