Scribd
Upload
117 views36 pages

Econometric S Lecture 43

The document discusses stationary and non-stationary time series data. It defines concepts like moments, strict stationarity, weak stationarity, and integrated processes. It also explains unit root tests like the Augmented Dickey-Fuller test and Phillips-Perron test that are used to determine if a time series is stationary or non-stationary.

Uploaded by

Khurram Aziz
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
117 views36 pages

Econometric S Lecture 43

The document discusses stationary and non-stationary time series data. It defines concepts like moments, strict stationarity, weak stationarity, and integrated processes. It also explains unit root tests like the Augmented Dickey-Fuller test and Phillips-Perron test that are used to determine if a time series is stationary or non-stationary.

Uploaded by

Khurram Aziz
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 36

In The Name of Allah, The Most Beneficent, The Most Merciful

Econometrics
Lecture 43

Dr. Sayyid Salman Rizavi


Stationary & Non-Stationary data
Unit Root Test
Cointegration & Error Correction Model
Time Series and Econometrics

Univariate Analysis: An analysis of a single sequence


of data

Multivariate time-series analysis: An analysis of


several sets of data for the same sequence of time

Econometricians Vs Time Series Analysts


Time Series and Econometrics

Econometricians emphasized economic theory

Theories applied without temporal structure

Time series analyst did not believe in economic


theory

From 1970s econometricians and time series


analysts became closer

Now theories are applied while accounting for time


series properties
Stationary and Non-Stationary Time Series
Some Concepts
Moments: a moment is a specific quantitative
measure of the shape of a set of points. Moments
are of different types e.g. raw, about mean etc.

The first raw moment is the mean.


First moment about mean is zero.
Second moment about mean is the variance.
Stationary and Non-Stationary Time Series

Some Concepts
Joint distribution of (1 ), (2 ), (3 ) . . . ( ) is
complicated so we usually define the

= = ( )
= 2 = (2 )
= 1, 2 = (1 , 2 )
Stationary and Non-Stationary Time Series
Strict or Strong Stationary
A series is called strict stationary if the joint
distribution of any set of observations
(1 ), (2 ), (3 ) . . . ( )
is the same as joint distribution of
(1 + ), (2 + ), (3 + ) . . . ( + )
for all and .
Stationary and Non-Stationary Time Series
Strict or Strong Stationary
All moments are independent of t.

The mean, variance, and all higher order


moments of the joint distribution of any
combination of variables
(1 ), (2 ), (3 ) . . . ( ) are constant &
independent of t.

Very strong assumption

Statistical Properties do not change over time.


Stationary and Non-Stationary Time Series
Now define = 2 1 and call it a lag.
As joint distribution of (1 ), 2 and that of (1 +
Stationary and Non-Stationary Time Series

Second Order or Weak Stationary (covariance


stationarity)

A series is called weakly stationary if its mean


and variance do not depend on (are constant)
and the depends only on the lag .

Stationary series revert in the long run to their


mean.
Stationary and Non-Stationary Time Series

Non-Stationary Data
In real life most of the data is non-stationary.
Variables that increase over time are non-
stationary.
Mean and variance are not constant over time.
We need differencing and/or detrending.
We can define a non-stationary model as =
+ where mean is a function of time (linear
or non-linear) and is second order stationary
series.
Stationary and Non-Stationary Time Series
Non-Stationary Data

OLS should not be used on non-stationary data.


(e.g. problem of spurious regression). We
usually can transform variables by taking
differences of using lags if the data becomes
stationary at difference or lag.
Stationary and Non-Stationary Time Series
Types of Non-Stationary Data

Random Walk with Drift: = + 1 +

Deterministic Trend Process: = 0 + 1 +

To induce Stationarity both will require different


treatment
Differencing
Detrending
Stationary and Non-Stationary Time Series

Random Walk with drift


Stationary and Non-Stationary Time Series

Deterministic Trend
Stationary and Non-Stationary Time Series

Integreted Non-Stationary Series


If a non-stationary series is difference times in
order to become stationary, it is said to be integrated
of order .
If ~ ~ (0)
0 is a stationary series. It will cross the mean
frequently.
(1) is a series containing one unit root
Stationary and Non-Stationary Time Series

Integreted Non-Stationary Series

Most of the economic and financial series contain


a single unit root (Some may be stationary)
However prices have been seen in various
researches to have 2 unit roots. (stationary at the
second levels)
Stationary and Non-Stationary Time Series

Unit Root Test


A unit root test tests is used to know if a time
series variable is non-stationary using an
autoregressive model.
The famous tests include
Augmented DickeyFuller test and
the Phillipe-Perron test.
The null hypothesis for these tests is the existence
of a unit root.
Stationary and Non-Stationary Time Series

Why do we need to test for Non-Stationarity?

The stationarity or non-stationarity of a series can


strongly influence its behavior and properties.
Spurious regressions
The parameters are misleading
If variables in the model are not stationary, the
usual t-ratios will not follow a t-distribution, so
various tests will not be valid
Stationary and Non-Stationary Time Series
Augmented Dickey-Fuller unit-root test ()
performs the augmented Dickey-Fuller
test that a variable follows a unit-root process.

The null hypothesis is that the variable contains a


unit root.
Stationarity Tests
Augmented Dickey-Fuller unit-root test ()
Syntax:
dfuller varname [if] [in] [, options]

Menu:
Statistics > Time series > Tests >
Augmented Dickey-Fuller unit-root test

Type help dfuller to seek help for the command


Stationary and Non-Stationary Time Series

Augmented Dickey-Fuller unit-root test ()


Characteristics of Non-Stationary Series
Characteristics of the Dickey-Fuller Regression
series Model
No Constant , No time = 1 +
Trend
Constant, without time = + 1 +
trend
Constant and time trend
= + 1 + +
Use constant (drift) when series fluctuates against a non-zero
mean.
Stationary and Non-Stationary Time Series

Phillips-Perron unit-root test ()


pperron performs the Phillips-Perron test that a
variable has a unit root.

The null hypothesis is that the variable contains a


unit root, and the alternative is that the variable
was generated by a stationary process.

pperron uses Newey-West standard errors to


account for serial correlation, (so it allows for
autocorrelated residuals)
Stationarity Tests
Phillips-Perron unit-root test ()
Syntax:
pperron varname [if] [in] [, options]

Menu:
Statistics > Time series > Tests > Phillips-Perron unit-
root test

Type help pperron to seek help for the command


Stationary and Non-Stationary Time Series
Examples of unit root test using Stata
Use the commands:


Seems to be
stationary
Stationary and Non-Stationary Time Series
Examples of unit root test using Stata
Use the commands:

Reject H0 of non-stationarity
Stationary and Non-Stationary Time Series
Examples of unit root test using Stata
Use the commands:
1

Seems to follow
a random walk
with drift
Stationary and Non-Stationary Time Series
Examples of unit root test using Stata

We can not reject H0. The series is non-stationary


Stationary and Non-Stationary Time Series
Examples of options with dfuller

trend specifies that a trend term be included in


the associated regression
Stationary and Non-Stationary Time Series
Examples of options with dfuller

drift indicates that the process under the null


hypothesis is a random walk with nonzero drift.
Stationary and Non-Stationary Time Series
Examples of options with dfuller

regress specifies that the associated regression


table appear in the output

NOTE: see that


coefficient of
L1 is not
significant
Stationary and Non-Stationary Time Series
Examples of options with dfuller
lags(#) specifies the number of lagged difference
terms to include in the covariate list.
Stationary and Non-Stationary Time Series
Now checking the first difference

The series dowclose is stationary at first


difference
Stationary and Non-Stationary Time Series
Phillip Perron Test Example

Perrons test also shows that dowclose is not


stationary at level
Stationary and Non-Stationary Time Series
Phillip Perron Test Example

Perrons test also shows that dowclose is


stationary at first difference level.
Thank you Very Much

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy