kuliah 11

33
* KULIAH 11 * Heteroskedasticity * Serial correlation * Multicollinerity * Normality * Omitted variables

Upload: babu

Post on 12-Jan-2016

27 views

Category:

Documents


0 download

DESCRIPTION

Heteroskedasticity Serial correlation Multicollinerity Normality Omitted variables. KULIAH 11. What’s Heteroskedasticity ?. Varians residual tdk konstan. Prototype. Penyebab. Error learning  misal : belajar mengetik - PowerPoint PPT Presentation

TRANSCRIPT

Page 1: KULIAH 11

* KULIAH 11

*Heteroskedasticity*Serial correlation

*Multicollinerity

*Normality

*Omitted variables

Page 2: KULIAH 11

*What’s Heteroskedasticity?

Page 3: KULIAH 11

*Varians residual tdk konstan

Prototype

Page 4: KULIAH 11

*Penyebab*Error learning misal: belajar mengetik

*Sampel yang beragam rumahtangga dgn pendptn, perusahaan berbagai level

*Adanya outlier

*Omitting variables

*Sebaran data tidak normal

*incorrect data transformation (e.g., ratio or first difference transformations) and

*incorrect functional form (e.g., linear versus log–linear models)

* lebih sering terjadi pada data cross section

Page 5: KULIAH 11

*Efek thd estimasi

*BLUE?

*Linear Unbiased but not efficient LU

Homoscedastic?

Which is the Homoscedast

ic?

Page 6: KULIAH 11

*KOnsekuensi*Bagaimana estimasi yg diperoleh terkait varians yg tidak

konstan?

*- Signifikansi ?

*- CI ?

* misleading …

Page 7: KULIAH 11

*Mendeteksi heteroskedasticity *Nature of problem (functional form review )

*Periksa Grafik residual

*Tes statistik

Page 8: KULIAH 11

*Tes Statistik*Bahwa residual berkorelasi dengan varians

*Park Test

* signifikan residuals are heteroskedastic

* weakness: may not satisfy the OLS assumptions and may itself be heteroscedastic

*Glejser Test

* weakness: the error term vi has some

problems in that its expected value is nonzero,

it is serially correlated and ironically it is

heteroscedastic, some models are non linear.

Page 9: KULIAH 11

*Ex: Park & Glejser test

Page 10: KULIAH 11

H0: residuals are homoskedasticH1: residuals are heteroskedastic

Page 11: KULIAH 11
Page 12: KULIAH 11

*Goldfeld-Quandt Test: the heteroscedastic variance, σ2i , is

positively related to one of the explanatory variables in the regression model, ex:

* σ2i would be larger, the larger the values of Xi

*Weakness:

*- depend on which c is arbitrary,

*- for X > 1 Var, which X is correct to be ordered?

Page 13: KULIAH 11
Page 14: KULIAH 11

*Ex:*Y = Income,

*X = Consumption,

*n = 30,

*c = 4

Page 15: KULIAH 11

*Ex: *Y = Income, X = Consumption, n = 30, c = 4

Page 16: KULIAH 11

*Breusch–Pagan–Godfrey Test

*Weakness: - large sample needed for small sample, depend much on normality assumption

Ex:

So, H0: residuals are Homoskedastic

Page 17: KULIAH 11

ESS = SSR

Page 18: KULIAH 11

*Ex:

𝜒❑2 (1,5% )=3,8414❑

Page 19: KULIAH 11

*White’s General Heteroscedasticity Test.

*Weakness: more variables will consume more df.

H0: residuals are homoskedastic

Or H0:

, df = # parameter -1

Page 20: KULIAH 11
Page 21: KULIAH 11

*Koenker–Bassett (KB) test.

*H0: residuals are homoskedastic

*Or H0:

*Tes hipotesis using t-test

Obtain residual, then estimate

Page 22: KULIAH 11

*Other tests…..*Find other references…

Page 23: KULIAH 11

*Remedial

Perhatikan 1 &

2

Reparameterize before analize !

Page 24: KULIAH 11

Reparameterize before analize !

Page 25: KULIAH 11

*Practically, run OLS first, then run:

* consistent estimator large sample needed

Page 26: KULIAH 11

* measure the elasticity

Page 27: KULIAH 11

*Other Remedial Procedure

Page 28: KULIAH 11
Page 29: KULIAH 11

*Run the following (weighted) regression:

*Compare with the unweighted

Apa perbedaan

kedua model ini?

Page 30: KULIAH 11

*White suggests:

*For RLB:

Page 31: KULIAH 11
Page 32: KULIAH 11

*Important notes

Page 33: KULIAH 11

*Tugas Bonus*Pelajari Gujarati, Basic

Econometrics, 14th edition,

*Ch. 11, section 11.7