Matematik / Matematisk statistik 

SF2945 Tidsserieanalys ht 2009/ Time Series analysis 2009 - Homework assignments

There are two compulsory homework assignments. These submitted in two reports: Report A and Report B., as defined in the document Homework in Time Series Analysis

• The deadline for Report A is 19th of November, and contains A.1. - A.2 , as defined in the document Homework in Time Series Analysis
• Deadline for Report B is 10th of December and contains B.1. - B.2. , as defined in the document Homework in Time Series Analysis
• The exam as well as BOTH A and B are required to pass the course.

  In the homework assignments you are recommended to use MATLAB. Several useful m-files are found in this page. The data files in the assignments are also found here.

   

  ---

  • A.1 Choose your own time series
    
    
    • Time Series Data Library All of data in text format !
      
      
      

       

    • A link  to further data sources that can be used.

       

     

    ---

    
    

  • A.2. Sealevel in Stockholm, ARMA -procesess

     

    ---

  • A.2.1. uses the following files

    • acf.m ( sample autocorrelation function)

    • acvf.m (sample autocovariance function)

    • diffd.m (difference operator)

    • ljungbox.m (Ljung-Box test)

    • ranktest.m (Rank test for independence)

    • seascomp.m (seasonal component)

    • smoothma.m (Moving average smoothing)

    • smoothpf.m (polynomial fitting)

    The data are found in  sealevel.dat   and in the MATLAB data file sealevel.mat. 

    ---

  • A.2.2. uses the following files

    • armaacvf.m (autocovariance function for ARMA process)

    • arroots (gives roots of AR generating function)

    • causal.m (tells if the process is causal)

    • innov.m (innovation algorithm used in predarma)

    • predarma.m (prediction of ARMA process)

    • psi.m (psi coefficients in linear representaton)

    • roots2ar (gives AR parameters from generating function roots)

    • simarma.m ( simulation of ARMA process)

    The acf.m and acvf.m files should also be used. Just click on the links and save the files in an appropriate place. The m-file  plotbar.m can be helpful when drawing autocorrelation function as bars from the x-axis. It is similar to the standard m-file stem which draws bars ending with circles.

     

     

    ---

    
    

  • B.1 analyze your own time series

     

    ---

    
    

  • B.2 Statistical Estimation in Time Series, Financial Time Series

     

    ---

    
    

  • B.2.1. uses the following files

    • boxcox.m  (graph that shows Box-Cox transformation)

    • boxcoxf.m (function of Box-Cox transformation)

    • pacf.m (Partial autocorrelation function, PACF)

    • pergram.m (periodogram)

    • specarma.m (spectral density ARMA process)

    • specdens.m (spectral density stationary process)

    • yuwaest.m (Yule-Walker estimation, AR-process)

    The data are found in, temp.dat, timech.dat and el.dat or all together in the MATLAB data file data3.mat. The matlab command 'load data3' will load them into a MATLAB session. The m-file read3.m  reads the dat-files into Matlab.

    ---

  • B.2.2. uses the following files

    • archsim.m (simulate an ARCH(1) process)

    • garchsim.m (simulate a GARCH(1,1) process)

    • prctile.m  (computes a given percentile in a data set)

    The MATLAB data file is found in logret_DEM_USD.mat . Here is the same data in a text-file, logret_DEM_USD.dat.

    
    

    ---

    
    

  [Kurshemsida]      [Kursförteckning]     [Avdelningen Matematisk statistik]