mirkousuelli / time-series-analysis

Repository dedicated to the practical concepts of Model Identification & Data Analysis in Python

time-series-analysis

Repository dedicated to the practical concepts of Model Identification & Data Analysis in Python

estimation.ipynb

1. Estimators
   1.1) Mean estimator
   1.1.1) Detrend
   1.2) Covariance estimator
   1.3) Spectrum estimator
2. Whiteness Anderson Test
   2.1) Procedure
3. Homework
   3.1) Mean estimator
   3.2) Covariance estimator
   3.3) Spectrum estimator

identification.ipynb

1. Covariance and Partial Covariance
   1.1) AR(n) data identification : 𝑃𝐴𝑅𝐶𝑂𝑉(𝜏)
   1.2) MA(n) data identification : 𝜌(𝜏)
   1.3) ARMA(n,m) data identification
2. Criterions
   2.1) FPE : Final Predictor Error
   2.1) AIC : Akaike Information Criterion
   2.3) MDL : Minimum Description Length

3. Procedure
   3.1) Realization measurments
   3.2) Parameters prediction
   3.2.1) LS method
   3.2.2) Durbin-Levinson method
   3.3) Variance prediction error
   3.4) Criterion computation
   3.4.1) FPE
   3.4.2) AIC
   3.4.3) MDL
   3.5) Model Selection
   3.5.1) 30 Samples
   3.5.2) 50 Samples
   3.5.3) 500 Samples