Aggr for reliability dataset

Moderators: statman, Analyst Techy, andris, Fierce, GerineL, Smash

Uri1616
Posts: 1
Joined: Sat Feb 22, 2014 10:00 pm

Aggr for reliability dataset

Postby Uri1616 » Sat Feb 22, 2014 10:10 pm

hi everyone,

I have this dataset "oldfile.sav" I generated using "update" to compare two other datasets formed by Uri and Yael. The first var "SY" is the raw number from the source datasets.
In this dataset each matching case from Uri's dataset and Yael dataset is displayed and marked by value '1' for "flag" .
Cases from the source datasets that weren't identical appear one after the other (ex. sy=32), while the first comes from Uri's file and the Second comes from Yael's. One of them gets '1' for "flag" and the other gets '0'. Both has the same raw number ("SY").

this is how it looks like:

sy flag var1 var2 var3 var4 var5 var6
27 1 1 0 0 0 0 0
32 0 3 0 1 0 0 0
32 1 2 0 1 0 1 0
33 1 1 0 0 0 0 0
34 1 1 0 0 0 0 0
35 1 1 0 0 0 0 0
36 1 1 0 0 0 1 0
36 0 0 0 0 0 1 0
37 1 1 0 0 0 0 0



Now I want to get a new file "sum.sav" in which each var (besides flag and sy) is aggregated, But I want three separate aggregations.
The first case of the new file should hold the aggregation of only the values that Uri and Yael entered identically.
The second should hold Uri's values that differentiate from Yael's.
The thirs should hold Yael's values that differentiate from Uri's.

Notice that in the non-matching cases, some of the values **are in fact identical** and therefor should be aggregated in
the first raw (in the ex. var3 was aggregated to '1' in the "match-agr" raw, bc both uri and yael entered '1' for it in raw 32).
for example in case 32, while values of var1 are different, the values of var3 are identical.

eventually the new file "sum.sav" for the dataset above sould look like this:

var1 var2 var3 var4 var5 var6

(match-agr) 5 0 1 0 1 0
(only-uri-agr) 4 0 0 0 0 0
(only-yael-agr) 2 0 0 0 1 0


Thank for your help,
Uri.
GerineL
Moderator
Posts: 1477
Joined: Tue Jun 10, 2008 4:50 pm

Re: Aggr for reliability dataset

Postby GerineL » Mon Feb 24, 2014 9:29 am

not entirely sure I understand correctly, but I think you can just use aggregate with a break on sy and flag (or just flag, that is not entirely clear to me) and then use either select cases to save datasets separately, or use if-functions to create variables holding only info for match cases, uri cases or yael cases in a separate column.

Who is online

Users browsing this forum: No registered users and 1 guest

cron