19th International Conference on Computational Statistics, Paris, August 22nd-27th 2010 M-Estimation in INARCH Models with a special focus on small means Hanan El-Saied, Roland Fried Department of Statistics TU Dortmund Germany 1
Contents • Motivation: Outliers in IN(G)ARCH models • M-estimation for i.i.d. Poisson data • M-estimation for INARCH-model • Bias correction • Outlook 2
Motivation: Number of Campylobacterosis Infections 50 40 30 number 20 10 0 0 20 40 60 80 100 120 140 time (4 week periods) INGARCH-model : Y ~ Poi Ferland, Latour, Oraichi (2006) t Y , s t t s Y t 0 1 t 13 1 t 1 Level shift at time 84, outlier pattern at time 100 Fokianos, F. (2010) 3
● M-estimation of location for i.i.d. data n n y y t t Minimize t 1 t 1 e.g. log f gives ML-estimator 4
● M-estimation of location for i.i.d. data n n y y t t Minimize t 1 t 1 e.g. log f gives ML-estimator Huber -function Tukey -function 3 2 psi-function 2 psi-function 1 1 -3 -2 -1 0 0 -1 -2 -4 -2 0 2 4 x -4 -2 0 2 4 x 2 2 x , | x | k x ( x ) ( x ) x 1 I | x | k k k k sign ( x ), | x | k k 5
M-estimation for i.i.d. Poisson data Modified Huber -function with bias correction y a , | y a | k ( y , ) k , a k sign ( y a ), | y a | k with a=a( ) such that E Y , 0 Simpson et al. (1987) k , a 1 6
M-estimation for i.i.d. Poisson data Modified Huber -function with bias correction y a , | y a | k ( y , ) k , a k sign ( y a ), | y a | k with a=a( ) such that E Y , 0 Simpson et al. (1987) k , a 1 Modified Tukey -function with bias correction 2 2 y y y 2 ( y , ) a k a I a k k , a Initialization by sample median or by estimating P (Y=0) 7
Efficiencies: asymptotic and sample size n=50 Asymptotic efficiency of Finite sample efficiency of Huber M-est. for several k Huber & Tukey M-est., n=50 1.00 .8 1.0 asymptotic efficiency relative efficiency .95 .6 .90 .4 .85 .2 .80 .0 0 5 10 15 20 25 0 5 10 15 20 25 huberM (robustbase), k=1.8 k=1 k=2 glmrob, k=1.8 Tukey, k=5 Tukey, k=6 Cadigan & Chen (2001) Tukey, adaptive k 8
Efficiencies: asymptotic and sample size n=50 Asymptotic efficiency of Finite sample efficiency of Huber M-est. for several k Huber & Tukey M-est., n=50 1.00 .8 1.0 asymptotic efficiency relative efficiency .95 .6 .90 .4 .85 .2 .80 .0 0 5 10 15 20 25 0 5 10 15 20 25 huberM (robustbase), k=1.8 k=1 k=2 glmrob, k=1.8 Tukey, k=5 Tukey, k=6 Cadigan & Chen (2001) Tukey, adaptive k 9
Robustness for =0.5 and =5 Efficiency relatively to sample mean in case of increasing number of outliers of increasing size, n=50, log-scale 1000 1000 relative efficiency relative efficiency 100 100 10 10 1 1 0.1 0.1 0 5 10 15 20 0 5 10 15 20 number and size of outliers number and size of outliers huberM (robustbase), k=1.8 glmrob, k=1.8 Tukey, k=5 Tukey, k=6 Tukey, adaptive k 10
● Conditional likelihod estimation for INARCH INARCH-model : Y ~ Poi , Y Y t Y , s t t t 0 1 t 1 p t p s Conditioning on first p observations y 1 , …, y p : 1 0 n y y 1 t 1 t t t t t p 1 y 0 t p 11
● Conditional likelihod estimation for INARCH INARCH-model : Y ~ Poi , Y Y t Y , s t t t 0 1 t 1 p t p s Conditioning on first p observations y 1 , …, y p : 1 0 n y y 1 t 1 t t t t t p 1 y 0 t p 1 M-estimation: y t 1 , 2 marginal y t t mean & variance t y t p 12
Efficiencies: INARCH(1), 0 =1,several 1 , n=100 Efficiency for 1 Efficiency for 0 .0 .2 .4 .6 .8 1.01.2 .0 .2 .4 .6 .8 1.01.2 relative efficiency relative efficiency 1 0.0 0.2 0.4 0.6 0.8 0.0 0.2 0.4 0.6 0.8 Huber, k=1.8, Huber, k=2.5 Tukey, k=5, Tukey, k=7 Tukey, adaptive k 13
Robustness: INARCH(1) with 0 =1, 1 =.4 Increasing number k of outliers of size k at end of time series Bias for 0 .1 .0 bias -.1 -.2 -.3 0 5 10 15 20 number and size of outliers Conditional ML Huber, k=1.8, Huber, k=2.5 Tukey, k=5, Tukey, k=7 Tukey, adaptive k 14
Robustness: INARCH(1) with 0 =1, 1 =.4 Increasing number k of outliers of size k at end of time series Bias for 1 Bias for 0 .1 .5 .4 .0 bias bias .3 -.1 .2 -.2 .1 -.3 .0 0 5 10 15 20 0 5 10 15 20 number and size of outliers number and size of outliers Conditional ML Huber, k=1.8, Huber, k=2.5 Tukey, k=5, Tukey, k=7 Tukey, adaptive k 15
● Bias correction for INARCH(p) model M-estimator with bias correction: 1 a 0 y 0 t 1 n y 1 t t t t t p 1 y t p a 0 p with a o ,…, a p depending on 0 , …, p such that expectation of left hand side equals 0. 16
Bias for INARCH(1) in dependence on 1 n=100 .3 .2 Bias 0 .1 Conditional ML .0 Tukey, k=7 -.1 1 Tukey, k=5 .1 .3 .5 .7 .9 Tukey, k=5, corrected .04 -.04 -.02 .00 .02 1 Bias 1 .1 .3 .5 .7 .9 17
Bias for INARCH(1) in dependence on 1 n=200 n=100 .3 .3 .2 .2 Bias Bias 0 .1 .1 Conditional ML .0 .0 Tukey, k=7 -.1 -.1 1 Tukey, k=5 .1 .3 .5 .7 .9 .1 .3 .5 .7 .9 Tukey, k=5, corrected .04 -.04 -.02 .00 .02 .04 Bias correction -.04 -.02 .00 .02 1 Bias Bias effective only in large samples 1 .1 .3 .5 .7 .9 .1 .3 .5 .7 .9 18
Conclusions Tukey M-estimators more robust against many large outliers Needs good robust initialization - from median or P (Y=0) Adaptive choice of the tuning constant k gives M-estimators with good efficiencies irrespective of the true Poisson parameter M-estimators provide robustness also in INARCH case Bias correction works for long time series Ongoing work: extend to INGARCH, prove asymptotic normality 19
References Cadigan, N.G., Chen, J. (2001). Properties of Robust M-estimators for Poisson and Negative Binomial Data. J. Statist. Comput. Simul. 70, 273-288. Davis, R.A., Dunsmuir, W.T.M., Street, S.B. (2003). Observation driven models for Poisson counts. Biometrika 90, 777-790. Ferland, R.A., Latour, A., Oraichi, D. (2006). Integer-valued GARCH processes. Journal of Time Series Analysis 27, 923-942. Fokianos, K., Fried, R. (2010). Outliers in INGARCH Processes. Journal of Time Series Analysis 31, 210-225 . Fokianos, K., Rahbek, A., Tjøstheim, D. (2009). Poisson Autoregression. J ournal of the American Statistical Association 104, 1430-1439. Simpson, D.G., Carroll, R.J., Ruppert, D. (1987). M-Estimation for Discrete Data: Asymptotic Distribution Theory & Implications. 20 Annals of Statistics 15, 657-669.
Recommend
More recommend