Professional Documents
Culture Documents
William Greene
Department of Economics
University of South Florida
Part 10: Time Series Applications [ 2/62]
ˆ 1 N ˆ i 1 ˆi or
(2) Average estimates = i1 Ni1
N 1 ˆi N
ˆ= (1 / N)Ni1ˆ
i
Function of averages:
ˆi
1 (1 / N)Ni1
In each case, each term i has variance O(1/Ti )
N
Each average has variance O(1/N) i=1
(1/N)O(1/Ti )
Expect consistency of estimates of long run effects.
Part 10: Time Series Applications [ 6/62]
Country Means
(Average the T observations for each i)
logYi,t i i log Yi,t 1 i x it i,t
i
i , =
1 i 1
logYi i i log Yi,1 i x i i
i contains log Yi,1
Estimates are inconsistent. But,
tT1 log y it
logYi ,
Ti
tT2 log y i,t 1 y i,T y i,0
log Yi,1 logYi logYi T (y) / Ti
Ti Ti
logYi i i log Yi,1 i x i i i i (logYi T (y) / Ti ) i x i i
i i i i
xi T (y) / Ti
1 i 1 i 1 i 1 i
Part 10: Time Series Applications [ 7/62]
Pooling
A Mixed/Fixed Approach
ki k k wki
wki ~ N [0,1]
0.757
5.67
6.45
22.18
Part 10: Time Series Applications [ 15/62]
Modeling an Economic
Time Series
Observed y0, y1, …, yt,…
What is the “sample”
Random sampling?
The “observation window”
Part 10: Time Series Applications [ 18/62]
Estimators
Functions of sums of observations
Law of large numbers?
Nonindependent observations
What does “increasing sample size” mean?
Asymptotic properties? (There are no finite
sample properties.)
Part 10: Time Series Applications [ 19/62]
For example,…
Part 10: Time Series Applications [ 21/62]
Decomposed
Part 10: Time Series Applications [ 22/62]
Side Issue
How does y(t) = 1.220175 y(t-1) - 0.262198 y(t-2) + a behave?
y(t) = 1.220175 y(t-1) + a is obviously explosive.
1.220175 0.262198
How to tell: A =
1 0
Smallest (possibly complex) root must be greater than 1.0.
Part 10: Time Series Applications [ 26/62]
1 2 .5 9
8 .0 1
3 .4 3
V a ri a b l e
-1 . 1 5
-5 . 7 3
-1 0 . 3 1
0 20 40 60 80 100
T
YT ET
Part 10: Time Series Applications [ 27/62]
1
1 (L) (L) (L) ...
2 3
1 L
Stationary series can be inverted
Autoregressive vs. moving average form of series
Part 10: Time Series Applications [ 29/62]
VECTOR
AUTOREGRESSION
Part 10: Time Series Applications [ 30/62]
Vector Autoregression
The vector autoregression (VAR) model is one of the most successful, flexible,
and easy to use models for the analysis of multivariate time series. It is
a natural extension of the univariate autoregressive model to dynamic multivariate
time series. The VAR model has proven to be especially useful for
describing the dynamic behavior of economic and financial time series and
for forecasting. It often provides superior forecasts to those from univariate
time series models and elaborate theory-based simultaneous equations
models. Forecasts from VAR models are quite flexible because they can be
made conditional on the potential future paths of specified variables in the
model.
In addition to data description and forecasting, the VAR model is also
used for structural inference and policy analysis. In structural analysis, certain
assumptions about the causal structure of the data under investigation
are imposed, and the resulting causal impacts of unexpected shocks or
innovations to specified variables on the variables in the model are summarized.
These causal impacts are usually summarized with impulse response
functions and forecast error variance decompositions.
Eric Zivot: http://faculty.washington.edu/ezivot/econ584/notes/varModels.pdf
Part 10: Time Series Applications [ 31/62]
VAR
y1 (t ) 11 y1 (t 1) 12 y2 (t 1) 13 y3 (t 1) 1 x(t ) 1 (t )
y2 (t ) 21 y1 (t 1) 22 y2 (t 1) 23 y3 (t 1) 2 x(t ) 2 (t )
y3 (t ) 31 y1 (t 1) 32 y2 (t 1) 33 y3 (t 1) 3 x(t ) 3 (t )
(In Zivot's examples,
1. Exchange rates
2. y(t)=stock returns, interest rates, indexes of industrial production,
rate of inflation
Part 10: Time Series Applications [ 32/62]
VAR Formulation
y (t) = y (t-1) + x(t) + (t)
SUR with identical regressors.
Granger Causality: Nonzero off diagonal elements in
y1 (t ) 11 y1 (t 1) 12 y2 (t 1) 13 y3 (t 1) 1 x(t ) 1 (t )
y2 (t ) 21 y1 (t 1) 22 y2 (t 1) 23 y3 (t 1) 2 x(t ) 2 (t )
y3 (t ) 31 y1 (t 1) 32 y2 (t 1) 33 y3 (t 1) 3 x(t ) 3 (t )
Hypothesis: y2 does not Granger cause y1: 12 =0
Part 10: Time Series Applications [ 33/62]
Impulse Response
y (t) = y (t-1) + x(t) + (t)
By backward substitution or using the lag operator (text, 943)
y (t) x(t) x(t-1) 2 x(t-2) +... (ad infinitum)
+ (t) (t-1) 2 (t-2) + ...
[ P must converge to 0 as P increases. Roots inside unit circle.]
Consider a one time shock (impulse) in the system, = 2 in period t
Consider the effect of the impulse on y1 ( s ), s=t, t+1,...
Effect in period t is 0. 2 is not in the y1 equation.
2 affects y2 in period t, which affects y1 in period t+1. Effect is 12
In period t+2, the effect from 2 periods back is ( 2 )12
... and so on.
Part 10: Time Series Applications [ 34/62]
Zivot’s Data
Part 10: Time Series Applications [ 35/62]
Impulse Responses
Part 10: Time Series Applications [ 36/62]
Bollerslev/Ghysel, 1974
Part 10: Time Series Applications [ 38/62]
ARCH Model
Part 10: Time Series Applications [ 39/62]
GARCH Model
Part 10: Time Series Applications [ 40/62]
MACROECONOMIC DATA
Part 10: Time Series Applications [ 42/62]
Nonstationary Data
Part 10: Time Series Applications [ 44/62]
Integrated Series
Part 10: Time Series Applications [ 45/62]
Stationary Data
Part 10: Time Series Applications [ 46/62]
Integrated Processes
Integration of order (P) when the P’th differenced
series is stationary
Stationary series are I(0)
Trending series are often I(1). Then yt – yt-1 = yt is
I(0). [Most macroeconomic data series.]
Accelerating series might be I(2). Then
(yt – yt-1)- (yt – yt-1) = 2yt is I(0)
Historic Hyperinflations
Interwar Germany, Hungary 1946, Zimbabwe 2007-2008
Money stock in hyperinflationary economies.
Price level in Venezuela in 2016 - 2017
Part 10: Time Series Applications [ 47/62]
A Unit Root?
How to test for = 1?
By construction: εt – εt-1 = ( - 1)εt-1 + ut
Test for = ( - 1) = 0 using regression?
Variance goes to 0 faster than 1/T. Need a new
table; can’t use standard t tables.
Dickey – Fuller tests
This invokes the possibility of unit roots in
economic data. (Are there?)
Nonstationary series
Implications for conventional analysis
Part 10: Time Series Applications [ 48/62]
y t 0 y t 1 t Ll1 l y t l t
Different restrictions on parameters produce the model.
The parameter of interest is 0.
Augmented Dickey-Fuller Tests:
Unit root test H0 : < 1 vs. H1 : 1.
KPSS Tests:
Null hypothesis is stationarity. Alternative is broadly
defined as nonstationary.
Part 10: Time Series Applications [ 49/62]
KPSS Test-1
Part 10: Time Series Applications [ 50/62]
KPSS Test-2
Part 10: Time Series Applications [ 51/62]
Application
Implications
COINTEGRATION
Part 10: Time Series Applications [ 56/62]
Cointegrated Processes:
Real DPI and Real Consumption
6967
5775
4582
Va ria b le
3390
2198
1006
0 41 82 123 164 205
Ob serv.#
REALDPI REALCONS
Part 10: Time Series Applications [ 57/62]
Lack of Cointegration
Divergent Series?
2 1 .0 4
1 6 .8 5
1 2 .6 7
Va ria b le
8 .4 8
4 .3 0
.1 2
0 20 40 60 80 100
Ob serv.#
YT XT
Part 10: Time Series Applications [ 58/62]
Cointegration
X(t) and y(t) are obviously I(1)
Looks like any linear combination of x(t) and y(t) will
also be I(1)
Does a model y(t) = x(t) + u(t) where u(t) is I(0)
make any sense? How can u(t) be I(0)?
In fact, there is a linear combination, [1,-] that is I(0).
y(t) = .1*t + noise, x(t) = .2*t + noise
y(t) and x(t) have a common trend
y(t) and x(t) are cointegrated.
Part 10: Time Series Applications [ 59/62]
Cointegrated Variables?
Part 10: Time Series Applications [ 60/62]
1 .5 0
1 .0 0
.5 0
ET
.0 0
-. 5 0
-1 . 0 0
-1 . 5 0
0 17 34 51 68 85 102
Ob serv.#
Part 10: Time Series Applications [ 61/62]
Cointegrating Relationships
Implications:
Long run vs. short run relationships
Problems of spurious regressions (as
usual)
Problem for existing empirical
studies: Regressions involving
variables of different integration.
E.g., regressions of flows on stocks
Part 10: Time Series Applications [ 62/62]
APPENDIX
Part 10: Time Series Applications [ 64/62]
Autocorrelation in Regression
Yt = b’xt + εt
Cov(εt, εt-1) ≠ 0
Ex. RealConst = a + bRealIncome + εt U.S. Data, quarterly, 1950-2000
Part 10: Time Series Applications [ 65/62]
Autocorrelation
How does it arise?
What does it mean?
Modeling approaches
Classical – direct: corrective
Estimation that accounts for autocorrelation
Inference in the presence of autocorrelation
Contemporary – structural
Model the source
Incorporate the time series aspect in the model
Part 10: Time Series Applications [ 66/62]
= u2/(1- 2) + 0
Part 10: Time Series Applications [ 67/62]
+----------------------------------------------------+
| Ordinary least squares regression |
| LHS=REALCONS Mean = 2999.436 |
| Autocorrel Durbin-Watson Stat. = .0920480 |
| Rho = cor[e,e(-1)] = .9539760 |
+----------------------------------------------------+
+---------+--------------+----------------+--------+---------+----------+
|Variable | Coefficient | Standard Error |t-ratio |P[|T|>t] | Mean of X|
+---------+--------------+----------------+--------+---------+----------+
Constant -80.3547488 14.3058515 -5.617 .0000
REALDPI .92168567 .00387175 238.054 .0000 3341.47598
| Robust VC Newey-West, Periods = 10 |
Constant -80.3547488 41.7239214 -1.926 .0555
REALDPI .92168567 .01503516 61.302 .0000 3341.47598
+---------------------------------------------+
| AR(1) Model: e(t) = rho * e(t-1) + u(t) |
| Final value of Rho = .998782 |
| Iter= 6, SS= 118367.007, Log-L=-941.371914 |
| Durbin-Watson: e(t) = .002436 |
| Std. Deviation: e(t) = 490.567910 |
| Std. Deviation: u(t) = 24.206926 |
| Durbin-Watson: u(t) = 1.994957 |
| Autocorrelation: u(t) = .002521 |
| N[0,1] used for significance levels |
+---------------------------------------------+
+---------+--------------+----------------+--------+---------+----------+
|Variable | Coefficient | Standard Error |b/St.Er.|P[|Z|>z] | Mean of X|
+---------+--------------+----------------+--------+---------+----------+
Constant 1019.32680 411.177156 2.479 .0132
REALDPI .67342731 .03972593 16.952 .0000 3341.47598
RHO .99878181 .00346332 288.389 .0000
Part 10: Time Series Applications [ 69/62]
Detecting Autocorrelation
Use residuals directly (Durbin and Watson)
d= Tt 2 (e t et 1 ) 2 / Tt 1et2 2(1 r )
Assumes normally distributed disturbances, strictly
exogenous regressors
Variable addition (LM test) (Godfrey)
Based on yt = ’xt + (εt-1 + ut)
Use regression residuals et and test = 0 in
regression of et on xt and et-1
Assumes consistency of b.
Part 10: Time Series Applications [ 70/62]
Reinterpreting Autocorrelation
Regression form
yt ' xt t , t t 1 ut
Error Correction Form
yt yt 1 '(xt xt 1 ) ( yt 1 ' xt 1 ) ut , ( 1)
' xt the equilibrium
The model describes adjustment of y t to equilibrium when x t changes.