Unduplicated cases

[subscribe SPSSX-l Anonymous-2]

Hello,


I have a student data set with 3 different terms (06/FA, 07/FA, 08/FA) and
I'm trying to identify the number of unduplicated student head count
enrolled in each program by term.  I'm using student ID as the matching
case.  I'm also sorting within the matching group by term.

For some reason it's not counting unduplicated students by term but by total
enrollment.  So it's only counting students once for all 3 terms instead of
each term.

I'm not sure what I'm doing wrong. Please help if you can.

This is what I've been using:

* Identify Duplicate Cases.
SORT CASES BY STC_PERSON_ID(A) STC_REPORTING_TERM(A).
MATCH FILES
  /FILE=*
  /BY STC_PERSON_ID
  /FIRST=PrimaryFirst
  /LAST=PrimaryLast.
DO IF (PrimaryFirst).
COMPUTE  MatchSequence=1-PrimaryLast.
ELSE.
COMPUTE  MatchSequence=MatchSequence+1.
END IF.
LEAVE  MatchSequence.
FORMAT  MatchSequence (f7).
COMPUTE  InDupGrp=MatchSequence>0.
SORT CASES InDupGrp(D).
MATCH FILES
  /FILE=*
  /DROP=PrimaryFirst InDupGrp MatchSequence.
VARIABLE LABELS  PrimaryLast 'Indicator of each last matching case as Primary'.
VALUE LABELS  PrimaryLast 0 'Duplicate Case' 1 'Primary Case'.
VARIABLE LEVEL  PrimaryLast (ORDINAL).
FREQUENCIES VARIABLES=PrimaryLast.

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD

[ViAnn Beadle]

I think that you need to add the REPORTING_TERM variable to your BY
statement in MATCH FILES.

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Michelle
Sent: Friday, February 06, 2009 12:25 PM
To: [hidden email]
Subject: Unduplicated cases

Hello,


I have a student data set with 3 different terms (06/FA, 07/FA, 08/FA) and
I'm trying to identify the number of unduplicated student head count
enrolled in each program by term.  I'm using student ID as the matching
case.  I'm also sorting within the matching group by term.

For some reason it's not counting unduplicated students by term but by total
enrollment.  So it's only counting students once for all 3 terms instead of
each term.

I'm not sure what I'm doing wrong. Please help if you can.

This is what I've been using:

* Identify Duplicate Cases.
SORT CASES BY STC_PERSON_ID(A) STC_REPORTING_TERM(A).
MATCH FILES
  /FILE=*
  /BY STC_PERSON_ID
  /FIRST=PrimaryFirst
  /LAST=PrimaryLast.
DO IF (PrimaryFirst).
COMPUTE  MatchSequence=1-PrimaryLast.
ELSE.
COMPUTE  MatchSequence=MatchSequence+1.
END IF.
LEAVE  MatchSequence.
FORMAT  MatchSequence (f7).
COMPUTE  InDupGrp=MatchSequence>0.
SORT CASES InDupGrp(D).
MATCH FILES
  /FILE=*
  /DROP=PrimaryFirst InDupGrp MatchSequence.
VARIABLE LABELS  PrimaryLast 'Indicator of each last matching case as
Primary'.
VALUE LABELS  PrimaryLast 0 'Duplicate Case' 1 'Primary Case'.
VARIABLE LEVEL  PrimaryLast (ORDINAL).
FREQUENCIES VARIABLES=PrimaryLast.

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD

[Fry, Jonathan B.]

I'm guessing each record in your data represents a student enrolled in a course during a term, and that each course is part of a program.  If the records already contain a PROGRAM field, then something like the syntax below will create a dataset in which each record represents a student enrolled in a program during a term.  The CROSSTABS at the end will print a table of student count by term by program.

Aggregate /out=*/ break = STC_PERSON_ID PROGRAM STC_REPORTING_TERM
        / NCourses=N.
Crosstabs PROGRAM BY STC_REPORTING_TERM.

Jonathan Fry

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Michelle
Sent: Friday, February 06, 2009 1:25 PM
To: [hidden email]
Subject: Unduplicated cases

Hello,


I have a student data set with 3 different terms (06/FA, 07/FA, 08/FA) and
I'm trying to identify the number of unduplicated student head count
enrolled in each program by term.  I'm using student ID as the matching
case.  I'm also sorting within the matching group by term.

For some reason it's not counting unduplicated students by term but by total
enrollment.  So it's only counting students once for all 3 terms instead of
each term.

I'm not sure what I'm doing wrong. Please help if you can.

This is what I've been using:

* Identify Duplicate Cases.
SORT CASES BY STC_PERSON_ID(A) STC_REPORTING_TERM(A).
MATCH FILES
  /FILE=*
  /BY STC_PERSON_ID
  /FIRST=PrimaryFirst
  /LAST=PrimaryLast.
DO IF (PrimaryFirst).
COMPUTE  MatchSequence=1-PrimaryLast.
ELSE.
COMPUTE  MatchSequence=MatchSequence+1.
END IF.
LEAVE  MatchSequence.
FORMAT  MatchSequence (f7).
COMPUTE  InDupGrp=MatchSequence>0.
SORT CASES InDupGrp(D).
MATCH FILES
  /FILE=*
  /DROP=PrimaryFirst InDupGrp MatchSequence.
VARIABLE LABELS  PrimaryLast 'Indicator of each last matching case as Primary'.
VALUE LABELS  PrimaryLast 0 'Duplicate Case' 1 'Primary Case'.
VARIABLE LEVEL  PrimaryLast (ORDINAL).
FREQUENCIES VARIABLES=PrimaryLast.

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD