SlideShare a Scribd company logo
1 of 48
Download to read offline
Ph.D. dissertation presentation
Empirical properties of functional regression models and
application to high-frequency financial data
Xi Zhang
Department of Mathematics and Statistics
Utah State University
March 20, 2013
1 Xi Zhang | March 20, 2013 1 / 48
Ph.D. dissertation presentation | Introduction
Outline
1 Introduction
Functional data analysis
High-frequency financial data sets
2 Empirical properties of forecasts with the functional autoregressive model
3 Functional prediction of intraday cumulative returns
4 Functional multifactor regression for intraday price curves
5 Summary and Conclusions
2 Xi Zhang | March 20, 2013 2 / 48
Ph.D. dissertation presentation | Introduction | Functional data analysis
Functional Data Analysis(FDA)
It analyzes data providing information about curves, surfaces or anything else
varying over a continuum (time, spatial location, wavelength, probability, etc).
The core idea is that curves should be treated as individual and complete
statistical objects, rather than as collections of individual observations.
Statistical tools of FDA typically rely on some form of smoothing to transform
high dimensional or incomplete data building up a curve into a smoother curve
that can be described by a smaller number of parameters.
The inherent complexity of FDA makes it impossible in a meaningful way to
estimate the “distribution” of a random function, or to find estimates that could
converge in a reasonable rate, which indicates that the properties of the FPCA are
of great importance in FDA.
3 Xi Zhang | March 20, 2013 3 / 48
Ph.D. dissertation presentation | Introduction | High-frequency financial data sets
8 years price process
4 Xi Zhang | March 20, 2013 4 / 48
Ph.D. dissertation presentation | Introduction | High-frequency financial data sets
Cumulative Intraday returns
Definition
Suppose Pn(tj ), n = 1, . . . , N, j = 1, . . . , m is the price of a financial asset at time tj
on day n. The functions
rn(tj ) = 100[ln Pn(tj ) − ln Pn(t1)], j = 2, . . . , m, n = 1, . . . , N,
are defined as the intraday cumulative returns (CIDR’s/ IDCR’s).
The above definition implicitly assumes that tj+1 > tj .
we work with one minute averages, so tj+1 − tj = 1 min, and P(tj ) is the average of the
maximum and minimum price within the jth minute.
5 Xi Zhang | March 20, 2013 5 / 48
Ph.D. dissertation presentation | Introduction | High-frequency financial data sets
Cumulative Intraday returns
6 Xi Zhang | March 20, 2013 6 / 48
Ph.D. dissertation presentation | Introduction | High-frequency financial data sets
Five days closer look
7 Xi Zhang | March 20, 2013 7 / 48
Ph.D. dissertation presentation | Introduction | High-frequency financial data sets
Why CIDR’s/IDCR’s?
Similar to curves of the price Pn(tj ) for a trading day n which are of high interest
by stock investors
Give more relevant information by showing how the return changes during a
trading day
Can be treated as continuous curves, one curve per day, adapted to functional data
8 Xi Zhang | March 20, 2013 8 / 48
Ph.D. dissertation presentation | Introduction | High-frequency financial data sets
High frequency returns
9 Xi Zhang | March 20, 2013 9 / 48
Ph.D. dissertation presentation | Empirical properties of forecasts with the functional autoregressive model
Outline
1 Introduction
2 Empirical properties of forecasts with the functional autoregressive model
Introduction
Simulation study
Results
3 Functional prediction of intraday cumulative returns
4 Functional multifactor regression for intraday price curves
5 Summary and Conclusions
10 Xi Zhang | March 20, 2013 10 / 48
Ph.D. dissertation presentation | Empirical properties of forecasts with the functional autoregressive model | Introduction
Functional Autoregressive model(FAR)
FAR(1) model
Xn+1 = Ψ(Xn) + εn+1,
where errors εn and the observations Xn are curves, and the operator Ψ acting on a
function X is defined as
Ψ(X)(t) = ψ(t, s)X(s)ds,
where ψ(t, s) is a bivariate kernel assumed to satisfy ||Ψ|| < 1, where
||Ψ||2
= ψ2
(t, s)dtds. (1)
The condition ||Ψ|| < 1 ensures the existence of a stationary causal solution to FAR(1)
equations.
11 Xi Zhang | March 20, 2013 11 / 48
Ph.D. dissertation presentation | Empirical properties of forecasts with the functional autoregressive model | Introduction
Methods
Bosq (2000) advocated a standard method by estimating the operator Ψ and
forecasting Xn+1 by ˆΨ(Xn). (Estimated Kernel (EK))
The empirical version of bivariate kernel ψ:
ˆψp(t, s) =
p
k, =1
ˆψk ˆvk (t)ˆv (s), (2)
where
ˆψji = ˆλ−1
i (N − 1)−1
N−1
n=1
Xn, ˆvi Xn+1, ˆvj . (3)
where ˆvk , k = 1, 2, . . . , p, the estimated (or empirical) FPC’s (EFPC’s).p is the
number of EFPC’s.
Kargin and Onatski (2008) proposed a sophisticated method: one step ahead
prediction in FAR(1) model based on predictive factors. (Predictive Factors (PF))
12 Xi Zhang | March 20, 2013 12 / 48
Ph.D. dissertation presentation | Empirical properties of forecasts with the functional autoregressive model | Introduction
Objective
Is the method of Predictive Factors (PF) superior in finite samples to the Estimated
Kernel (EK)?
13 Xi Zhang | March 20, 2013 13 / 48
Ph.D. dissertation presentation | Empirical properties of forecasts with the functional autoregressive model | Simulation study
Data generating process
FAR(1) model
Xn+1(t) =
1
0
ψ(t, s)Xn(s)ds + εn+1(t), n = 1, 2, . . . , N.
Three error processes
Brownian bridges
ε(1)
(t) = BB(t)
ε(2)
(t) = ξ1
√
2 sin(2πt) +
√
λ
√
2ξ2 cos(2πt) ,
where ξ1 and ξ2 are independent standard normals, λ can be any constant (in the
simulations we use λ = 0.5).
ε(3)
(t) = ε(2)
(t) + aε(1)
(t) ,
14 Xi Zhang | March 20, 2013 14 / 48
Ph.D. dissertation presentation | Empirical properties of forecasts with the functional autoregressive model | Simulation study
Kernels
Four kernels (defined for (t, s) ∈ [0, 1]2
):
Gaussian : ψ(t, s) = C exp −(t2
+ s2
)/2 ,
Identity : ψ(t, s) = C,
Sloping plane (t) : ψ(t, s) = Ct,
Sloping plane (s) : ψ(t, s) = Cs.
C are chosen such that ||Ψ|| = 0.5 or ||Ψ|| = 0.8.
15 Xi Zhang | March 20, 2013 15 / 48
Ph.D. dissertation presentation | Empirical properties of forecasts with the functional autoregressive model | Simulation study
Measures of quality of prediction
Quantities:
En =
1
0
Xn(t) − ˆXn(t)
2
dt and Rn =
1
0
Xn(t) − ˆXn(t) dt.
are used to measure the prediction error at time n.
16 Xi Zhang | March 20, 2013 16 / 48
Ph.D. dissertation presentation | Empirical properties of forecasts with the functional autoregressive model | Results
Comparison of five prediction methods
MP Mean Prediction ˆXn+1(t) = 0.
NP Naive Prediction ˆXn+1 = Xn.
EX Exact ˆXn+1 = Ψ(Xn).
EK Estimated Kernel.
EKI Estimated Kernel Improved, using ˆλi + ˆb instead of ˆλi .
PF Predictive Factors.
17 Xi Zhang | March 20, 2013 17 / 48
Ph.D. dissertation presentation | Empirical properties of forecasts with the functional autoregressive model | Results
Boxplots of the prediction errors ||Ψ|| = 0.5
En (left) and Rn (right); innovations: ε(1)
, kernel: sloping plane (t), N = 100, p = 3.
18 Xi Zhang | March 20, 2013 18 / 48
Ph.D. dissertation presentation | Empirical properties of forecasts with the functional autoregressive model | Results
Conclusions
Based on all 32 sets of boxplots and 32 sets of tables, we report:
Taking the autoregressive structure into account reduces prediction errors.
None of the Methods EX, EK, EKI uniformly dominates the other. In most cases
method EK is the best, or at least as good as the others.
In some cases, method PF performs visibly worse than the other methods, but
always better than NP.
Using the improved estimation does not generally reduce prediction errors.
19 Xi Zhang | March 20, 2013 19 / 48
Ph.D. dissertation presentation | Functional prediction of intraday cumulative returns
Outline
1 Introduction
2 Empirical properties of forecasts with the functional autoregressive model
3 Functional prediction of intraday cumulative returns
Introduction
Methods and models
Application to US stocks
Results
4 Functional multifactor regression for intraday price curves
5 Summary and Conclusions
20 Xi Zhang | March 20, 2013 20 / 48
Ph.D. dissertation presentation | Functional prediction of intraday cumulative returns | Introduction
Capital Asset Pricing Model(CAPM)
The simplest form of celebrated Capital Asset Pricing Model(CAPM):
rn = α + βrm,n + εn (4)
where
rn = 100(ln Pn − ln Pn−1) ≈ 100
Pn − Pn−1
Pn−1
(5)
is the return, in percent, over a unit of time on a specific asset, e.g. a stock, and rm,n is
the analogously defined return on a relevant market index.
21 Xi Zhang | March 20, 2013 21 / 48
Ph.D. dissertation presentation | Functional prediction of intraday cumulative returns | Introduction
Objective
Model the relationship between the IDCR’s curves for a single asset and those for
a market index
Evaluate their relevance by comparing their predictive power
22 Xi Zhang | March 20, 2013 22 / 48
Ph.D. dissertation presentation | Functional prediction of intraday cumulative returns | Methods and models
Simple Functional CAPM (SF)
A simple functional CAPM is defined as
Yn(t) = α + ψXn(t) + εn(t), t ∈ [0, 1]. (6)
A model without the intercept (α ≡ 0), denoted SF*, is also considered.
23 Xi Zhang | March 20, 2013 23 / 48
Ph.D. dissertation presentation | Functional prediction of intraday cumulative returns | Methods and models
Fully Functional CAPM (FF)
This model is defined by the relation
Yn(t) = α(t) + ψ(t, s)Xn(s)ds + εn(t), t ∈ [0, 1]. (7)
If α ≡ 0, this model is denoted FF*.
24 Xi Zhang | March 20, 2013 24 / 48
Ph.D. dissertation presentation | Functional prediction of intraday cumulative returns | Methods and models
Functional CAPM with dependent errors
This model is defined by 6, but the errors are assumed to follow a functional
autoregressive process of order 1, FAR(1) process:
εn(t) = ϕ(t, s)εn−1(s)ds + wn(t), (8)
where the wn are iid mean zero random functions.
Fully Functional CAPM with dependent errors (FFDE). This model is defined by 7
with errors which follow the FAR(1) process. When doing prediction, this model fails,
because kernel operators ϕ(t, s) and ψ(t, s) cannot commute.
25 Xi Zhang | March 20, 2013 25 / 48
Ph.D. dissertation presentation | Functional prediction of intraday cumulative returns | Methods and models
Problems seek to solve
Can a simpler model with a scalar coefficient give predictions as good as a model
with a kernel coefficient?
Does including an intercept improve predictions, or does this extra parameter
actually make them worse?
Does modeling error correlation lead to improved predictions?
26 Xi Zhang | March 20, 2013 26 / 48
Ph.D. dissertation presentation | Functional prediction of intraday cumulative returns | Methods and models
Estimation of regression parameters
All calculations have been performed in the R package fda.
The cumulative returns in one minute resolution are converted to functional
objects.
99 Fourier basis functions are used.
Empirical functional principal components (EFPC’s) ˆv1, . . . , ˆvp of the data are
computed.
27 Xi Zhang | March 20, 2013 27 / 48
Ph.D. dissertation presentation | Functional prediction of intraday cumulative returns | Methods and models
Evaluate the quality of prediction
The integrated mean squared error defined as
MSEP(N) = N−1
N
n=1
(Yn(t) − ˆYn(t))2
dt. (9)
28 Xi Zhang | March 20, 2013 28 / 48
Ph.D. dissertation presentation | Functional prediction of intraday cumulative returns | Application to US stocks
Data preparation
10 large U.S. corporations in five sectors
Standard & Poor’s 100 index representing market index
1000–day long periods: 01/03/2000 to 02/22/2006 without obvious outliers
29 Xi Zhang | March 20, 2013 29 / 48
Ph.D. dissertation presentation | Functional prediction of intraday cumulative returns | Application to US stocks
Description of 10 Stocks representing five sectors
Sector Stocks Full Name 1000 days period
Energy
XOM Exxon Mobil 05/25/2000-05/19/2004
CVX Chevron
10/10/2001-07/23/2004
12/13/2004-02/22/2006
Information MSFT Microsoft 05/25/2000-05/19/2004
Technology IBM IBM 01/03/2000-12/24/2003
Financial
CITI Citi Bank 10/17/2000-03/07/2005
BOA Bank of America 03/13/2001-12/19/2005
Consumer KO Coca-Cola 05/25/2000-05/19/2004
Staples WMT Wal-Mart Stores 05/25/2000-05/19/2004
Consumer MCD McDonald’s 10/17/2000-03/07/2005
Discretionary DIS The Walt Disney 05/25/2000-05/19/2004
30 Xi Zhang | March 20, 2013 30 / 48
Ph.D. dissertation presentation | Functional prediction of intraday cumulative returns | Results
Prediction results (1)
31 Xi Zhang | March 20, 2013 31 / 48
Ph.D. dissertation presentation | Functional prediction of intraday cumulative returns | Results
Prediction results (2)
32 Xi Zhang | March 20, 2013 32 / 48
Ph.D. dissertation presentation | Functional prediction of intraday cumulative returns | Results
Conclusions
Models with intercept, i.e. SF and FF, make better prediction than models
without intercept i.e. SF* and FF*. The latter should not be used.
Modeling error dependence with a functional AR(1) model does not improve
MSEP’s.
The two models with intercept, i.e. SF and FF, do NOT dominate each other.
They have almost the same MSEP’s.
SF model is recommended if minimizing the MSEP is the only concern. It is
intuitive, its estimation is straightforward, and the prediction equation is very
simple.
33 Xi Zhang | March 20, 2013 33 / 48
Ph.D. dissertation presentation | Functional multifactor regression for intraday price curves
Outline
1 Introduction
2 Empirical properties of forecasts with the functional autoregressive model
3 Functional prediction of intraday cumulative returns
4 Functional multifactor regression for intraday price curves
Motivation
Methods and models
Application to U.S. stocks
results
5 Summary and Conclusions
34 Xi Zhang | March 20, 2013 34 / 48
Ph.D. dissertation presentation | Functional multifactor regression for intraday price curves | Motivation
Objective
Whether adding additional factors beyond IDCR’s/CIDR’s on a market index are
statistically significant and whether they lead to improved predictions?
35 Xi Zhang | March 20, 2013 35 / 48
Ph.D. dissertation presentation | Functional multifactor regression for intraday price curves | Methods and models
A general factor model
Factor model
Rn(t) = β0(t) +
p
j=1
βj Fnj (t) + εn(t). (10)
The parameters of the model are the mean function β0(·) and the vector of the
coefficients:
β = [β1, . . . , βp]T
.
36 Xi Zhang | March 20, 2013 36 / 48
Ph.D. dissertation presentation | Functional multifactor regression for intraday price curves | Methods and models
Parameter Estimation
The mean function is estimated by
ˆβ0(t) = ¯R(t) −
p
j=1
ˆβj
¯Fj (t), (11)
The method of moments estimator of β is
ˆβ = ˆF
−1
ˆR, (12)
where
ˆF = N−1
N
n=1
Fc
nj , Fc
nk , j, k = 1, 2, . . . , p (p × p), (13)
ˆR = N−1
N
n=1
Rc
n , Fc
nj , j = 1, 2, . . . , p
T
(p × 1). (14)
37 Xi Zhang | March 20, 2013 37 / 48
Ph.D. dissertation presentation | Functional multifactor regression for intraday price curves | Methods and models
Predictive efficiency
Relative predictive efficiency gains (in percent) defined as
E = 100
MSEPM
MSEPF
− 1 ,
where MSEPM is the MSEP computing using only Mn from model SF, and MSEPF is
the MSEP computed using all factors in the model.
38 Xi Zhang | March 20, 2013 38 / 48
Ph.D. dissertation presentation | Functional multifactor regression for intraday price curves | Methods and models
Confidence Intervals
Asymptotical
ˆβ asymptotically distributed with the mean β and the covariance matrix
N−1
F−1
ΓF−1
.
The matrix Γ is estimated as the long run covariance matrix of the sequence ˆξn.
ˆξn = ˆεn, Fn1 − ¯F1 , . . . , ˆεn, Fnp − ¯Fp
T
.
and
ˆεn(t) = Rn(t) − ˆβ0(t) −
p
j=1
ˆβj Fnj (t).
An R function lrvar with default kernel and bandwidth values is used to estimate
ˆΓ.
The variance of ˆβj is the jth diagonal element of N−1 ˆF−1ˆΓˆF−1
.
Subsampling
39 Xi Zhang | March 20, 2013 39 / 48
Ph.D. dissertation presentation | Functional multifactor regression for intraday price curves | Application to U.S. stocks
Sector Symbol Full Name
Energy
XOM Exxon Mobil Corporation
CVX Chevron Corporation
COP ConocoPhillips
Information MSFT Microsoft Corporation
Technology IBM IBM Corporation
ORCL Oracle Corporation
Financial
CITI Citi Bank
BOA Bank of America Corporation
JPM JPMorgan Chase Co.
Consumer Staples
KO Coca-Cola
WMT Wal-Mart Stores
PG Procter Gamble Co.
Consumer MCD McDonald’s Corporation
Discretionary DIS The Walt Disney Corporation
CMCSA Comcast Corporation
Transportation
FDX FedEx Corporation
JBLU JetBlue Airways Corporation
UPS United Parcel Service, Inc.
40 Xi Zhang | March 20, 2013 40 / 48
Ph.D. dissertation presentation | Functional multifactor regression for intraday price curves | Application to U.S. stocks
Models to test
A simpler model
Rn(t) = β0(t) + β1Mn(t) + β2Ln−1 + εn(t), (15)
PA model with Ln−1 representing the asset daily return;
PI model with Ln−1 representing the index daily return;
FF Fama–French model:
Rn(t) = β0(t) + β1Mn(t) + β2Sn + β3Hn + εn(t), (16)
where Sn and Hn are the Fama–French factors (scalars).
OF model with oil futures as the extra factor:
Rn(t) = β0(t) + β1Mn(t) + β2Cn(t) + εn(t), (17)
41 Xi Zhang | March 20, 2013 41 / 48
Ph.D. dissertation presentation | Functional multifactor regression for intraday price curves | results
Table : Summary of conclusions for the OF model for the stocks
Sector Subsampling Asymptotic
Energy 0/+ +
Information Technology 0 −
Financial 0 −/0
Consumer Staples 0 −/0
Consumer Discretionary 0 0/−
Transportation 0 −
42 Xi Zhang | March 20, 2013 42 / 48
Ph.D. dissertation presentation | Functional multifactor regression for intraday price curves | results
Table : Monte Carol study results out of bootstrapping.
Data size power
Bootstrapped asymptotic subsampling asymptotic subsampling
MSFT1 7 0 74 0
WMT1 5 0 98 3
UPS1 6 0 56 0
43 Xi Zhang | March 20, 2013 43 / 48
Ph.D. dissertation presentation | Summary and Conclusions
Outline
1 Introduction
2 Empirical properties of forecasts with the functional autoregressive model
3 Functional prediction of intraday cumulative returns
4 Functional multifactor regression for intraday price curves
5 Summary and Conclusions
44 Xi Zhang | March 20, 2013 44 / 48
Ph.D. dissertation presentation | Summary and Conclusions
Main results
The sophisticated method of prediction recently proposed in Kargin and
Onatski(2008), actually does not dominate a simpler method based on the
functional principal components. Limits on the quality of predictions are founded
and showed that no other method can exceed them.
Complex functional regression models do not perform better than a simple model.
A functional regression framework that allows us to evaluate quantitatively how
the shapes of intraday price curves depend on the shapes of other curve–valued
factors or on scalar factors is proposed.
Scalar factors have no significant impact on the shape of the price curves.
Oil factors affect the oil companys’ intraday price evolution significantly, but
mostly negative to other stocks.
Asymptotic theory leads to practically useful confidence intervals for the regression
coefficients.
45 Xi Zhang | March 20, 2013 45 / 48
Ph.D. dissertation presentation | Summary and Conclusions
Publication
Kokoszka, P., Miao, H., and Zhang, X. Functional multifactor regression for
intraday price curves. Submitted to Journal of Econometrics.
Kokoszka, P. and Zhang, X. Functional prediction of intra-day cumulative returns.
Statistical Modeling. 12(4):377-398, 2012.
Didericksen, D., Kokoszka, P., and Zhang, X. Empirical properties of forecasts
with the functional autoregressive model. Computational Statistics.
27(2):285-298, 2012.
Kokoszka, P. and Zhang X. Estimation of the autoregressive kernel in the
functional AR(1) process. Utah State University, Utah, USA. 2011.
46 Xi Zhang | March 20, 2013 46 / 48
Ph.D. dissertation presentation
Acknowledgement
Special thanks to: Dr. Piotr S. Kokoszka, and my PhD committee members: Dr. Daniel
Coster, Dr. Richard Cutler, Dr. John Stevens, and Dr. Lie Zhu.
47 Xi Zhang | March 20, 2013 47 / 48
Ph.D. dissertation presentation
Thank You.
48 Xi Zhang | March 20, 2013 48 / 48

More Related Content

What's hot

Welcome to International Journal of Engineering Research and Development (IJERD)
Welcome to International Journal of Engineering Research and Development (IJERD)Welcome to International Journal of Engineering Research and Development (IJERD)
Welcome to International Journal of Engineering Research and Development (IJERD)
IJERD Editor
 
Solving Multidimensional Multiple Choice Knapsack Problem By Genetic Algorith...
Solving Multidimensional Multiple Choice Knapsack Problem By Genetic Algorith...Solving Multidimensional Multiple Choice Knapsack Problem By Genetic Algorith...
Solving Multidimensional Multiple Choice Knapsack Problem By Genetic Algorith...
Shubhashis Shil
 
Kernel methods in machine learning
Kernel methods in machine learningKernel methods in machine learning
Kernel methods in machine learning
butest
 

What's hot (17)

A method for finding an optimal solution of an assignment problem under mixed...
A method for finding an optimal solution of an assignment problem under mixed...A method for finding an optimal solution of an assignment problem under mixed...
A method for finding an optimal solution of an assignment problem under mixed...
 
A NEW METHOD OF CENTRAL DIFFERENCE INTERPOLATION
A NEW METHOD OF CENTRAL DIFFERENCE INTERPOLATIONA NEW METHOD OF CENTRAL DIFFERENCE INTERPOLATION
A NEW METHOD OF CENTRAL DIFFERENCE INTERPOLATION
 
A Tutorial of the EM-algorithm and Its Application to Outlier Detection
A Tutorial of the EM-algorithm and Its Application to Outlier DetectionA Tutorial of the EM-algorithm and Its Application to Outlier Detection
A Tutorial of the EM-algorithm and Its Application to Outlier Detection
 
MUMS: Bayesian, Fiducial, and Frequentist Conference - Spatially Informed Var...
MUMS: Bayesian, Fiducial, and Frequentist Conference - Spatially Informed Var...MUMS: Bayesian, Fiducial, and Frequentist Conference - Spatially Informed Var...
MUMS: Bayesian, Fiducial, and Frequentist Conference - Spatially Informed Var...
 
WSDM2019tutorial
WSDM2019tutorialWSDM2019tutorial
WSDM2019tutorial
 
ecir2019tutorial
ecir2019tutorialecir2019tutorial
ecir2019tutorial
 
Welcome to International Journal of Engineering Research and Development (IJERD)
Welcome to International Journal of Engineering Research and Development (IJERD)Welcome to International Journal of Engineering Research and Development (IJERD)
Welcome to International Journal of Engineering Research and Development (IJERD)
 
The Sample Average Approximation Method for Stochastic Programs with Integer ...
The Sample Average Approximation Method for Stochastic Programs with Integer ...The Sample Average Approximation Method for Stochastic Programs with Integer ...
The Sample Average Approximation Method for Stochastic Programs with Integer ...
 
The Evaluation of Topsis and Fuzzy-Topsis Method for Decision Making System i...
The Evaluation of Topsis and Fuzzy-Topsis Method for Decision Making System i...The Evaluation of Topsis and Fuzzy-Topsis Method for Decision Making System i...
The Evaluation of Topsis and Fuzzy-Topsis Method for Decision Making System i...
 
Approximation in Stochastic Integer Programming
Approximation in Stochastic Integer ProgrammingApproximation in Stochastic Integer Programming
Approximation in Stochastic Integer Programming
 
GJMA-4664
GJMA-4664GJMA-4664
GJMA-4664
 
Sota
SotaSota
Sota
 
Solving Multidimensional Multiple Choice Knapsack Problem By Genetic Algorith...
Solving Multidimensional Multiple Choice Knapsack Problem By Genetic Algorith...Solving Multidimensional Multiple Choice Knapsack Problem By Genetic Algorith...
Solving Multidimensional Multiple Choice Knapsack Problem By Genetic Algorith...
 
Kernel methods in machine learning
Kernel methods in machine learningKernel methods in machine learning
Kernel methods in machine learning
 
A HYBRID COA/ε-CONSTRAINT METHOD FOR SOLVING MULTI-OBJECTIVE PROBLEMS
A HYBRID COA/ε-CONSTRAINT METHOD FOR SOLVING MULTI-OBJECTIVE PROBLEMSA HYBRID COA/ε-CONSTRAINT METHOD FOR SOLVING MULTI-OBJECTIVE PROBLEMS
A HYBRID COA/ε-CONSTRAINT METHOD FOR SOLVING MULTI-OBJECTIVE PROBLEMS
 
CLIM Program: Remote Sensing Workshop, Optimization for Distributed Data Syst...
CLIM Program: Remote Sensing Workshop, Optimization for Distributed Data Syst...CLIM Program: Remote Sensing Workshop, Optimization for Distributed Data Syst...
CLIM Program: Remote Sensing Workshop, Optimization for Distributed Data Syst...
 
効率的反実仮想学習
効率的反実仮想学習効率的反実仮想学習
効率的反実仮想学習
 

Viewers also liked

Presentation _2010
Presentation _2010Presentation _2010
Presentation _2010
Acton Avital
 
Final dissertation presentation 8 13-12
Final dissertation presentation 8 13-12Final dissertation presentation 8 13-12
Final dissertation presentation 8 13-12
Jalaledin
 
Luxury fashion branding_final_thesis
Luxury fashion branding_final_thesisLuxury fashion branding_final_thesis
Luxury fashion branding_final_thesis
Shivangi Singh
 

Viewers also liked (9)

Open Access: Enabling Broadband Connectivity in Kenya
Open Access: Enabling Broadband Connectivity in KenyaOpen Access: Enabling Broadband Connectivity in Kenya
Open Access: Enabling Broadband Connectivity in Kenya
 
Presentation _2010
Presentation _2010Presentation _2010
Presentation _2010
 
Contextual studies prep
Contextual studies prepContextual studies prep
Contextual studies prep
 
Final dissertation presentation 8 13-12
Final dissertation presentation 8 13-12Final dissertation presentation 8 13-12
Final dissertation presentation 8 13-12
 
Dissertation presentation
Dissertation presentation Dissertation presentation
Dissertation presentation
 
Presentation of Dissertation
Presentation of DissertationPresentation of Dissertation
Presentation of Dissertation
 
Dissertation Defense Presentation
Dissertation Defense PresentationDissertation Defense Presentation
Dissertation Defense Presentation
 
Presentation for Dissertation Proposal Defense
Presentation for Dissertation Proposal DefensePresentation for Dissertation Proposal Defense
Presentation for Dissertation Proposal Defense
 
Luxury fashion branding_final_thesis
Luxury fashion branding_final_thesisLuxury fashion branding_final_thesis
Luxury fashion branding_final_thesis
 

Similar to ppt0320defenseday

Thesis seminar
Thesis seminarThesis seminar
Thesis seminar
gvesom
 
KAUST_talk_short.pdf
KAUST_talk_short.pdfKAUST_talk_short.pdf
KAUST_talk_short.pdf
Chiheb Ben Hammouda
 
Bayesian inference for mixed-effects models driven by SDEs and other stochast...
Bayesian inference for mixed-effects models driven by SDEs and other stochast...Bayesian inference for mixed-effects models driven by SDEs and other stochast...
Bayesian inference for mixed-effects models driven by SDEs and other stochast...
Umberto Picchini
 

Similar to ppt0320defenseday (20)

Paper Summary of Disentangling by Factorising (Factor-VAE)
Paper Summary of Disentangling by Factorising (Factor-VAE)Paper Summary of Disentangling by Factorising (Factor-VAE)
Paper Summary of Disentangling by Factorising (Factor-VAE)
 
Estimating Space-Time Covariance from Finite Sample Sets
Estimating Space-Time Covariance from Finite Sample SetsEstimating Space-Time Covariance from Finite Sample Sets
Estimating Space-Time Covariance from Finite Sample Sets
 
Transportation Problem with Pentagonal Intuitionistic Fuzzy Numbers Solved Us...
Transportation Problem with Pentagonal Intuitionistic Fuzzy Numbers Solved Us...Transportation Problem with Pentagonal Intuitionistic Fuzzy Numbers Solved Us...
Transportation Problem with Pentagonal Intuitionistic Fuzzy Numbers Solved Us...
 
Sequential Monte Carlo algorithms for agent-based models of disease transmission
Sequential Monte Carlo algorithms for agent-based models of disease transmissionSequential Monte Carlo algorithms for agent-based models of disease transmission
Sequential Monte Carlo algorithms for agent-based models of disease transmission
 
Thesis seminar
Thesis seminarThesis seminar
Thesis seminar
 
KAUST_talk_short.pdf
KAUST_talk_short.pdfKAUST_talk_short.pdf
KAUST_talk_short.pdf
 
Deep Reinforcement Learning Through Policy Optimization, John Schulman, OpenAI
Deep Reinforcement Learning Through Policy Optimization, John Schulman, OpenAIDeep Reinforcement Learning Through Policy Optimization, John Schulman, OpenAI
Deep Reinforcement Learning Through Policy Optimization, John Schulman, OpenAI
 
MUMS Opening Workshop - Model Uncertainty in Data Fusion for Remote Sensing -...
MUMS Opening Workshop - Model Uncertainty in Data Fusion for Remote Sensing -...MUMS Opening Workshop - Model Uncertainty in Data Fusion for Remote Sensing -...
MUMS Opening Workshop - Model Uncertainty in Data Fusion for Remote Sensing -...
 
Sequential Monte Carlo algorithms for agent-based models of disease transmission
Sequential Monte Carlo algorithms for agent-based models of disease transmissionSequential Monte Carlo algorithms for agent-based models of disease transmission
Sequential Monte Carlo algorithms for agent-based models of disease transmission
 
A Study on Performance Analysis of Different Prediction Techniques in Predict...
A Study on Performance Analysis of Different Prediction Techniques in Predict...A Study on Performance Analysis of Different Prediction Techniques in Predict...
A Study on Performance Analysis of Different Prediction Techniques in Predict...
 
A Study on Youth Violence and Aggression using DEMATEL with FCM Methods
A Study on Youth Violence and Aggression using DEMATEL with FCM MethodsA Study on Youth Violence and Aggression using DEMATEL with FCM Methods
A Study on Youth Violence and Aggression using DEMATEL with FCM Methods
 
Program on Mathematical and Statistical Methods for Climate and the Earth Sys...
Program on Mathematical and Statistical Methods for Climate and the Earth Sys...Program on Mathematical and Statistical Methods for Climate and the Earth Sys...
Program on Mathematical and Statistical Methods for Climate and the Earth Sys...
 
Introduction to Functional Data Analysis
Introduction to Functional Data AnalysisIntroduction to Functional Data Analysis
Introduction to Functional Data Analysis
 
RuleML2015: Input-Output STIT Logic for Normative Systems
RuleML2015: Input-Output STIT Logic for Normative SystemsRuleML2015: Input-Output STIT Logic for Normative Systems
RuleML2015: Input-Output STIT Logic for Normative Systems
 
A walk through the intersection between machine learning and mechanistic mode...
A walk through the intersection between machine learning and mechanistic mode...A walk through the intersection between machine learning and mechanistic mode...
A walk through the intersection between machine learning and mechanistic mode...
 
Tree models with Scikit-Learn: Great models with little assumptions
Tree models with Scikit-Learn: Great models with little assumptionsTree models with Scikit-Learn: Great models with little assumptions
Tree models with Scikit-Learn: Great models with little assumptions
 
Cost indexes
Cost indexesCost indexes
Cost indexes
 
Bayesian inference for mixed-effects models driven by SDEs and other stochast...
Bayesian inference for mixed-effects models driven by SDEs and other stochast...Bayesian inference for mixed-effects models driven by SDEs and other stochast...
Bayesian inference for mixed-effects models driven by SDEs and other stochast...
 
PSIVT2015_slide
PSIVT2015_slidePSIVT2015_slide
PSIVT2015_slide
 
MCQMC 2020 talk: Importance Sampling for a Robust and Efficient Multilevel Mo...
MCQMC 2020 talk: Importance Sampling for a Robust and Efficient Multilevel Mo...MCQMC 2020 talk: Importance Sampling for a Robust and Efficient Multilevel Mo...
MCQMC 2020 talk: Importance Sampling for a Robust and Efficient Multilevel Mo...
 

ppt0320defenseday

  • 1. Ph.D. dissertation presentation Empirical properties of functional regression models and application to high-frequency financial data Xi Zhang Department of Mathematics and Statistics Utah State University March 20, 2013 1 Xi Zhang | March 20, 2013 1 / 48
  • 2. Ph.D. dissertation presentation | Introduction Outline 1 Introduction Functional data analysis High-frequency financial data sets 2 Empirical properties of forecasts with the functional autoregressive model 3 Functional prediction of intraday cumulative returns 4 Functional multifactor regression for intraday price curves 5 Summary and Conclusions 2 Xi Zhang | March 20, 2013 2 / 48
  • 3. Ph.D. dissertation presentation | Introduction | Functional data analysis Functional Data Analysis(FDA) It analyzes data providing information about curves, surfaces or anything else varying over a continuum (time, spatial location, wavelength, probability, etc). The core idea is that curves should be treated as individual and complete statistical objects, rather than as collections of individual observations. Statistical tools of FDA typically rely on some form of smoothing to transform high dimensional or incomplete data building up a curve into a smoother curve that can be described by a smaller number of parameters. The inherent complexity of FDA makes it impossible in a meaningful way to estimate the “distribution” of a random function, or to find estimates that could converge in a reasonable rate, which indicates that the properties of the FPCA are of great importance in FDA. 3 Xi Zhang | March 20, 2013 3 / 48
  • 4. Ph.D. dissertation presentation | Introduction | High-frequency financial data sets 8 years price process 4 Xi Zhang | March 20, 2013 4 / 48
  • 5. Ph.D. dissertation presentation | Introduction | High-frequency financial data sets Cumulative Intraday returns Definition Suppose Pn(tj ), n = 1, . . . , N, j = 1, . . . , m is the price of a financial asset at time tj on day n. The functions rn(tj ) = 100[ln Pn(tj ) − ln Pn(t1)], j = 2, . . . , m, n = 1, . . . , N, are defined as the intraday cumulative returns (CIDR’s/ IDCR’s). The above definition implicitly assumes that tj+1 > tj . we work with one minute averages, so tj+1 − tj = 1 min, and P(tj ) is the average of the maximum and minimum price within the jth minute. 5 Xi Zhang | March 20, 2013 5 / 48
  • 6. Ph.D. dissertation presentation | Introduction | High-frequency financial data sets Cumulative Intraday returns 6 Xi Zhang | March 20, 2013 6 / 48
  • 7. Ph.D. dissertation presentation | Introduction | High-frequency financial data sets Five days closer look 7 Xi Zhang | March 20, 2013 7 / 48
  • 8. Ph.D. dissertation presentation | Introduction | High-frequency financial data sets Why CIDR’s/IDCR’s? Similar to curves of the price Pn(tj ) for a trading day n which are of high interest by stock investors Give more relevant information by showing how the return changes during a trading day Can be treated as continuous curves, one curve per day, adapted to functional data 8 Xi Zhang | March 20, 2013 8 / 48
  • 9. Ph.D. dissertation presentation | Introduction | High-frequency financial data sets High frequency returns 9 Xi Zhang | March 20, 2013 9 / 48
  • 10. Ph.D. dissertation presentation | Empirical properties of forecasts with the functional autoregressive model Outline 1 Introduction 2 Empirical properties of forecasts with the functional autoregressive model Introduction Simulation study Results 3 Functional prediction of intraday cumulative returns 4 Functional multifactor regression for intraday price curves 5 Summary and Conclusions 10 Xi Zhang | March 20, 2013 10 / 48
  • 11. Ph.D. dissertation presentation | Empirical properties of forecasts with the functional autoregressive model | Introduction Functional Autoregressive model(FAR) FAR(1) model Xn+1 = Ψ(Xn) + εn+1, where errors εn and the observations Xn are curves, and the operator Ψ acting on a function X is defined as Ψ(X)(t) = ψ(t, s)X(s)ds, where ψ(t, s) is a bivariate kernel assumed to satisfy ||Ψ|| < 1, where ||Ψ||2 = ψ2 (t, s)dtds. (1) The condition ||Ψ|| < 1 ensures the existence of a stationary causal solution to FAR(1) equations. 11 Xi Zhang | March 20, 2013 11 / 48
  • 12. Ph.D. dissertation presentation | Empirical properties of forecasts with the functional autoregressive model | Introduction Methods Bosq (2000) advocated a standard method by estimating the operator Ψ and forecasting Xn+1 by ˆΨ(Xn). (Estimated Kernel (EK)) The empirical version of bivariate kernel ψ: ˆψp(t, s) = p k, =1 ˆψk ˆvk (t)ˆv (s), (2) where ˆψji = ˆλ−1 i (N − 1)−1 N−1 n=1 Xn, ˆvi Xn+1, ˆvj . (3) where ˆvk , k = 1, 2, . . . , p, the estimated (or empirical) FPC’s (EFPC’s).p is the number of EFPC’s. Kargin and Onatski (2008) proposed a sophisticated method: one step ahead prediction in FAR(1) model based on predictive factors. (Predictive Factors (PF)) 12 Xi Zhang | March 20, 2013 12 / 48
  • 13. Ph.D. dissertation presentation | Empirical properties of forecasts with the functional autoregressive model | Introduction Objective Is the method of Predictive Factors (PF) superior in finite samples to the Estimated Kernel (EK)? 13 Xi Zhang | March 20, 2013 13 / 48
  • 14. Ph.D. dissertation presentation | Empirical properties of forecasts with the functional autoregressive model | Simulation study Data generating process FAR(1) model Xn+1(t) = 1 0 ψ(t, s)Xn(s)ds + εn+1(t), n = 1, 2, . . . , N. Three error processes Brownian bridges ε(1) (t) = BB(t) ε(2) (t) = ξ1 √ 2 sin(2πt) + √ λ √ 2ξ2 cos(2πt) , where ξ1 and ξ2 are independent standard normals, λ can be any constant (in the simulations we use λ = 0.5). ε(3) (t) = ε(2) (t) + aε(1) (t) , 14 Xi Zhang | March 20, 2013 14 / 48
  • 15. Ph.D. dissertation presentation | Empirical properties of forecasts with the functional autoregressive model | Simulation study Kernels Four kernels (defined for (t, s) ∈ [0, 1]2 ): Gaussian : ψ(t, s) = C exp −(t2 + s2 )/2 , Identity : ψ(t, s) = C, Sloping plane (t) : ψ(t, s) = Ct, Sloping plane (s) : ψ(t, s) = Cs. C are chosen such that ||Ψ|| = 0.5 or ||Ψ|| = 0.8. 15 Xi Zhang | March 20, 2013 15 / 48
  • 16. Ph.D. dissertation presentation | Empirical properties of forecasts with the functional autoregressive model | Simulation study Measures of quality of prediction Quantities: En = 1 0 Xn(t) − ˆXn(t) 2 dt and Rn = 1 0 Xn(t) − ˆXn(t) dt. are used to measure the prediction error at time n. 16 Xi Zhang | March 20, 2013 16 / 48
  • 17. Ph.D. dissertation presentation | Empirical properties of forecasts with the functional autoregressive model | Results Comparison of five prediction methods MP Mean Prediction ˆXn+1(t) = 0. NP Naive Prediction ˆXn+1 = Xn. EX Exact ˆXn+1 = Ψ(Xn). EK Estimated Kernel. EKI Estimated Kernel Improved, using ˆλi + ˆb instead of ˆλi . PF Predictive Factors. 17 Xi Zhang | March 20, 2013 17 / 48
  • 18. Ph.D. dissertation presentation | Empirical properties of forecasts with the functional autoregressive model | Results Boxplots of the prediction errors ||Ψ|| = 0.5 En (left) and Rn (right); innovations: ε(1) , kernel: sloping plane (t), N = 100, p = 3. 18 Xi Zhang | March 20, 2013 18 / 48
  • 19. Ph.D. dissertation presentation | Empirical properties of forecasts with the functional autoregressive model | Results Conclusions Based on all 32 sets of boxplots and 32 sets of tables, we report: Taking the autoregressive structure into account reduces prediction errors. None of the Methods EX, EK, EKI uniformly dominates the other. In most cases method EK is the best, or at least as good as the others. In some cases, method PF performs visibly worse than the other methods, but always better than NP. Using the improved estimation does not generally reduce prediction errors. 19 Xi Zhang | March 20, 2013 19 / 48
  • 20. Ph.D. dissertation presentation | Functional prediction of intraday cumulative returns Outline 1 Introduction 2 Empirical properties of forecasts with the functional autoregressive model 3 Functional prediction of intraday cumulative returns Introduction Methods and models Application to US stocks Results 4 Functional multifactor regression for intraday price curves 5 Summary and Conclusions 20 Xi Zhang | March 20, 2013 20 / 48
  • 21. Ph.D. dissertation presentation | Functional prediction of intraday cumulative returns | Introduction Capital Asset Pricing Model(CAPM) The simplest form of celebrated Capital Asset Pricing Model(CAPM): rn = α + βrm,n + εn (4) where rn = 100(ln Pn − ln Pn−1) ≈ 100 Pn − Pn−1 Pn−1 (5) is the return, in percent, over a unit of time on a specific asset, e.g. a stock, and rm,n is the analogously defined return on a relevant market index. 21 Xi Zhang | March 20, 2013 21 / 48
  • 22. Ph.D. dissertation presentation | Functional prediction of intraday cumulative returns | Introduction Objective Model the relationship between the IDCR’s curves for a single asset and those for a market index Evaluate their relevance by comparing their predictive power 22 Xi Zhang | March 20, 2013 22 / 48
  • 23. Ph.D. dissertation presentation | Functional prediction of intraday cumulative returns | Methods and models Simple Functional CAPM (SF) A simple functional CAPM is defined as Yn(t) = α + ψXn(t) + εn(t), t ∈ [0, 1]. (6) A model without the intercept (α ≡ 0), denoted SF*, is also considered. 23 Xi Zhang | March 20, 2013 23 / 48
  • 24. Ph.D. dissertation presentation | Functional prediction of intraday cumulative returns | Methods and models Fully Functional CAPM (FF) This model is defined by the relation Yn(t) = α(t) + ψ(t, s)Xn(s)ds + εn(t), t ∈ [0, 1]. (7) If α ≡ 0, this model is denoted FF*. 24 Xi Zhang | March 20, 2013 24 / 48
  • 25. Ph.D. dissertation presentation | Functional prediction of intraday cumulative returns | Methods and models Functional CAPM with dependent errors This model is defined by 6, but the errors are assumed to follow a functional autoregressive process of order 1, FAR(1) process: εn(t) = ϕ(t, s)εn−1(s)ds + wn(t), (8) where the wn are iid mean zero random functions. Fully Functional CAPM with dependent errors (FFDE). This model is defined by 7 with errors which follow the FAR(1) process. When doing prediction, this model fails, because kernel operators ϕ(t, s) and ψ(t, s) cannot commute. 25 Xi Zhang | March 20, 2013 25 / 48
  • 26. Ph.D. dissertation presentation | Functional prediction of intraday cumulative returns | Methods and models Problems seek to solve Can a simpler model with a scalar coefficient give predictions as good as a model with a kernel coefficient? Does including an intercept improve predictions, or does this extra parameter actually make them worse? Does modeling error correlation lead to improved predictions? 26 Xi Zhang | March 20, 2013 26 / 48
  • 27. Ph.D. dissertation presentation | Functional prediction of intraday cumulative returns | Methods and models Estimation of regression parameters All calculations have been performed in the R package fda. The cumulative returns in one minute resolution are converted to functional objects. 99 Fourier basis functions are used. Empirical functional principal components (EFPC’s) ˆv1, . . . , ˆvp of the data are computed. 27 Xi Zhang | March 20, 2013 27 / 48
  • 28. Ph.D. dissertation presentation | Functional prediction of intraday cumulative returns | Methods and models Evaluate the quality of prediction The integrated mean squared error defined as MSEP(N) = N−1 N n=1 (Yn(t) − ˆYn(t))2 dt. (9) 28 Xi Zhang | March 20, 2013 28 / 48
  • 29. Ph.D. dissertation presentation | Functional prediction of intraday cumulative returns | Application to US stocks Data preparation 10 large U.S. corporations in five sectors Standard & Poor’s 100 index representing market index 1000–day long periods: 01/03/2000 to 02/22/2006 without obvious outliers 29 Xi Zhang | March 20, 2013 29 / 48
  • 30. Ph.D. dissertation presentation | Functional prediction of intraday cumulative returns | Application to US stocks Description of 10 Stocks representing five sectors Sector Stocks Full Name 1000 days period Energy XOM Exxon Mobil 05/25/2000-05/19/2004 CVX Chevron 10/10/2001-07/23/2004 12/13/2004-02/22/2006 Information MSFT Microsoft 05/25/2000-05/19/2004 Technology IBM IBM 01/03/2000-12/24/2003 Financial CITI Citi Bank 10/17/2000-03/07/2005 BOA Bank of America 03/13/2001-12/19/2005 Consumer KO Coca-Cola 05/25/2000-05/19/2004 Staples WMT Wal-Mart Stores 05/25/2000-05/19/2004 Consumer MCD McDonald’s 10/17/2000-03/07/2005 Discretionary DIS The Walt Disney 05/25/2000-05/19/2004 30 Xi Zhang | March 20, 2013 30 / 48
  • 31. Ph.D. dissertation presentation | Functional prediction of intraday cumulative returns | Results Prediction results (1) 31 Xi Zhang | March 20, 2013 31 / 48
  • 32. Ph.D. dissertation presentation | Functional prediction of intraday cumulative returns | Results Prediction results (2) 32 Xi Zhang | March 20, 2013 32 / 48
  • 33. Ph.D. dissertation presentation | Functional prediction of intraday cumulative returns | Results Conclusions Models with intercept, i.e. SF and FF, make better prediction than models without intercept i.e. SF* and FF*. The latter should not be used. Modeling error dependence with a functional AR(1) model does not improve MSEP’s. The two models with intercept, i.e. SF and FF, do NOT dominate each other. They have almost the same MSEP’s. SF model is recommended if minimizing the MSEP is the only concern. It is intuitive, its estimation is straightforward, and the prediction equation is very simple. 33 Xi Zhang | March 20, 2013 33 / 48
  • 34. Ph.D. dissertation presentation | Functional multifactor regression for intraday price curves Outline 1 Introduction 2 Empirical properties of forecasts with the functional autoregressive model 3 Functional prediction of intraday cumulative returns 4 Functional multifactor regression for intraday price curves Motivation Methods and models Application to U.S. stocks results 5 Summary and Conclusions 34 Xi Zhang | March 20, 2013 34 / 48
  • 35. Ph.D. dissertation presentation | Functional multifactor regression for intraday price curves | Motivation Objective Whether adding additional factors beyond IDCR’s/CIDR’s on a market index are statistically significant and whether they lead to improved predictions? 35 Xi Zhang | March 20, 2013 35 / 48
  • 36. Ph.D. dissertation presentation | Functional multifactor regression for intraday price curves | Methods and models A general factor model Factor model Rn(t) = β0(t) + p j=1 βj Fnj (t) + εn(t). (10) The parameters of the model are the mean function β0(·) and the vector of the coefficients: β = [β1, . . . , βp]T . 36 Xi Zhang | March 20, 2013 36 / 48
  • 37. Ph.D. dissertation presentation | Functional multifactor regression for intraday price curves | Methods and models Parameter Estimation The mean function is estimated by ˆβ0(t) = ¯R(t) − p j=1 ˆβj ¯Fj (t), (11) The method of moments estimator of β is ˆβ = ˆF −1 ˆR, (12) where ˆF = N−1 N n=1 Fc nj , Fc nk , j, k = 1, 2, . . . , p (p × p), (13) ˆR = N−1 N n=1 Rc n , Fc nj , j = 1, 2, . . . , p T (p × 1). (14) 37 Xi Zhang | March 20, 2013 37 / 48
  • 38. Ph.D. dissertation presentation | Functional multifactor regression for intraday price curves | Methods and models Predictive efficiency Relative predictive efficiency gains (in percent) defined as E = 100 MSEPM MSEPF − 1 , where MSEPM is the MSEP computing using only Mn from model SF, and MSEPF is the MSEP computed using all factors in the model. 38 Xi Zhang | March 20, 2013 38 / 48
  • 39. Ph.D. dissertation presentation | Functional multifactor regression for intraday price curves | Methods and models Confidence Intervals Asymptotical ˆβ asymptotically distributed with the mean β and the covariance matrix N−1 F−1 ΓF−1 . The matrix Γ is estimated as the long run covariance matrix of the sequence ˆξn. ˆξn = ˆεn, Fn1 − ¯F1 , . . . , ˆεn, Fnp − ¯Fp T . and ˆεn(t) = Rn(t) − ˆβ0(t) − p j=1 ˆβj Fnj (t). An R function lrvar with default kernel and bandwidth values is used to estimate ˆΓ. The variance of ˆβj is the jth diagonal element of N−1 ˆF−1ˆΓˆF−1 . Subsampling 39 Xi Zhang | March 20, 2013 39 / 48
  • 40. Ph.D. dissertation presentation | Functional multifactor regression for intraday price curves | Application to U.S. stocks Sector Symbol Full Name Energy XOM Exxon Mobil Corporation CVX Chevron Corporation COP ConocoPhillips Information MSFT Microsoft Corporation Technology IBM IBM Corporation ORCL Oracle Corporation Financial CITI Citi Bank BOA Bank of America Corporation JPM JPMorgan Chase Co. Consumer Staples KO Coca-Cola WMT Wal-Mart Stores PG Procter Gamble Co. Consumer MCD McDonald’s Corporation Discretionary DIS The Walt Disney Corporation CMCSA Comcast Corporation Transportation FDX FedEx Corporation JBLU JetBlue Airways Corporation UPS United Parcel Service, Inc. 40 Xi Zhang | March 20, 2013 40 / 48
  • 41. Ph.D. dissertation presentation | Functional multifactor regression for intraday price curves | Application to U.S. stocks Models to test A simpler model Rn(t) = β0(t) + β1Mn(t) + β2Ln−1 + εn(t), (15) PA model with Ln−1 representing the asset daily return; PI model with Ln−1 representing the index daily return; FF Fama–French model: Rn(t) = β0(t) + β1Mn(t) + β2Sn + β3Hn + εn(t), (16) where Sn and Hn are the Fama–French factors (scalars). OF model with oil futures as the extra factor: Rn(t) = β0(t) + β1Mn(t) + β2Cn(t) + εn(t), (17) 41 Xi Zhang | March 20, 2013 41 / 48
  • 42. Ph.D. dissertation presentation | Functional multifactor regression for intraday price curves | results Table : Summary of conclusions for the OF model for the stocks Sector Subsampling Asymptotic Energy 0/+ + Information Technology 0 − Financial 0 −/0 Consumer Staples 0 −/0 Consumer Discretionary 0 0/− Transportation 0 − 42 Xi Zhang | March 20, 2013 42 / 48
  • 43. Ph.D. dissertation presentation | Functional multifactor regression for intraday price curves | results Table : Monte Carol study results out of bootstrapping. Data size power Bootstrapped asymptotic subsampling asymptotic subsampling MSFT1 7 0 74 0 WMT1 5 0 98 3 UPS1 6 0 56 0 43 Xi Zhang | March 20, 2013 43 / 48
  • 44. Ph.D. dissertation presentation | Summary and Conclusions Outline 1 Introduction 2 Empirical properties of forecasts with the functional autoregressive model 3 Functional prediction of intraday cumulative returns 4 Functional multifactor regression for intraday price curves 5 Summary and Conclusions 44 Xi Zhang | March 20, 2013 44 / 48
  • 45. Ph.D. dissertation presentation | Summary and Conclusions Main results The sophisticated method of prediction recently proposed in Kargin and Onatski(2008), actually does not dominate a simpler method based on the functional principal components. Limits on the quality of predictions are founded and showed that no other method can exceed them. Complex functional regression models do not perform better than a simple model. A functional regression framework that allows us to evaluate quantitatively how the shapes of intraday price curves depend on the shapes of other curve–valued factors or on scalar factors is proposed. Scalar factors have no significant impact on the shape of the price curves. Oil factors affect the oil companys’ intraday price evolution significantly, but mostly negative to other stocks. Asymptotic theory leads to practically useful confidence intervals for the regression coefficients. 45 Xi Zhang | March 20, 2013 45 / 48
  • 46. Ph.D. dissertation presentation | Summary and Conclusions Publication Kokoszka, P., Miao, H., and Zhang, X. Functional multifactor regression for intraday price curves. Submitted to Journal of Econometrics. Kokoszka, P. and Zhang, X. Functional prediction of intra-day cumulative returns. Statistical Modeling. 12(4):377-398, 2012. Didericksen, D., Kokoszka, P., and Zhang, X. Empirical properties of forecasts with the functional autoregressive model. Computational Statistics. 27(2):285-298, 2012. Kokoszka, P. and Zhang X. Estimation of the autoregressive kernel in the functional AR(1) process. Utah State University, Utah, USA. 2011. 46 Xi Zhang | March 20, 2013 46 / 48
  • 47. Ph.D. dissertation presentation Acknowledgement Special thanks to: Dr. Piotr S. Kokoszka, and my PhD committee members: Dr. Daniel Coster, Dr. Richard Cutler, Dr. John Stevens, and Dr. Lie Zhu. 47 Xi Zhang | March 20, 2013 47 / 48
  • 48. Ph.D. dissertation presentation Thank You. 48 Xi Zhang | March 20, 2013 48 / 48