ST 590G -- Computation for Data Analysis

  First Assignment -- due Thursday, 01 September 2011

Measurements of atmospheric carbon dioxide are in nine files in the directory 'csiro' according to nine stations.  All of these files have a long descriptive header, but the lengths vary.  Below is the list of stations, file names, and the length of the header.  
   Alert              alt_mm.dat        16    
   Cape Ferguson      cferg_mm.dat      16
   Cape Grim          cgrim_mm.dat      16
   Estevan Point      estpo_mm.dat      17
   Macquarie Island   macq_mm.dat       16
   Mawson             mawson_mm.dat     16
   Mauna Loa          mlo_mm.dat        16
   Shetland Islands   shetland_mm.dat   16
   South Pole         spo_mm.dat        16

All stations end in 2001, except for Alert which ends in 2006.

For more information about these data, see
    http://cdiac.ornl.gov/trends/co2/csiro
These files all have the following format: a header, then the 
data, then a footer with more explanatory information.  The body of the data has a column for the year, then twelve columns of monthly values, and the annual average column for a total of 14 columns.  These values are *tab-delimited* so use 'dsd' and 'dlm' in your infile statement.

Read in the data from one station and perform the following tasks:
 a) Create a dataset with each observation corresponding to a month, with variables YEAR, MONTH (numeric), and CO2.  Also create a time or date variable that properly indexes the data.
 b) Plot CO2 versus time/date.
 c) Check whether given the annual averages match (close enough) the sample mean from the monthly values.  (Note the given annual average is missing for a year if any monthly value is missing.)

Which station to read?  Use the last digit of your student id and take the stations in numeric order: Alert (1), Cape Ferguson (2), ..., South Pole (9).  If you have a 0 in your student id, use the last nonzero number.

The file 'UMTMVS.txt' was obtained from FRED, and holds monthly values of a manufacturing index in tab-delimited format.  

 d) Read in these data and create a dataset with variables MFG and
a time/date variable.
 e) Plot the manufacuring index versus time/date.
 f) Put these two datasets together via merge/by.
 g) Regress your CO2 value on the manufacturing index.  Report the results and comment on the fit.

 
       FOR ALL EXERCISES: Hand in
        (1)  Your program
            * With at least as many comments as you have toes! *
        (2)  Your output
        (3)  The answers to any questions asked.