Use this URL to cite or link to this record in EThOS:
Title: Essays on estimation and inference for volatility with high frequency data
Author: Kalnina, Ilze
Awarding Body: London School of Economics and Political Science (University of London)
Current Institution: London School of Economics and Political Science (University of London)
Date of Award: 2009
Availability of Full Text:
Access from EThOS:
Full text unavailable from EThOS. Please try the link below.
Access from Institution:
Volatility is a measure of risk, and as such it is crucial for finance. But volatility is not observable, which is why estimation and inference for it are important. Large high frequency data sets have the potential to increase the precision of volatility estimates. However, this data is also known to be contaminated by market microstructure frictions, such as bid-ask spread, which pose a challenge to estimation of volatility. The first chapter, joint with Oliver Linton, proposes an econometric model that captures the effects of market microstructure on a latent price process. In particular, this model allows for correlation between the measurement error and the return process and allows the measurement error process to have diurnal heteroskedasticity. A modification of the TSRV estimator of quadratic variation is proposed and asymptotic distribution derived. Financial econometrics continues to make progress in developing more robust and efficient estimators of volatility. But for some estimators, the asymptotic variance is hard to derive or may take a complicated form and be difficult to estimate. To tackle these problems, the second chapter develops an automated method of inference that does not rely on the exact form of the asymptotic variance. The need for a new approach is motivated by the failure of traditional bootstrap and subsampling variance estimators with high frequency data, which is explained in the paper. The main contribution is to propose a novel way of conducting inference for an important general class of estimators that includes many estimators of integrated volatility. A subsampling scheme is introduced that consistently estimates the asymptotic variance for an estimator, thereby facilitating inference and the construction of valid confidence intervals. The third chapter shows how the multivariate version of the subsampling method of Chapter 2 can be used to study the question of time variability in equity betas.
Supervisor: Not available Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID:  DOI: Not available