Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 3 of 3
Full-Text Articles in Statistical Models
Mortgage Transition Model Based On Loanperformance Data, Shuyao Yang
Mortgage Transition Model Based On Loanperformance Data, Shuyao Yang
Arts & Sciences Electronic Theses and Dissertations
The unexpected increase in loan default on the mortgage market is widely considered to be one of the main cause behind the economic crisis. To provide some insight on loan delinquency and default, I analyze the mortgage performance data from Fannie Mae website and investigate how economic factors and individual loan and borrower information affect the events of default and prepaid. Various delinquency status including default and prepaid are treated as discrete states of a Markov chain. One-step transition probabilities are estimated via multinomial logistic models. We find that in general current loan-to-value ratio, credit score, unemployment rate, and interest …
Statistical Analysis Of Markovian Queueing Models Of Limit Order Books, Yiyao Luo
Statistical Analysis Of Markovian Queueing Models Of Limit Order Books, Yiyao Luo
Arts & Sciences Electronic Theses and Dissertations
The objective of this thesis is to investigate the suitability of some Markovian queueing models in being able to effectively describe the dynamical properties of a limit order book more specifically. We review and compare the assumptions proposed by Huang et al.[Quantitative Finance,12,547-557(2012)] and Cont et al.[SIAM Journal for Financial Mathematics,4,1- 25(2013)], and estimate the intensity parameters in both ways, based on real data of a stock on the Nasdaq Stock Market. Trough comparing by cumulative distribution functions of first-passage time to state 0, we will hsow that the estimators of Cont’s model fit our data better and we put …
On Post-Selection Confidence Intervals In Linear Regression, Xinwei Zhang
On Post-Selection Confidence Intervals In Linear Regression, Xinwei Zhang
Arts & Sciences Electronic Theses and Dissertations
The general goal of this thesis is to investigate and examine some issues about post-selection inference which arises from the setting where statistical inference is carried out after a datadriven model selection step. In this setting, the classical inference theory which requires a fixed priori model becomes invalid since the selected model is a result of random event. Hence, a common practice in applied research which ignores the model selection and builds up confidence interval will result in misleading or even false conclusion. In this thesis, specifically, we first discusses some examples to show how the classical inference theory loses …