CONFERENCE PRESENTATIONS
Presentation, IAAE (International Association for Applied Econometrics) 2016 Annual Conference, University of Milano-Bicocca, Italy, June 2016
Session Host, “Uncertainty and the Macroeconomy” session, IAAE 2016 Annual Conference, University of Milano-Bicocca, Italy, June 2016
PUBLICATION
Lahiri, Kajal, and Wuwei Wang “Estimating Macroeconomic Uncertainty Using Information Measures from SPF Density Forecasts” forthcoming in “Innovations in info-metrics: a cross-disciplinary perspective on information and information processing” 2018.
RESEARCH PAPERS
Estimating Macroeconomic Uncertainty Using Information Measures from SPF Density Forecasts (accepted by IAAE 2016 Annual Conference), job market paper.
Information theory such as measures of entropy is applied into the framework of uncertainty decomposition. We apply generalized beta and triangular distributions to histograms from the SPF and obtain aggregate variance, average variance and disagreement, as well as aggregate entropy, average entropy and information measures. We find these two sets of measures are largely analogous to each other, except in cases where the underlying densities deviate significantly from normality. We find that aggregate uncertainty fell precipitously after 1992, whereas the disagreement between respondents was high before 1981. Our information measures suggest a more permanent reduction in overall uncertainty since the great moderation compared to other parallel studies. Using entropy measures, we find uncertainty affects the economy negatively. We find insignificant price puzzle in the inflation VAR framework. Information theory can be applied to capture the common shock and “news” in the density forecasts. We find that common shock accounts for the bulk of the individual uncertainty, it decreases as horizon falls and ‘news’ is countercyclical.
On the Asymmetry of Loss Functions in SPF (2014 SUNY at Albany)
I estimated and assessed the asymmetry of forecasters’ loss functions. I found that forecasters tend to provide more favorable forecasts in their point forecasts than in their density forecasts for the same target variable. Asymmetry is correlated to the level of the target variable and the previous forecast error.
Uncertainty and Forecasters’ Participation in SPF surveys (2017 SUNY at Albany)
I use probit and hazard models to test whether forecasters reduce participation in SPF surveys if macroeconomic uncertainty is high. I find that professional forecasters are more likely to miss a forecast in uncertain times. They are also less likely to participate in longer horizon forecasts.
PROFESSIONAL AFFILIATIONS
Member, International Association for Applied Econometrics.
Research Assistant
Data processing using STATA in health economics using NHIS data. Research Foundation of SUNY at Albany. Jan. 2011—Jun. 2011
Presentation, IAAE (International Association for Applied Econometrics) 2016 Annual Conference, University of Milano-Bicocca, Italy, June 2016
Session Host, “Uncertainty and the Macroeconomy” session, IAAE 2016 Annual Conference, University of Milano-Bicocca, Italy, June 2016
PUBLICATION
Lahiri, Kajal, and Wuwei Wang “Estimating Macroeconomic Uncertainty Using Information Measures from SPF Density Forecasts” forthcoming in “Innovations in info-metrics: a cross-disciplinary perspective on information and information processing” 2018.
RESEARCH PAPERS
Estimating Macroeconomic Uncertainty Using Information Measures from SPF Density Forecasts (accepted by IAAE 2016 Annual Conference), job market paper.
Information theory such as measures of entropy is applied into the framework of uncertainty decomposition. We apply generalized beta and triangular distributions to histograms from the SPF and obtain aggregate variance, average variance and disagreement, as well as aggregate entropy, average entropy and information measures. We find these two sets of measures are largely analogous to each other, except in cases where the underlying densities deviate significantly from normality. We find that aggregate uncertainty fell precipitously after 1992, whereas the disagreement between respondents was high before 1981. Our information measures suggest a more permanent reduction in overall uncertainty since the great moderation compared to other parallel studies. Using entropy measures, we find uncertainty affects the economy negatively. We find insignificant price puzzle in the inflation VAR framework. Information theory can be applied to capture the common shock and “news” in the density forecasts. We find that common shock accounts for the bulk of the individual uncertainty, it decreases as horizon falls and ‘news’ is countercyclical.
On the Asymmetry of Loss Functions in SPF (2014 SUNY at Albany)
I estimated and assessed the asymmetry of forecasters’ loss functions. I found that forecasters tend to provide more favorable forecasts in their point forecasts than in their density forecasts for the same target variable. Asymmetry is correlated to the level of the target variable and the previous forecast error.
Uncertainty and Forecasters’ Participation in SPF surveys (2017 SUNY at Albany)
I use probit and hazard models to test whether forecasters reduce participation in SPF surveys if macroeconomic uncertainty is high. I find that professional forecasters are more likely to miss a forecast in uncertain times. They are also less likely to participate in longer horizon forecasts.
PROFESSIONAL AFFILIATIONS
Member, International Association for Applied Econometrics.
Research Assistant
Data processing using STATA in health economics using NHIS data. Research Foundation of SUNY at Albany. Jan. 2011—Jun. 2011