Page History

ULTIMATE CLUSTER APPROXIMATION with stratification at the first stage

Variance estimation at country level

The following is an example of SAS syntaxes that estimate the coefficients of variation for the total Utilised agricultural area (UAA) (HA) in Portugal in a table with dimensions FARMTYPE, SO_EUR (standard output size classes) and AGRAREA (utilised agricultural area size classes) and in a table with dimensions FARMTYPE and SO_EUR. Because UAA is a CORE variable, PROC SURVEYMEANS uses the Extrapolation factor of the CORE as weight.

*Determine the extrapolation factor and the coverage of the table ;

data DATA_CORE;

set IFSORA.IFS_T_MAIN_2020 ;

*Our table covers Portugal and the data in the CORE. It covers only the holdings in the main frame (HLD_FEF="0");
*We also can select 2 or more countries;

where (country=" PT " and EXTPOL_FACT1_CORE is not missing and HLD_FEF="0");

*We make the following replacement, in order to allow valid computations also for censuses. The replacement is not made in the original dataset but in the intermediary table DATA_CORE;

if STRA_IDF_CORE ='_Z' then STRA_ID_CORE= 1 ;

*We replace null extrapolation factors with 1 but only to compute the "weight_core". The fields EXTPOL_FACT*_CORE remain unchanged;

*The first extrapolation factor for CORE is always completed and never null (unlike for the MODULES);

if missing(EXTPOL_FACT2_CORE) then EXTPOL_FACT2_CORE_n= 1 ; else EXTPOL_FACT2_CORE_n=EXTPOL_FACT2_CORE;

if missing(EXTPOL_FACT3_CORE) then EXTPOL_FACT3_CORE_n= 1 ; else EXTPOL_FACT3_CORE_n=EXTPOL_FACT3_CORE;

weight_core=EXTPOL_FACT1_CORE*EXTPOL_FACT2_CORE_n*EXTPOL_FACT3_CORE_n;

if OSU_S1_CORE=. then OSU_S1_CORE= 1 ;

if PSU_CORE=. then PSU_CORE=HLD_ID;

UAA=UAAS+UAAT;

run ;

**********************************************

PROC SURVEYMEANS;

**********************************************

Construction of computational strata, depending on OSU_S1_ and PSU_ ;

PROC SQL ;

  CREATE TABLE _CST1 AS SELECT

    COUNTRY, STRA_ID_CORE,PSU_CORE,MIN(OSU_S1_CORE) AS OSU_S1_CORE

    FROM DATA_CORE GROUP BY COUNTRY, STRA_ID_CORE,PSU_CORE;

QUIT ;

PROC SORT DATA=_CST1;

   BY COUNTRY STRA_ID_CORE OSU_S1_CORE;

RUN ;

***Within each formal stratum STRA_ID_:

The first record of each formal stratum receives _SEQ=1 then the following records of the same stratum receive _SEQ = an incrementing number by 1.

If OSU_S1 (the rank of systematic sampling) is incrementing (so a systematic sampling is used) and the record has _SEQ>2 (so the record is not the first and not the second, these first 2 records form the first computational stratum), then the formal stratum STRA_ID_ gets split i.e. a new computational stratum _CST is created within the formal stratum STRA_ID_. The process is iterative (DO - END). The number of records for each computational stratum is 2 (defined by _SEQ>2).

The split is not done before a record if that record is the last one in the formal stratum. This is done in order to avoid that the last computational stratum has less than 2 records. ;

DATA _CST;

  SET _CST1;

  RETAIN _CST 1 _SEQ;

  BY COUNTRY STRA_ID_CORE;

  P_OSU_S1_CORE=LAG(OSU_S1_CORE);

  IF FIRST.STRA_ID_CORE THEN DO;

               _SEQ= 1 ;

              P_OSU_S1_CORE= . ;

              _CST= 1 ;

  END;

  ELSE _SEQ+1 ;

  IF OSU_S1_CORE>P_OSU_S1_CORE AND _SEQ> 2 AND NOT(LAST.STRA_ID_CORE) THEN DO;

             _CST+1 ;

             _SEQ= 1 ;

END;

RUN;

***Generalisation;

/****In case performance problems occur with the above syntax, please try using the below syntax instead of the above syntax where you can define _NCST (new computational strata) = 3 or 4 etc. instead of 2.

Please let us (the Eurostat farm structure team) know if you had to use this syntax and which value you took for _NCST

/*

%LET _NCST=3;

DATA _CST;

   SET _CST1;

   RETAIN _CST 1 _SEQ;

   BY COUNTRY STRA_ID_CORE;

  P_OSU_S1_CORE=LAG(OSU_S1_CORE);

  IF FIRST.STRA_ID_CORE THEN DO;

            _SEQ=1;

           P_OSU_S1_CORE=.;

           _CST=1;

END;

ELSE _SEQ+1;

IF OSU_S1_CORE>P_OSU_S1_CORE AND _SEQ>&_NCST. AND NOT(LAST.STRA_ID_CORE) THEN DO;

          _CST+1;

         _SEQ=1;

END;

DROP _SEQ P_OSU_S1_CORE ;

RUN;

/*;

PROC SQL ;

   CREATE TABLE DATA_CORE AS SELECT A.*,B._CST

   FROM DATA_CORE A

   LEFT JOIN _CST B ON A.COUNTRY=B.COUNTRY AND A.STRA_ID_CORE=B.STRA_ID_CORE AND A.PSU_CORE=B.PSU_CORE;

QUIT ;

PROC SORT DATA=DATA_CORE;

   BY COUNTRYSTRA_ID_CORE _CST;

RUN ;

proc sql ;

create table pop_STRA_ID as

select COUNTRY, STRA_ID_CORE, _CST, sum(weight_core) as _total_, count(*) as sample

from data_core group by COUNTRY, STRA_ID_CORE, _CST;

quit ;

data pop_STRA_ID;

set pop_STRA_ID;

if _total_ < sample then _total_=sample;

run ;

proc sort data=data_core;

by COUNTRY STRA_ID_CORE _CST;

run ;

ods exclude all;

proc surveymeans data=data_core total=pop_STRA_ID sum varsum cvsum clsum ;

by COUNTRY;

domain FARMTYPE*SO_EUR*AGRAREA FARMTYPE*SO_EUR;

var UAA;

strata STRA_ID_CORE _CST;

cluster PSU_CORE;

weight WEIGHT_CORE;

ods output domain=cv;

run ;

The result is the coefficients of variation stored in field CVSUM in the table cv.