Survey
* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project
Download Trade Classification and Nearly-Gamma Random Variables
Document related concepts
no text concepts found
Transcript
The University of Chicago Department of Statistics Ph.D. Seminar DALE ROSENTHAL Department of Statistics The University of Chicago Trade Classification and Nearly-Gamma Random Variables WEDNESDAY, June 18, 2008 at 3:00 PM at 110 Eckhart Hall, 5734 S. University Avenue ABSTRACT For a number of financial problems, modeling delays plays an important role. I develop asymptotic expansions for a sum of exponential distributions which may be nonidentically-distributed and correlated. These expansions are applied to classifying trades. I propose a generalized linear mixed model for the conditional probability a trade was buyer-initiated. The model encompasses the three major competing methods for classifying trades; uses the asymptotic expansions I develop to better estimate the quotes prevailing when a stock market trade occurred; and allows for buys/sells to be autocorrelated and cross-correlated among all stocks and within a sector. Finally, this work hints at reviving and extending a subset of nearly-forgotten time series models. Randomly-delayed autoregressive (RaDAR) models form a subclass of distributed lag models. Information about building access for persons with disabilities may be obtained in advance by calling Jewanna Carver at 773.834-5169 or by email ([email protected]).
