* NOTE THAT WE MUST USE THE grossing-up weight GROSSWT.
* or the design effects will not be correct.

* Now we need to set up the plan file which can be done. 
* most easily interactively.
* First set up the survey design in a plan file
  You will probably find it easier to do this in a window, go
    to >>analyse >>complex samples.

* AT first screen give your plan file a name and a place to be saved.
* At the second put    GROSSwt for weight 
                               (to get design effects right need a grossing up weight).
                       PSU (prinary sampling unit) for CLUSTER
                       STRATUM for STRATA.
* See the exemplar file for the design of the survey.
* At next stage tick WR (with replacement)
              and you are all set - code below was pasted from this and could be just run.

* This syntax was generated by pasting from the menu .
* You can change the name of the plan file to where you want to save it on your machine.

* Analysis Preparation Wizard.
CSPLAN ANALYSIS
 /PLAN FILE='ex2.csaplan'
 /PLANVARS ANALYSISWEIGHT=grosswt
 /PRINT PLAN
 /DESIGN  STRATA= stratum  CLUSTER= psu
   /ESTIMATOR TYPE=WR.

* Now get proportion of internet use and its standard error 
   adjusting for weighting, stratification and clustering.
* You can analyse as complex samples from windows by going
  to the complex samples and submenus, (this next one is tables) 
  or by pasting the code below into SPSS.
* Complex Samples Descriptives.

* Complex Samples Frequencies.
CSTABULATE
 /PLAN FILE = 'ex2.csaplan'
 /TABLES VARIABLES = intuse
 /CELLS  POPSIZE tablepct
 /STATISTICS  SE CIN(95) DEFF DEFFSQRT
 /MISSING SCOPE = TABLE CLASSMISSING = EXCLUDE.


* The remaining analyses shown here are pasted 
  from the SPSS Complex survey procedures, note
  that you need to have the right plan file
  this one is  a plan ex2 with weighting and clustering.

* Complex Samples Frequencies.
CSTABULATE
 /PLAN FILE = 'ex2.csaplan'
 /TABLES VARIABLES = intuse
 /SUBPOP TABLE = sex  DISPLAY=LAYERED
 /CELLS  TABLEPCT
 /STATISTICS  SE COUNT DEFF
 /MISSING SCOPE = TABLE CLASSMISSING = EXCLUDE.

* Complex Samples Frequencies.
* tables by hours used.
CSTABULATE
 /PLAN FILE = 'ex2.csaplan'
 /TABLES VARIABLES = RC5
 /CELLS  TABLEPCT
 /STATISTICS  SE CIN(95) DEFF DEFFSQRT
 /MISSING SCOPE = TABLE CLASSMISSING = EXCLUDE.

* Complex Samples Frequencies.
* To get proportions by council area.
CSTABULATE
 /PLAN FILE = 'ex2.csaplan'
 /TABLES VARIABLES = intuse
 /SUBPOP TABLE = COUNCIL  DISPLAY=LAYERED
 /CELLS  TABLEPCT
 /STATISTICS  SE COUNT DEFF
 /MISSING SCOPE = TABLE CLASSMISSING = EXCLUDE.


* Complex Samples Crosstabs.
* To get chi-squared tests
CSTABULATE
 /PLAN FILE = 'ex2.csaplan'
 /TABLES VARIABLES = intuse BY sex
 /CELLS  POPSIZE
 /STATISTICS  SE DEFF DEFFSQRT
 /TEST  ODDSRATIO INDEPENDENCE
 /MISSING SCOPE = TABLE CLASSMISSING = EXCLUDE.

* to check the effect of different designs as for Table 2.4.
* It is necessary to set up a new plan file.
* This one checks out what the design effects would be without clustering.
* It has been given a differnt name here.

* Analysis Preparation Wizard.
CSPLAN ANALYSIS
 /PLAN FILE='ex2v2.csaplan'
 /PLANVARS ANALYSISWEIGHT=grosswt
 /PRINT PLAN
 /DESIGN  STRATA= stratum  CLUSTER= UNIQID
   /ESTIMATOR TYPE=WR.

* Complex Samples Frequencies.
CSTABULATE
 /PLAN FILE = 'ex2v2.csaplan'
 /TABLES VARIABLES = intuse
 /CELLS  POPSIZE tablepct
 /STATISTICS  SE CIN(95) DEFF DEFFSQRT
 /MISSING SCOPE = TABLE CLASSMISSING = EXCLUDE.