Scribd
Upload
23 views

Chapter 1

...

Uploaded by

Teo Sheng
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
23 views

Chapter 1

...

Uploaded by

Teo Sheng
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 6

BEEQ 3013 Econometrics

Chapter 1: Time Series Model Analysis I

1.1 The nature of time series data

1.2 Static models and finite distributed lags model (A221)


Static model Dynamic model
Definition In a static model, the effect of explanatory The dynamic models include lagged effects of dependent and independent
variables on the dependent variable operates in variables
the same period.
The DL (Distributed Lag) models include lagged values of the
explanatory variables. In a distributed lag model the effect of a certain
explanatory is spread over time. @ We allow one or more variables to
affect y with a lag[kesan tertangguh]
Model Y t =β 0 + β 1 z t +ut t = 1,2,…,n (time series) gf r t=α 0 + δ 0 ρ et +δ 1 ρ e t−1 +δ 2 ρ e t−2 +ut
gf r t = general fertility rate(children born per 1,000 women childbearing
Modelling a contemporaneous relationship age)
between y and z ρ e t = real dollar value personal tax exemption
δ 0= Immediate change in fertility (y) due one-dollar increase in ρ e t
LRP= In a distributed lag model, the eventual change in the
dependent variable given a permanent, one-unit increase in the
BEEQ 3013 Econometrics

independent variable (δ 0 +δ 1+ δ 2)
A221 Question 1a/ A172_Q1a) ii)
Explain the meaning of the finite distributed lag model. [5]
Answer: A finite distributed lag model (FDL) assumes a linear relationship between a dependent variable y𝑦 and several lags of an
independent variable 𝑥. Equation 1 shows a finite distributed lag model of order q.

yt=α+β0xt+β1xt−1+...+βqxt−q+et (1)
The coefficient βs𝛽𝑠 is an s𝑠-period delay multiplier, and the coefficient β0𝛽0, the immediate (contemporaneous) impact of a change
in x𝑥 on y𝑦, is an impact multiplier. If x𝑥 increases by one unit today, the change in y𝑦 will be β0+β1+...+βs𝛽0+𝛽1+...+𝛽𝑠 after s𝑠 periods;
this quantity is called the s𝑠-period interim multiplier. The total multiplier is equal to the sum of all β𝛽s in the model.

Notes: Finite Distributed Lag (LRP)


Let said
gf r t=α 0 + δ 0 ρ et +δ 1 ρ e t−1 +δ 2 ρ e t−2 +ut

 Long Run Propensity refers to δ 0 +δ 1+ δ 2


 We cannot just sum up all the standard error
 Now will become θ0 =δ 0+ δ 1 +δ 2
 δ 0=θ 0−δ 1−δ 2
 gf r t=α 0 +(θ0 −δ 1−δ 2 )ρ e t + δ 1 ρ et −1+ δ 2 ρ et −2+ ut
 gf r t=α 0 +θ 0 ρ e t −δ 1 ρ e t−δ 2 ρ et + δ 1 ρ e t−1 +δ 2 ρ e t−2 +ut
 gf r t=α 0 +θ 0 ρ e t + δ 1 (ρ e t−1− ρe t )+δ 2 (ρ et −2−ρ e t )+ut
θ0
 =t
Se (θ0 ) s
 看 P > α = fail to reject H0 or Se(θ 0) > θ0 =δ 0+ δ 1 +δ 2 (not significance at any level)
BEEQ 3013 Econometrics

Explain Two Properties of OLS under the classical assumption. [5]


Answer:
1. The stochastic process {(xt1, xt2, …, xtk, yt ): t ( 1, 2, …, n} follows the linear model

Y t =β 0 + β 1 X t 1+ …+ β k X tk +u t
where {ut : t = 1, 2, …, n} is the sequence of errors or disturbances. Here, n is the number of observations (time periods).
In the notation xtj, t denotes the time period, and j is, as usual, a label to indicate one of the k explanatory variables. The terminology used in cross-sectional
regression applies here: yt is the dependent variable, explained variable, or regressand; the xtj are the independent variables, explanatory variables, or
regressors. We should think of Assumption TS.1 as being essentially the same as Assumption MLR.1 (the first cross-sectional assumption), but we are now
specifying a linear model for time series data. The examples covered in Section 10.2 can be cast as (10.8) by appropriately defining xtj. For example, equation
(10.5) is obtained by setting xt1= zt, xt2= zt-1, and xt3= zt-2.

2. No perfect Collinearity
In the sample (and therefore in the underlying time series process), no independent variable is constant nor a perfect linear combination of the
others. That assumption does allow the explanatory variables to be correlated, but it rules out perfect correlation in the sample

3. Zero Conditional Mean


For each t, the expected value of the error ut , given the explanatory variables for all time periods, is zero. Mathematically
E(ut uX) = 0, t =1, 2, …, n.
BEEQ 3013 Econometrics

Assumption TS.3 implies that the error at time t, ut , is uncorrelated with each explanatory variable in every time period. The fact that this is
stated in terms of the conditional expectation means that we must also correctly specify the functional relationship between yt and the
explanatory variables. If ut is independent of X and E(ut ) = 0.

4. Homoskedasticity
Conditional on X, the variance of ut is the same for all t: Var(ut X) = Var(ut) = o2 , t = 1, 2, …, n.
This assumption means that Var(ut uX) cannot depend on X—it is sufficient that ut and X are independent—and that Var(ut ) must be constant over time.
When TS.4 does not hold, we say that the errors are heteroskedastic, just as in the cross-sectional case

5. No Serial Correlation
Conditional on X, the errors in two different time periods are uncorrelated: Corr(ut ,us X) 5 0, for all t = s
The easiest way to think of this assumption is to ignore the conditioning on X. Then, Assumption TS.5 is simply

Corr(ut,us)= 0, for all t = s

(This is how the no serial correlation assumption is stated when X is treated as non random.) When considering whether Assumption TS.5 is likely to hold,
we focus on equation (10.12) because of its simple interpretation

6. Normality
The errors ut are independent of X and are independently and identically distributed as Normal (0,o2 ).

A182_Question 1a)
Explain the meaning of long run propensity or long-run multiplier. [5]
1.3 Functional form and dummy variables (refer textbook 356-362)
BEEQ 3013 Econometrics

1.4 Trending in regression analysis


A182_Q1b)
Give the reason why we include the trend variable in our estimation model
1.5 Stationary and nonstationary
Stationary process : A time series process where the marginal and all joint distributions are invariant across time. = weakly dependent
( hubungan antara pemboleh ubah dengan time weakly), means variance and covariance are constant
Non Stationary process: A time series process whose joint distributions are not constant across different epochs = highly persistence
(variable and time t very high weakly – another time)

Autocorrelation Function (ACF) & Correlogram


Yk
Formula : ρk = Notes: The value ρk must between -1 and 1
Y0

A182_Question 1(c)
Explain the meaning of a correlogram and draw the correlogram for the case of highly persistent time series.[5]
A correlogram (also called Auto Correlation Function ACF Plot or Autocorrelation plot) is a visual way to show serial correlation in data that
changes over time (i.e. time series data). Serial correlation (also called autocorrelation) is where an error at one point in time travels to a
subsequent point in time. For example, you might overestimate the value of your stock market investments for the first quarter, leading to an
overestimate of values for following quarters. Draw= loot at slide at page 9
BEEQ 3013 Econometrics

1.6 Weakly dependent time series

1.7 Using highly persistent time series

You might also like