Date:         Thu, 27 May 1999 10:50:30 +0100
Reply-To:     Peter Crawford <Peter@CRAWFORDSOFTWARE.DEMON.CO.UK>
Sender:       "SAS(r) Discussion" <SAS-L@UGA.CC.UGA.EDU>
From:         Peter Crawford <Peter@CRAWFORDSOFTWARE.DEMON.CO.UK>
Subject:      Re: basic statistics using class frequencies
In-Reply-To:  <374C5F3E.34B7@capitale.qc.ca>

If access to SAS/INSIGHT is available, this data with derived age-group-
midpoint makes a great sample for Josi Ailton Alencar andrade to explore
 
 
Bernard Tremblay <bernard@CAPITALE.QC.CA> writes
>Hi,
>
>        Could we combine the two suggestion from "Giannone, Lisa"
><Lisa.Giannone@schwab.com>
>and Rob Carscadden <rcarscadden@metisamerica.com>.   If you don't have
>access to the detailed data
>used to calculate the freqs this could be done by using the midpoint of
>the class and the frequency
>(assuming uniform distribution inside classes).  See the following code:
>
>~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
>data test;
>  input class $ freq midpoint;
>cards;
><10           567       5
>10-20         887       15
>20-30         565       25
>30-40         1345      35
>40-50         1233      45
>50-60         367       55
>60-70         115       65
>70-80         32        75
>>80           12        85
>;
>run;
>
>PROC UNIVARIATE DATA = test;
>VAR midpoint;
>FREQ freq;
>OUTPUT  MEAN= MEDIAN= STD= ;
>run;
>~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
>
>        The may be more appropriate statistic procecures, but I'm giving it a
>try!
>
>        Just my 0.02$,
>
>                Bernard Tremblay
>--
>         \\\|///
>       \\  - -  //
>        (  @ @  )
>+-----oOOo-(_)-oOOo-------+--------------------------------------+
>| Bernard Tremblay        |                                      |
>|          La Capitale    | Tel: (418) 646-2401                  |
>|                         | Fax: (418) 646-5960                  |
>|                         | Int: Bernard.Tremblay@capitale.qc.ca |
>+-------------------------+--------------------------------------+
>|          Imaginasys enr | Res: (418) 658-1411                  |
>|                         | Int: bertrem@quebectel.com           |
>+--------------Oooo-------+--------------------------------------+
>       oooO   (   )
>      (   )    ) /
>       \ (    (_/
>        \_)
>
>
>
>
>Josi Ailton Alencar andrade wrote:
>>
>>     Hello All,
>>
>>     I have some tables which contain the absolute frequency and its
>> classes. For exemple:
>>
>> Age class    Frequency
>> <10            567
>> 10-20         887
>> 20-30         565
>> 30-40         1345
>> 40-50         1233
>> 50-60         367
>> 60-70         115
>> 70-80         32
>> >80            12
>>
>>     Is there any sas procedure or method who give me the basic
>> statististics (average, median, standart desviation, percentiles, etc.)
>> of the AGE variable?
>>
>>     Thanks.
>>
>>     Bye.
 
--
Peter Crawford    (_knowledge_ is a poor substitute for *real* experience,
                                               but they make a great team)