multiple classification across six variables

[msherman]

Dear List; I have a data set with six variables where the patients are classified according to acute coronary symdromes. The data file was set up in the following manner. (

ClinicalDiagnosis1MultivesselCAD2SinglevesselCAD3Valvular4Chestp data values are 1  2  3  4 (each number reps a different diagnosis)

    ClinicalDiagnosis5CardiomyopathyCongestiveHeartFailuredyspnea data values are 5

    ClinicalDiagnosis9CABG10PCI±stent11BothCABGampPCI data values are 9 10 11

    ClinicalDiagnosis6CardiacArrestPacerDefibrillatorLifeBridgeVest data values are 6

    ClinicalDiagnosis7AtrialFibrillationArrhythmia8TIACVA  data values are 7 8

    ClinicalDiagnosis12ChestPainAngina13AMI14BothChestPainampAMI data values are 12 13 14

I am trying to figure out a way of getting a table that shows the cross classification of all cardiac patients.

Thus it might look like

1Multivesel_Cardiomyopathy(1 and 5)

1Multivessel_Cabg (1 and 9)

1Multivessel_Stent (1 and 10)

Etc which would cover all possible combinations.

 

Is there a simple way of doing this or must it be labor intensive whereby I create all of the combinations with a bunch of do if s??  thanks   martin sherman

 

 

 

===================== 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

[Brian Dates]

Martin,

Do you want all combinations of two factors or all combinations?

Brian

On Fri, Oct 23, 2020 at 10:52 AM Martin Sherman <[hidden email]> wrote:

Dear List; I have a data set with six variables where the patients are classified according to acute coronary symdromes. The data file was set up in the following manner. (

ClinicalDiagnosis1MultivesselCAD2SinglevesselCAD3Valvular4Chestp data values are 1  2  3  4 (each number reps a different diagnosis)

    ClinicalDiagnosis5CardiomyopathyCongestiveHeartFailuredyspnea data values are 5

    ClinicalDiagnosis9CABG10PCI±stent11BothCABGampPCI data values are 9 10 11

    ClinicalDiagnosis6CardiacArrestPacerDefibrillatorLifeBridgeVest data values are 6

    ClinicalDiagnosis7AtrialFibrillationArrhythmia8TIACVA  data values are 7 8

    ClinicalDiagnosis12ChestPainAngina13AMI14BothChestPainampAMI data values are 12 13 14

I am trying to figure out a way of getting a table that shows the cross classification of all cardiac patients.

Thus it might look like

1Multivesel_Cardiomyopathy(1 and 5)

1Multivessel_Cabg (1 and 9)

1Multivessel_Stent (1 and 10)

Etc which would cover all possible combinations.

 

Is there a simple way of doing this or must it be labor intensive whereby I create all of the combinations with a bunch of do if s??  thanks   martin sherman

 

 

 

===================== 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

Maybe so? 

CTABLES /TABLE (a+b+c+d+e+f)[C] BY a+b+c+d+e+f[C][COUNT].

Not 100% clear what you want to do.

Mario Giesel

Munich, Germany

---

Am Freitag, 23. Oktober 2020, 16:52:26 MESZ hat Martin Sherman <[hidden email]> Folgendes geschrieben:

Dear List; I have a data set with six variables where the patients are classified according to acute coronary symdromes. The data file was set up in the following manner. (

ClinicalDiagnosis1MultivesselCAD2SinglevesselCAD3Valvular4Chestp data values are 1  2  3  4 (each number reps a different diagnosis)

    ClinicalDiagnosis5CardiomyopathyCongestiveHeartFailuredyspnea data values are 5

    ClinicalDiagnosis9CABG10PCI±stent11BothCABGampPCI data values are 9 10 11

    ClinicalDiagnosis6CardiacArrestPacerDefibrillatorLifeBridgeVest data values are 6

    ClinicalDiagnosis7AtrialFibrillationArrhythmia8TIACVA  data values are 7 8

    ClinicalDiagnosis12ChestPainAngina13AMI14BothChestPainampAMI data values are 12 13 14

I am trying to figure out a way of getting a table that shows the cross classification of all cardiac patients.

Thus it might look like

1Multivesel_Cardiomyopathy(1 and 5)

1Multivessel_Cabg (1 and 9)

1Multivessel_Stent (1 and 10)

Etc which would cover all possible combinations.

 

Is there a simple way of doing this or must it be labor intensive whereby I create all of the combinations with a bunch of do if s??  thanks   martin sherman

 

 

 

===================== 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

[Art Kendall]

I am not sure what you are trying to do.

Are you trying to cluster cases based on categorical variables?  I.e, to see
if you can group cases into meaningful sets?



-----
Art Kendall
Social Research Consultants
--
Sent from: http://spssx-discussion.1045642.n5.nabble.com/

=====================
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

[Art Kendall]

Something like this untested approach?

String part1(a2) Part2(a2) Part3(a3) Part4(a2) Part5(a2) Part5(a2).
If ANY(MyVar1, 2,3,4) Part1=concat(String(MyVar1,n1),'|').
if myvar2 EQ 5 Part2= concat(String(MyVar2,n1),".
If ANY(MyVar3, 9,10,11) Part1=concat(String(MyVar3,n2),'|').
if myvar4 EQ 6 Part2= Concat(String(MyVar4,n1),'|').
If ANY(MyVar5, 7,8) Part1=Concat(String(MyVar5,n1),'|').
If ANY(MyVar6, 12,13,14) Part1=String(MyVar3,n2).
String MyGroup (a13).
compute MyGroup = concat1(part1 to part6).
FREQUENCIES VARIABLES = Part1 to Part6 MyGroup.



-----
Art Kendall
Social Research Consultants
--
Sent from: http://spssx-discussion.1045642.n5.nabble.com/

=====================
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