28
PARTIAL ADJUSTMENT 1 The idea behind the partial adjustment model is that, while a dependent variable Y may be related to an explanatory variable X, there is inertia in the system. t t t u X Y 2 1 *

PARTIAL ADJUSTMENT 1 The idea behind the partial adjustment model is that, while a dependent variable Y may be related to an explanatory variable X, there

Embed Size (px)

Citation preview

Page 1: PARTIAL ADJUSTMENT 1 The idea behind the partial adjustment model is that, while a dependent variable Y may be related to an explanatory variable X, there

PARTIAL ADJUSTMENT

1

The idea behind the partial adjustment model is that, while a dependent variable Y may be related to an explanatory variable X, there is inertia in the system.

ttt uXY 21*

Page 2: PARTIAL ADJUSTMENT 1 The idea behind the partial adjustment model is that, while a dependent variable Y may be related to an explanatory variable X, there

2

The actual value of Yt is a compromise between its value in the previous time period, Yt–1, and the value justified by the current value of the explanatory variable.

PARTIAL ADJUSTMENT

ttt uXY 21*

Page 3: PARTIAL ADJUSTMENT 1 The idea behind the partial adjustment model is that, while a dependent variable Y may be related to an explanatory variable X, there

3

Let us denote the justified value of Y (or target, desired, or appropriate value, however you want to describe it) as Yt*, given by the equation shown.

PARTIAL ADJUSTMENT

ttt uXY 21*

Page 4: PARTIAL ADJUSTMENT 1 The idea behind the partial adjustment model is that, while a dependent variable Y may be related to an explanatory variable X, there

4

In the partial adjustment model it is assumed that the actual increase in the dependent variable from time t – 1 to time t, Yt – Yt–1, is proportional to the discrepancy between the justified value and the previous value, Yt* – Yt–1.

PARTIAL ADJUSTMENT

1*1 tttt YYYY ttt uXY 21

*

Page 5: PARTIAL ADJUSTMENT 1 The idea behind the partial adjustment model is that, while a dependent variable Y may be related to an explanatory variable X, there

5

l is usually described as the speed of adjustment.

PARTIAL ADJUSTMENT

1*1 tttt YYYY ttt uXY 21

*

Page 6: PARTIAL ADJUSTMENT 1 The idea behind the partial adjustment model is that, while a dependent variable Y may be related to an explanatory variable X, there

6

The actual value in the current time period is therefore a weighted average of the desired value and the previous actual value. l logically should lie in the interval 0 (no change at all) to 1 (full adjustment in the current time period).

PARTIAL ADJUSTMENT

1*1 tttt YYYY

1* 1 ttt YYY

ttt uXY 21*

Page 7: PARTIAL ADJUSTMENT 1 The idea behind the partial adjustment model is that, while a dependent variable Y may be related to an explanatory variable X, there

7

Substituting for Yt* from the original relationship, one obtains a regression specification in terms of observable variables of the ADL(1,0) form.

.1,, 32211

PARTIAL ADJUSTMENT

1*1 tttt YYYY

1* 1 ttt YYY

ttt uXY 21*

ttt

ttt

tttt

uYX

uYX

YuXY

1321

121

121

1

1

where

Page 8: PARTIAL ADJUSTMENT 1 The idea behind the partial adjustment model is that, while a dependent variable Y may be related to an explanatory variable X, there

8

It follows that its dynamics are those of the ADK(1,0) model discussed in the previous slideshow. The short-run impact of X on Y is given by the coefficient b2 = g2l.

PARTIAL ADJUSTMENT

1*1 tttt YYYY

1* 1 ttt YYY

ttt uXY 21*

ttt

ttt

tttt

uYX

uYX

YuXY

1321

121

121

1

1

Page 9: PARTIAL ADJUSTMENT 1 The idea behind the partial adjustment model is that, while a dependent variable Y may be related to an explanatory variable X, there

9

The long-run effect can be evaluated by finding the relationship between the equilibrium values of Y and X.

PARTIAL ADJUSTMENT

1*1 tttt YYYY

1* 1 ttt YYY

YXY 121

ttt uXY 21*

ttt

ttt

tttt

uYX

uYX

YuXY

1321

121

121

1

1

Page 10: PARTIAL ADJUSTMENT 1 The idea behind the partial adjustment model is that, while a dependent variable Y may be related to an explanatory variable X, there

10

1*1 tttt YYYY

1* 1 ttt YYY

YXY 121

XY 21

XY 21

The long-run effect turns out to be g2. This makes sense, since this is the coefficient in the equation determining the desired value of Y.

ttt uXY 21*

ttt

ttt

tttt

uYX

uYX

YuXY

1321

121

121

1

1

PARTIAL ADJUSTMENT

Page 11: PARTIAL ADJUSTMENT 1 The idea behind the partial adjustment model is that, while a dependent variable Y may be related to an explanatory variable X, there

11

Brown's Habit Persistence Model of the aggregate consumption function was an early example of the use of a partial adjustment model. Desired consumption is related to wage income, nonwage income and a dummy variable.

PARTIAL ADJUSTMENT

tttt uANWWC 321*

Page 12: PARTIAL ADJUSTMENT 1 The idea behind the partial adjustment model is that, while a dependent variable Y may be related to an explanatory variable X, there

12

The reason for separating income into wage income and nonwage income is that the marginal propensity to consume is likely to be higher for wage income than for nonwage income.

PARTIAL ADJUSTMENT

tttt uANWWC 321*

Page 13: PARTIAL ADJUSTMENT 1 The idea behind the partial adjustment model is that, while a dependent variable Y may be related to an explanatory variable X, there

13

Brown fitted the model with a time series which included observations before and after the Second World War. The dummy variable, A, was defined to be 0 for the prewar observations and 1 for the postwar ones.

PARTIAL ADJUSTMENT

tttt uANWWC 321*

Page 14: PARTIAL ADJUSTMENT 1 The idea behind the partial adjustment model is that, while a dependent variable Y may be related to an explanatory variable X, there

14

As the name of his model suggests, Brown hypothesized that there was a lag in the response of consumption to changes in income and he used a partial adjustment model.

PARTIAL ADJUSTMENT

tttt uANWWC 321* 1*

1 tttt CCCC 1

* 1 ttt CCC

Page 15: PARTIAL ADJUSTMENT 1 The idea behind the partial adjustment model is that, while a dependent variable Y may be related to an explanatory variable X, there

15

Substituting for desired consumption, one obtains current consumption in terms of current income and previous consumption.

PARTIAL ADJUSTMENT

tttt

ttttt

uACNWW

CuANWWC

1321

1321

1

1

tttt uANWWC 321* 1*

1 tttt CCCC 1

* 1 ttt CCC

Page 16: PARTIAL ADJUSTMENT 1 The idea behind the partial adjustment model is that, while a dependent variable Y may be related to an explanatory variable X, there

16

Brown fitted the model with aggregate Canadian data for the years 1926–1949, omitting the years 1942–1945, using a simultaneous equations estimation technique. The variables were measured in billions of Canadian dollars at constant prices. t statistics are in parentheses.

PARTIAL ADJUSTMENT

tttt uANWWC 321* 1*

1 tttt CCCC 1

* 1 ttt CCC

tttt

ttttt

uACNWW

CuANWWC

1321

1321

1

1

ACNWWC tttt 69.022.028.061.090.0ˆ1

(7.4) (4.2) (2.8)(4.8) (4.8)

Page 17: PARTIAL ADJUSTMENT 1 The idea behind the partial adjustment model is that, while a dependent variable Y may be related to an explanatory variable X, there

17

The short-run marginal propensities to consume out of wage and nonwage income are 0.61 and 0.28, respectively. Note that the former is indeed larger than the latter. How would you test whether the difference is significant?

PARTIAL ADJUSTMENT

tttt uANWWC 321* 1*

1 tttt CCCC 1

* 1 ttt CCC

tttt

ttttt

uACNWW

CuANWWC

1321

1321

1

1

ACNWWC tttt 69.022.028.061.090.0ˆ1

(7.4) (4.2) (2.8)(4.8) (4.8)

Page 18: PARTIAL ADJUSTMENT 1 The idea behind the partial adjustment model is that, while a dependent variable Y may be related to an explanatory variable X, there

18

The coefficient of lagged consumption literally implies that, if consumption in the previous year had been 1 billion dollars greater, consumption this year would have been 0.22 billion dollars greater.

PARTIAL ADJUSTMENT

tttt uANWWC 321* 1*

1 tttt CCCC 1

* 1 ttt CCC

tttt

ttttt

uACNWW

CuANWWC

1321

1321

1

1

ACNWWC tttt 69.022.028.061.090.0ˆ1

(7.4) (4.2) (2.8)(4.8) (4.8)

Page 19: PARTIAL ADJUSTMENT 1 The idea behind the partial adjustment model is that, while a dependent variable Y may be related to an explanatory variable X, there

19

That is a bit clumsy. It is better to interpret it with reference to l in the adjustment process. It implies that the speed of adjustment is 0.78, meaning that 0.78 of the difference between desired and actual consumption is eliminated in one year.

PARTIAL ADJUSTMENT

tttt uANWWC 321* 1*

1 tttt CCCC 1

* 1 ttt CCC

tttt

ttttt

uACNWW

CuANWWC

1321

1321

1

1

ACNWWC tttt 69.022.028.061.090.0ˆ1

(7.4) (4.2) (2.8)(4.8) (4.8)

Page 20: PARTIAL ADJUSTMENT 1 The idea behind the partial adjustment model is that, while a dependent variable Y may be related to an explanatory variable X, there

20

With the speed of adjustment, we can derive the long-run propensities to consume. We do this by dividing the short-run propensities by l. We find that the long-run propensity to consume out of wages is 0.78.

PARTIAL ADJUSTMENT

tttt uANWWC 321* 1*

1 tttt CCCC 1

* 1 ttt CCC

tttt

ttttt

uACNWW

CuANWWC

1321

1321

1

1

ACNWWC tttt 69.022.028.061.090.0ˆ1

(7.4) (4.2) (2.8)(4.8) (4.8)

78.022.0161.0

2

g 36.022.0128.0

3

g

Page 21: PARTIAL ADJUSTMENT 1 The idea behind the partial adjustment model is that, while a dependent variable Y may be related to an explanatory variable X, there

21

ACNWWC tttt 69.022.028.061.090.0ˆ1

Similarly, the long-run propensity to consume nonwage income is 0.36. Note that, in this example, there is not a great difference between the short-run and long-run propensities. That is because the speed of adjustment is rapid.

(7.4) (4.2) (2.8)(4.8)

tttt uANWWC 321* 1*

1 tttt CCCC 1

* 1 ttt CCC

tttt

ttttt

uACNWW

CuANWWC

1321

1321

1

1

(4.8)

78.022.0161.0

2

g 36.022.0128.0

3

g

PARTIAL ADJUSTMENT

Page 22: PARTIAL ADJUSTMENT 1 The idea behind the partial adjustment model is that, while a dependent variable Y may be related to an explanatory variable X, there

============================================================Dependent Variable: LGHOUS Method: Least Squares Sample(adjusted): 1960 2003 Included observations: 44 after adjusting endpoints ============================================================ Variable CoefficientStd. Errort-Statistic Prob. ============================================================ C 0.073957 0.062915 1.175499 0.2467 LGDPI 0.282935 0.046912 6.031246 0.0000 LGPRHOUS -0.116949 0.027383 -4.270880 0.0001 LGHOUS(-1) 0.707242 0.044405 15.92699 0.0000============================================================R-squared 0.999795 Mean dependent var 6.379059Adjusted R-squared 0.999780 S.D. dependent var 0.421861S.E. of regression 0.006257 Akaike info criter-7.223711Sum squared resid 0.001566 Schwarz criterion -7.061512Log likelihood 162.9216 F-statistic 65141.75Durbin-Watson stat 1.810958 Prob(F-statistic) 0.000000============================================================

22

Here is the result of a parallel logarithmic regression of expenditure on housing on DPI and relative price, using the Demand Functions data set.

PARTIAL ADJUSTMENT

Page 23: PARTIAL ADJUSTMENT 1 The idea behind the partial adjustment model is that, while a dependent variable Y may be related to an explanatory variable X, there

23

The short-run income elasticity is 0.28.

PARTIAL ADJUSTMENT

============================================================Dependent Variable: LGHOUS Method: Least Squares Sample(adjusted): 1960 2003 Included observations: 44 after adjusting endpoints ============================================================ Variable CoefficientStd. Errort-Statistic Prob. ============================================================ C 0.073957 0.062915 1.175499 0.2467 LGDPI 0.282935 0.046912 6.031246 0.0000 LGPRHOUS -0.116949 0.027383 -4.270880 0.0001 LGHOUS(-1) 0.707242 0.044405 15.92699 0.0000============================================================R-squared 0.999795 Mean dependent var 6.379059Adjusted R-squared 0.999780 S.D. dependent var 0.421861S.E. of regression 0.006257 Akaike info criter-7.223711Sum squared resid 0.001566 Schwarz criterion -7.061512Log likelihood 162.9216 F-statistic 65141.75Durbin-Watson stat 1.810958 Prob(F-statistic) 0.000000============================================================

Page 24: PARTIAL ADJUSTMENT 1 The idea behind the partial adjustment model is that, while a dependent variable Y may be related to an explanatory variable X, there

24

The short-run price elasticity is 0.12. Both of these elasticities are very low. This is because housing is a good example of a category of expenditure with slow adjustment.

PARTIAL ADJUSTMENT

============================================================Dependent Variable: LGHOUS Method: Least Squares Sample(adjusted): 1960 2003 Included observations: 44 after adjusting endpoints ============================================================ Variable CoefficientStd. Errort-Statistic Prob. ============================================================ C 0.073957 0.062915 1.175499 0.2467 LGDPI 0.282935 0.046912 6.031246 0.0000 LGPRHOUS -0.116949 0.027383 -4.270880 0.0001 LGHOUS(-1) 0.707242 0.044405 15.92699 0.0000============================================================R-squared 0.999795 Mean dependent var 6.379059Adjusted R-squared 0.999780 S.D. dependent var 0.421861S.E. of regression 0.006257 Akaike info criter-7.223711Sum squared resid 0.001566 Schwarz criterion -7.061512Log likelihood 162.9216 F-statistic 65141.75Durbin-Watson stat 1.810958 Prob(F-statistic) 0.000000============================================================

Page 25: PARTIAL ADJUSTMENT 1 The idea behind the partial adjustment model is that, while a dependent variable Y may be related to an explanatory variable X, there

25

The adjustment rate implicit in the coefficient of LGHOUS(–1) is only 0.29. People do not change their housing quickly in response to changes in income and price. If anything, the estimated rate seems a little high.

PARTIAL ADJUSTMENT

============================================================Dependent Variable: LGHOUS Method: Least Squares Sample(adjusted): 1960 2003 Included observations: 44 after adjusting endpoints ============================================================ Variable CoefficientStd. Errort-Statistic Prob. ============================================================ C 0.073957 0.062915 1.175499 0.2467 LGDPI 0.282935 0.046912 6.031246 0.0000 LGPRHOUS -0.116949 0.027383 -4.270880 0.0001 LGHOUS(-1) 0.707242 0.044405 15.92699 0.0000============================================================R-squared 0.999795 Mean dependent var 6.379059Adjusted R-squared 0.999780 S.D. dependent var 0.421861S.E. of regression 0.006257 Akaike info criter-7.223711Sum squared resid 0.001566 Schwarz criterion -7.061512Log likelihood 162.9216 F-statistic 65141.75Durbin-Watson stat 1.810958 Prob(F-statistic) 0.000000============================================================

Page 26: PARTIAL ADJUSTMENT 1 The idea behind the partial adjustment model is that, while a dependent variable Y may be related to an explanatory variable X, there

26

The long-run income elasticity is 0.97, not far off the income elasticity in the static model in the first sequence for this chapter, 1.03.

PARTIAL ADJUSTMENT

============================================================Dependent Variable: LGHOUS Method: Least Squares Sample(adjusted): 1960 2003 Included observations: 44 after adjusting endpoints ============================================================ Variable CoefficientStd. Errort-Statistic Prob. ============================================================ C 0.073957 0.062915 1.175499 0.2467 LGDPI 0.282935 0.046912 6.031246 0.0000 LGPRHOUS -0.116949 0.027383 -4.270880 0.0001 LGHOUS(-1) 0.707242 0.044405 15.92699 0.0000============================================================R-squared 0.999795 Mean dependent var 6.379059Adjusted R-squared 0.999780 S.D. dependent var 0.421861S.E. of regression 0.006257 Akaike info criter-7.223711Sum squared resid 0.001566 Schwarz criterion -7.061512Log likelihood 162.9216 F-statistic 65141.75Durbin-Watson stat 1.810958 Prob(F-statistic) 0.000000============================================================

97.07072.012829.0

long-run income elasticity

Page 27: PARTIAL ADJUSTMENT 1 The idea behind the partial adjustment model is that, while a dependent variable Y may be related to an explanatory variable X, there

============================================================Dependent Variable: LGHOUS Method: Least Squares Sample(adjusted): 1960 2003 Included observations: 44 after adjusting endpoints ============================================================ Variable CoefficientStd. Errort-Statistic Prob. ============================================================ C 0.073957 0.062915 1.175499 0.2467 LGDPI 0.282935 0.046912 6.031246 0.0000 LGPRHOUS -0.116949 0.027383 -4.270880 0.0001 LGHOUS(-1) 0.707242 0.044405 15.92699 0.0000============================================================R-squared 0.999795 Mean dependent var 6.379059Adjusted R-squared 0.999780 S.D. dependent var 0.421861S.E. of regression 0.006257 Akaike info criter-7.223711Sum squared resid 0.001566 Schwarz criterion -7.061512Log likelihood 162.9216 F-statistic 65141.75Durbin-Watson stat 1.810958 Prob(F-statistic) 0.000000============================================================

27

The long run price elasticity is 0.40, again not far from the estimate in the static model, 0.48. In this example the long-run elasticities are much greater than the short-run ones because the speed of adjustment is slow.

long-run price elasticity 40.07072.011169.0

PARTIAL ADJUSTMENT

Page 28: PARTIAL ADJUSTMENT 1 The idea behind the partial adjustment model is that, while a dependent variable Y may be related to an explanatory variable X, there

Copyright Christopher Dougherty 2013.

These slideshows may be downloaded by anyone, anywhere for personal use.

Subject to respect for copyright and, where appropriate, attribution, they may be

used as a resource for teaching an econometrics course. There is no need to

refer to the author.

The content of this slideshow comes from Section 11.4 of C. Dougherty,

Introduction to Econometrics, fourth edition 2011, Oxford University Press.

Additional (free) resources for both students and instructors may be

downloaded from the OUP Online Resource Centre

http://www.oup.com/uk/orc/bin/9780199567089/.

Individuals studying econometrics on their own who feel that they might benefit

from participation in a formal course should consider the London School of

Economics summer school course

EC212 Introduction to Econometrics

http://www2.lse.ac.uk/study/summerSchools/summerSchool/Home.aspx

or the University of London International Programmes distance learning course

20 Elements of Econometrics

www.londoninternational.ac.uk/lse.

2013.01.20