0
DATA STATIONER ANDDATA NON STATIONER
Example- Real GDP (2000 Prices) Seasonally Adjusted      (1) Plot Time Series - Non-Stationary                   (i.e. tim...
These are Examples of                               Non-Stationary Time Series16000                                       ...
Unit Root Testing    (1) Plot First Difference of Time Series - Stationary                    (i.e. constant mean and corr...
Informal Procedures to identify non-stationary processes(2)     Diagnostic test - Correlogram           Correlation betwee...
These are Examples of                                     Stationary Time Series 8000                                     ...
What is a Spurious Regression?A Spurious or Nonsensical relationship may  result when one Non-stationary time series is  r...
Symptoms of Likely Presence of Spurious              Regression• If the R2 of the regression is greater than the  Durbin-W...
What is a “Unit Root”?If a Non-Stationary Time Series Yt hasto be “differenced” d times to make itstationary, then Yt is s...
Unit Root Testing: Formal Tests toEstablish Stationarity of Time Series•   Dickey-Fuller (DF) Test•   Augmented Dickey-Ful...
Analisis time series
Upcoming SlideShare
Loading in...5
×

Analisis time series

882

Published on

Published in: Business, Technology
0 Comments
0 Likes
Statistics
Notes
  • Be the first to comment

  • Be the first to like this

No Downloads
Views
Total Views
882
On Slideshare
0
From Embeds
0
Number of Embeds
0
Actions
Shares
0
Downloads
15
Comments
0
Likes
0
Embeds 0
No embeds

No notes for slide

Transcript of "Analisis time series"

  1. 1. DATA STATIONER ANDDATA NON STATIONER
  2. 2. Example- Real GDP (2000 Prices) Seasonally Adjusted (1) Plot Time Series - Non-Stationary (i.e. time varying mean and correlogram non-zero) GDP Y 100 75 50 1955 1960 1965 1970 1975 1980 1985 1990 1995 2000 Time 1.00 r ACF-Y 0.75 0.50 0.25 0 5 10 k 2
  3. 3. These are Examples of Non-Stationary Time Series16000 12000 10000 900014000 8000 10000 8000 700012000 8000 6000 600010000 6000 5000 8000 4000 4000 4000 6000 3000 2000 4000 2000 2000 2000 0 0 1000 92 94 96 98 00 02 04 92 94 96 98 00 02 04 92 94 96 98 00 02 04 92 94 96 98 00 02 04 AUSTRALIA CANADA CHINA GERMANY24000 45000 50000 700020000 40000 6000 40000 35000 500016000 30000 30000 400012000 25000 20000 3000 8000 20000 2000 10000 4000 15000 1000 0 10000 0 0 92 94 96 98 00 02 04 92 94 96 98 00 02 04 92 94 96 98 00 02 04 92 94 96 98 00 02 04 HONGKONG JAPAN KOREA MALAYSIA 7000 30000 12000 60000 6000 25000 10000 50000 5000 20000 8000 40000 4000 15000 6000 3000 30000 10000 4000 2000 20000 1000 5000 2000 0 0 0 10000 92 94 96 98 00 02 04 92 94 96 98 00 02 04 92 94 96 98 00 02 04 92 94 96 98 00 02 04 SINGAPORE TAIWAN UK USA
  4. 4. Unit Root Testing (1) Plot First Difference of Time Series - Stationary (i.e. constant mean and correlogram zero) 3 DY 2 1 0 -1 1955 1960 1965 1970 1975 1980 1985 1990 1995 2000 Time 1.0 r ACF-DY 0.5 0.0 -0.5 0 5 10 k 4
  5. 5. Informal Procedures to identify non-stationary processes(2) Diagnostic test - Correlogram Correlation between 1980 and 1980 + k. For stationary process correlogram dies out rapidly. Series has no memory. 1980 is not related to 1985. 0.50 whitenoise 0.25 0.00 -0.25 0 50 100 150 200 250 300 350 400 450 500 1.0 ACF-whitenoise 0.5 0.0 -0.5 0 5 10 5
  6. 6. These are Examples of Stationary Time Series 8000 6000 4000 6000 6000 4000 3000 4000 4000 2000 2000 2000 2000 0 1000 0 0 -2000 0 -2000 -2000 -4000 -4000 -1000 -4000 -6000 -6000 -2000 -6000 92 94 96 98 00 02 04 92 94 96 98 00 02 04 92 94 96 98 00 02 04 92 94 96 98 00 02 04 AUST CAN CHI GERM12000 12000 12000 2000 8000 8000 8000 1000 4000 4000 4000 0 0 0 0 -1000 -4000 -4000 -4000 -2000 -8000 -8000 -8000-12000 -12000 -12000 -3000 92 94 96 98 00 02 04 92 94 96 98 00 02 04 92 94 96 98 00 02 04 92 94 96 98 00 02 04 HONG JAP KOR MAL 3000 12000 5000 30000 4000 2000 8000 3000 20000 1000 2000 4000 10000 1000 0 0 0 0 -1000 -1000 -4000 -2000 -10000 -2000 -3000 -3000 -8000 -4000 -20000 92 94 96 98 00 02 04 92 94 96 98 00 02 04 92 94 96 98 00 02 04 92 94 96 98 00 02 04 SING TWN UKK US
  7. 7. What is a Spurious Regression?A Spurious or Nonsensical relationship may result when one Non-stationary time series is regressed against one or more Non-stationary time seriesThe best way to guard against Spurious Regressions is to check for “Cointegration” of the variables used in time series modeling
  8. 8. Symptoms of Likely Presence of Spurious Regression• If the R2 of the regression is greater than the Durbin-Watson Statistic• If the residual series of the regression has a Unit Root
  9. 9. What is a “Unit Root”?If a Non-Stationary Time Series Yt hasto be “differenced” d times to make itstationary, then Yt is said to containd “Unit Roots”. It is customary todenote Yt ~ I(d) which reads “Yt isintegrated of order d”
  10. 10. Unit Root Testing: Formal Tests toEstablish Stationarity of Time Series• Dickey-Fuller (DF) Test• Augmented Dickey-Fuller (ADF) Test• Phillips-Perron (PP) Unit Root Test• Dickey-Pantula Unit Root Test• GLS Transformed Dickey-Fuller Test• ERS Point Optimal Test• KPSS Unit Root Test• Ng and Perron Test
  1. A particular slide catching your eye?

    Clipping is a handy way to collect important slides you want to go back to later.

×