Faculty of Economics, Keio University.
2-15-45 Mita, Minato-ku, Tokyo 108-8345, Japan
E-mail : clinet (at) keio.jp
Phone : +81-3-5427-1506
Office : South building, 20709 (7F)
Fields of Interest
Statistical Inference, Stochastic Processes, Financial Statistics, Financial Econometrics, High Frequency Data, Market Microstructure, Limit Order Books.
Assistant Professor, Faculty of Economics, Keio University.
September 2017 -
Ph.D., Graduate School of Mathematical Sciences, The University of Tokyo. Under the supervision of Nakahiro Yoshida. October 2014 - September 2017. Statistical inference for point processes and its applications to Limit Order Book. （点過程に対する統計的推測及びリミットオーダーブックへの応用）
Full CV here .
2018/02/27 : 13th German Probability and Statistics Days 2018, University of Freiburg.
2017/08/29 : TMU workshop on finance 2017, Tokyo Metropolitan University.
2017/06/21 : The 10th Annual SoFiE Conference (2017), New York University.
2017/05/23 : Keio University Econometrics Workshop, Institute of Economic Studies.
2017/01/31 : ASC2017 : Asymptotic Statistics and Computations, The University of Tokyo. webpage
2016/12/12 : Workshop on Portfolio dynamics and limit order books, Ecole Centrale Paris (Co-organizer). webpage
2016/11/22 : Keio University Econometrics Workshop, Institute of Economic Studies.
2016/06/30 : IMS-APRM : The 4th Institute of Mathematical Statistics Asia Pacific Rim Meeting, Chinese University of Hong Kong.
2016/03/23 : Statistics for Stochastic Processes and Analysis of High Frequency Data V. University of Pierre and Marie Curie, Paris.
2016/02/16 : ASC2016 : Asymptotic statistics and computations, The University of Tokyo.
2015/11/06 : Berlin meeting on statistical analysis of stochastic processes, Humboldt University.
2015/10/25 : Toyama Symposium on new developments of statistical science in various fields.
Here is a (partially documented) Python package ivol about efficient estimation of volatility and related quantities for noisy high-frequency data. I recommend to use it with Python 3. It is possible to apply the local method to several estimators as studied in my latest paper with Yoann Potiron (see above). In particular, are implemented :
The Quasi Maximum Likelihood Estimator (QMLE).
The Realized Kernel (RK).
The Pre-Averaging Estimator (PAE).
The Two-Scales Realized Volatility (TSRV).
Estimators of the noise variance, the quarticity, and the heteroskedasticity measure ρ as studied in our paper.
Once you have unzipped
the package in a directory accessible to your pythonpath, you can get started by typing
import ivol; help(ivol)
in a python console. The package is not complete and is probably not free of errors. Use it with caution !