Financial Econometrics

Financial Econometrics
Financial econometrics is defined as the application of
statistical techniques to problems in finance. Financial
econometrics can be useful for
• testing theories in finance,
• determining asset prices or returns,
• testing hypotheses concerning the relationships between
variables,
• examining the effect on financial markets of changes in
economic conditions,
• forecasting future values of financial variables and for
financial decision-making.
Steps involved in formulating an econometric model
• General statement of the problem:
• This will usually involve the formulation of a theoretical model, or intuition from financial
theory that two or more variables should be related to one another in a certain way.
• Collection of data relevant to the model:
• The data required may be available electronically through a financial information provider,
such as Reuters or from published government figures.
• Choice of estimation method relevant to the model:
• For example, is a single equation or multiple equation technique to be used?
• Statistical evaluation of the model:
• What assumptions were required to estimate the parameters of the model optimally?
Were these assumptions satisfied by the data or the model?
• Evaluation of the model from a theoretical perspective:
• Are the parameter estimates of the sizes and signs that the theory or intuition
from step 1 suggested?
• Use of model:
• When a researcher is finally satisfied with the model, it can then be used for
testing the theory specified in step 1, or for formulating forecasts or suggested
courses of action.
Linear Regression Model
 Linear
Regression
Model
• Regression is concerned with
describing and evaluating the
relationship between a given
variable and one or more other
variables.
• More specifically, regression is an
attempt to explain movements in a
variable by reference to movements
in one or more other variables.
 Linear
Simple Regression
Regression yt = α+βxt +ut
Model
• Regression is concerned with
describing and evaluating the
relationship between a given
variable and one or more other
variables.
• More specifically, regression is an
attempt to explain movements in a
variable by reference to movements
in one or more other variables.
 Linear
Simple Regression
Regression yt = α+βxt +ut
Model
• Regression is concerned with
describing and evaluating the Multiple Regression
relationship between a given yt = α+β1x1t +β2x2t+---+ut
variable and one or more other
variables.
• More specifically, regression is an
attempt to explain movements in a
variable by reference to movements
in one or more other variables.
 Linear
Simple Regression
Regression yt = α+βxt +ut
Model
• Regression is concerned with
describing and evaluating the Multiple Regression
relationship between a given yt = α+β1x1t +β2x2t+---+ut
variable and one or more other
variables.
• More specifically, regression is an
Linearity and Possible
attempt to explain movements in a
variable by reference to movements Forms for the Regression
in one or more other variables. Function
 Forms of
Simple Regression
Linear Regression yt = α+βxt +ut
Model
• Yt = AX t e
β ut

• ln Yt = ln(A) +βln Xt +ut Multiple Regression

• where A andβ to be estimated. Now let
α = ln(A),
yt = α+β1x1t +β2x2t+---+ut
• yt = lnYt and xt = lnXt
• yt = α+βxt +ut
• On the other hand, some models are
intrinsically non-linear, e.g. yt = α+βx t +ut
γ
Linearity and Possible
• Such models cannot be estimated using Forms for the Regression
OLS, but might be estimable using a non- Function
linear estimation method
 Estimating
Linear Regression Model

Ordinary Least Square Method

 Ordinary Least Square Method

The assumptions
concerning the
disturbance term
 Ordinary Least Square Method
• The aim of the ordinary least
Principle squares method is to minimize the
prediction error, between the
predicted and real values.
• It takes into account the sum of
squared errors instead of the errors
as they are because sometimes
they can be negative or positive
and they could sum up to a nearly
null value.
 Ordinary Least Square Method

Principle Xi Yi
5 3
The Regression Model:
2 4
Yi= β0+β1Xi + ui 3 8
Estimated regression equation: 2 9
i = + X
0 1 i

i = 11.01 - 1.67X i
 Ordinary Least Square Method

Principle Xi Yi i

5 3 2.66
The Regression Model:
2 4 7.67
Yi= β0+β1Xi + ui
3 8 6
Estimated regression equation:
2 9 7.67
i = + X
0 1 i
Residual: = 11.01 - 1.67X
i i
i = Y -
i i
 Ordinary Least Square Method

Principle Minimize Ʃ i = Ʃ(Yi – 0 – 1Xi)

2 2

FOC : = 0 and = 0
Normal
Equations ƩYi – n 0 – 1ƩXi = 0 --------(1)

Ʃ Xi Yi – 0 Ʃ Xi– 1ƩXi = 0 --------(2)

2
 Ordinary Least Square Method

Principle Solve the normal equations

simultaneously to obtain the
Normal estimates
Equations =
1

0 = – 1
Estimators
 Ordinary Least Square Method

Principle
Yi = b0 + b1X1i + b2X2i + ui
Normal
Equations

Estimators
 Matrix Approach to Regression
• Calculations increase substantially as the number of
independent variables increase.
• Matrix notation can aid in solving larger regressions
algebraically.
• The following solution works with any number of
independent variables, and is therefore extremely
flexible.
Matrix Approach to Regression
Matrix Approach to Regression
Matrix Approach to Regression
Q&A