Re: how to combine 5 categorical variables
Locked
Re: how to combine 5 categorical variables
 
|
Please give more detail. Can you cobble together an
example with the 6 variables and a variable that show what you
want?
cooking, settable, cleaning, dishes, clothes, ironing 1 1 1 1 1 1 x 2 2 2 2 2 2 x 3 3 3 3 3 3 x 1 1 2 2 3 3 x 1 1 1 2 2 2 x 1 1 1 3 3 3 x 2 2 2 1 1 1 x 3 3 3 1 1 1 x 1 2 1 2 1 2 x 2 1 2 1 2 1 x etc. BTW try to avoid (... = sysmis) in your transformations like RECODE, COMPUTE. Although it is syntactically correct it is semantically (i.e., wrt meaning) incorrect. The reason the output value is missing is that the user said to treat it as such. Therefore it is "user missing". It is not missing because the system is unable to follow you instructions, i.e., sysmis. In the long run this is a very useful distinction in debugging and refining your syntax and approach. recode v1 (1=1) (2=2) (3 thru 11=0) (else=-1) into cooking. recode v2 (1=1) (2=2) (3 thru 11=0) (else=-1) into settable. recode v3 (1=1) (2=2) (3 thru 11=0) (else=-1) into cleaning. recode v4 (1=1) (2=2) (3 thru 11=0) (else=-1) into dishes. recode v5 (1=1) (2=2) (3 thru 11=0) (else=-1) into clothes. recode v6 (1=1) (2=2) (3 thru 11=0) (else=-1) into ironing. VALUE LABELS cooking, settable, cleaning, dishes, clothes, ironing 1'Wife' 2'Husband' 3'Everybody Else' -1 'else on recode'. missing values cooking to ironing(-1). Art Kendall Social Research Consultants On 5/23/2012 4:57 AM, Dogan Hatun wrote: Hello,===================== 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
Social Research Consultants |
Re: how to combine 5 categorical variables
Administrator
|
By most reasonable definitions, a "Variable" can only take on *ONE* value per case.
SO the notion of combining 6 into one which takes on 3 values is murky at best. People who believe otherwise are typically doing some sort of marketing 'research'. Maybe OP is looking for some sort of MULT RESPONSE, but such are truly limited from any statistical POV.
Please reply to the list and not to my personal email.
Those desiring my consulting or training services please feel free to email me. --- "Nolite dare sanctum canibus neque mittatis margaritas vestras ante porcos ne forte conculcent eas pedibus suis." Cum es damnatorum possederunt porcos iens ut salire off sanguinum cliff in abyssum?" |
|
In reply to this post by Art Kendall
The variables look like:
Housework - cooking Frequency Percent Valid Percent Cumulative Percent Valid Respondent 7414 91.8 91.8 91.8 Husband 19 .2 .2 92.1 Female children 170 2.1 2.1 94.2 Male children 2 .0 .0 94.2 Mother/mother-in-law 265 3.3 3.3 97.5 Father/father-in-law 2 .0 .0 97.5 Other females in the household 174 2.2 2.2 99.7 Other males in the household 2 .0 .0 99.7 Paid servant/maid 11 .1 .1 99.8 Nobody does the job 7 .1 .1 99.9 Other 7 .1 .1 100.0 Total 8073 100.0 100.0 Missing 99 2 .0 Total 8075 100.0 Housework - setting table main person Frequency Percent Valid Percent Cumulative Percent Valid Respondent 7030 87.1 87.1 87.1 Husband 34 .4 .4 87.5 Female children 689 8.5 8.5 96.0 Male children 11 .1 .1 96.2 Mother/mother-in-law 55 .7 .7 96.9 Father/father-in-law 1 .0 .0 96.9 Other females in the household 232 2.9 2.9 99.7 Other males in the household 3 .0 .0 99.8 Paid servant/maid 5 .1 .1 99.8 Nobody does the job 3 .0 .0 99.9 Other 10 .1 .1 100.0 Total 8073 100.0 100.0 Missing 99 2 .0 Total 8075 100.0 ... and I want to combine them into one(Routine Housework) that looks like Routine Housework 1)Wife(respondent).... 2)Husband .... 3)Everybody else .... |
Re: how to combine 5 categorical variables
Administrator
|
What Art had in mind, I think, is that you list some cases (rows) of data that show different combinations of values for the cooking and table setting variables, and what you want the combined variable to look like for each of those combinations. For example, if Cooking = Husband and Table Setting = Female Children, what do you want the combined variable to show?
HTH.
--
Bruce Weaver bweaver@lakeheadu.ca http://sites.google.com/a/lakeheadu.ca/bweaver/ "When all else fails, RTFM." PLEASE NOTE THE FOLLOWING: 1. My Hotmail account is not monitored regularly. To send me an e-mail, please use the address shown above. 2. The SPSSX Discussion forum on Nabble is no longer linked to the SPSSX-L listserv administered by UGA (https://listserv.uga.edu/). |
Re: how to combine 5 categorical variables
|
|
I do not see how you would be able to keep all available data, but if you are looking for who is the primary for routine house work,
using a 'count' variable would create3 variables showing the number of times a particular task was reported for each. e.g. (assuming codes of 1=wife, 2=husband and 3+ is everyone else.) count RH_wife=cooking cleaning <the rest of the variables>... (1). count RH_husband=cooking cleaning <the rest of the variables> ... (2). count RH_other=cooking cleaning <the rest of the variables> ... (3 thru hi). Then you could identify the highest If (RH_wife>RH_husband and RH_wife>RH_Other) mainRH=1. If (RH_ husband >RH_ wife and RH_ husband >RH_Other) mainRH=2. If (RH_ Other >RH_husband and RH_ Other >RH_ wife) mainRH=3. Var labels mainRH 'Primary provider of routine housework'. Val labels mainRH 1 'Wife' 2 'Husband' 3 'Other'. -----Original Message----- From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Bruce Weaver Sent: Wednesday, May 23, 2012 1:04 PM To: [hidden email] Subject: Re: [SPSSX-L] how to combine 5 categorical variables What Art had in mind, I think, is that you list some cases (rows) of data that show different combinations of values for the cooking and table setting variables, and what you want the combined variable to look like for each of those combinations. For example, if Cooking = Husband and Table Setting = Female Children, what do you want the combined variable to show? HTH. dodo wrote > > The variables look like: > > Housework - cooking > Frequency Percent Valid Percent Cumulative Percent > Valid Respondent 7414 91.8 91.8 91.8 > Husband 19 .2 .2 92.1 > Female children 170 2.1 2.1 94.2 > Male children 2 .0 .0 94.2 > Mother/mother-in-law 265 3.3 3.3 97.5 > Father/father-in-law 2 .0 .0 97.5 > Other females in the household 174 2.2 2.2 99.7 > Other males in the household 2 .0 .0 99.7 > Paid servant/maid 11 .1 .1 99.8 > Nobody does the job 7 .1 .1 99.9 > Other 7 .1 .1 100.0 > Total 8073 100.0 100.0 > Missing 99 2 .0 > Total 8075 100.0 > > > Housework - setting table main person > Frequency Percent Valid Percent Cumulative Percent > Valid Respondent 7030 87.1 87.1 87.1 > Husband 34 .4 .4 87.5 > Female children 689 8.5 8.5 96.0 > Male children 11 .1 .1 96.2 > Mother/mother-in-law 55 .7 .7 96.9 > Father/father-in-law 1 .0 .0 96.9 > Other females in the household 232 2.9 2.9 99.7 > Other males in the household 3 .0 .0 99.8 > Paid servant/maid 5 .1 .1 99.8 > Nobody does the job 3 .0 .0 99.9 > Other 10 .1 .1 100.0 > Total 8073 100.0 100.0 > Missing 99 2 .0 > Total 8075 100.0 > > ... > > and I want to combine them into one(Routine Housework) that looks > like Routine Housework > 1)Wife(respondent).... > 2)Husband .... > 3)Everybody else .... > ----- -- Bruce Weaver [hidden email] http://sites.google.com/a/lakeheadu.ca/bweaver/ "When all else fails, RTFM." NOTE: My Hotmail account is not monitored regularly. To send me an e-mail, please use the address shown above. -- View this message in context: http://spssx-discussion.1045642.n5.nabble.com/Re-how-to-combine-5-categorical-variables-tp5713334p5713340.html Sent from the SPSSX Discussion mailing list archive at 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 PRIVILEGED AND CONFIDENTIAL INFORMATION This transmittal and any attachments may contain PRIVILEGED AND CONFIDENTIAL information and is intended only for the use of the addressee. If you are not the designated recipient, or an employee or agent authorized to deliver such transmittals to the designated recipient, you are hereby notified that any dissemination, copying or publication of this transmittal is strictly prohibited. If you have received this transmittal in error, please notify us immediately by replying to the sender and delete this copy from your system. You may also call us at (309) 827-6026 for assistance. ===================== 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 |
Re: how to combine 5 categorical variables
|
In reply to this post by dodo
I missed out on the earlier part of this, but in addition to what Art and
David have suggested, I would go back a stage and create some dummy variables using COUNT. These could be counts of all tasks done by any females, females only, any males. Males only etc. Without knowing what your variables are called, and using the categories from your value labels (assuming codes 1 to 7 in order as printed, you need to do something like this: COUNT HUSBAND = HOUSEWORK TO <var1> to <varn> (1) /FEMKIDS = HOUSEWORK TO <var1> to <varn> (2) /MALEKIDS = HOUSEWORK TO <var1> to <varn> (3) /Feminlaw = HOUSEWORK TO <var1> to <varn> (4) /Maleinlaw = HOUSEWORK TO <var1> to <varn> (5) /nobody = HOUSEWORK TO <var1> to <varn> (6) /other = HOUSEWORK TO <var1> to <varn> (7). FREQUENCIES FEMKIDS TO OTHER. TEMP. RECODE FEMKIDS TO OTHER (1 THRU HI = 1). MULT RESPONSE GROUPS = HOUSEWORK (FEMKIDS TO OTHER (1)). /FREQ HOUSEWORK. The problem is you have very small numbers in most categories, but it's the LOGIC AND process that matter in arriving at useful intermediate variables. Using COUNT as above, you may find you have larger groups which you can then use to understand your data. Hope this helps. John Hall John F Hall (Mr) Email: [hidden email] Website: www.surveyresearch.weebly.com -----Original Message----- From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of dodo Sent: 23 May 2012 19:09 To: [hidden email] Subject: Re: how to combine 5 categorical variables The variables look like: Housework - cooking Frequency Percent Valid Percent Cumulative Percent Valid Respondent 7414 91.8 91.8 91.8 Husband 19 .2 .2 92.1 Female children 170 2.1 2.1 94.2 Male children 2 .0 .0 94.2 Mother/mother-in-law 265 3.3 3.3 97.5 Father/father-in-law 2 .0 .0 97.5 Other females in the household 174 2.2 2.2 99.7 Other males in the household 2 .0 .0 99.7 Paid servant/maid 11 .1 .1 99.8 Nobody does the job 7 .1 .1 99.9 Other 7 .1 .1 100.0 Total 8073 100.0 100.0 Missing 99 2 .0 Total 8075 100.0 Housework - setting table main person Frequency Percent Valid Percent Cumulative Percent Valid Respondent 7030 87.1 87.1 87.1 Husband 34 .4 .4 87.5 Female children 689 8.5 8.5 96.0 Male children 11 .1 .1 96.2 Mother/mother-in-law 55 .7 .7 96.9 Father/father-in-law 1 .0 .0 96.9 Other females in the household 232 2.9 2.9 99.7 Other males in the household 3 .0 .0 99.8 Paid servant/maid 5 .1 .1 99.8 Nobody does the job 3 .0 .0 99.9 Other 10 .1 .1 100.0 Total 8073 100.0 100.0 Missing 99 2 .0 Total 8075 100.0 ... and I want to combine them into one(Routine Housework) that looks like Routine Housework 1)Wife(respondent).... 2)Husband .... 3)Everybody else .... -- View this message in context: http://spssx-discussion.1045642.n5.nabble.com/Re-how-to-combine-5-categorica l-variables-tp5713334p5713339.html Sent from the SPSSX Discussion mailing list archive at 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 ===================== 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 |
Re: how to combine 5 categorical variables
|
|
Would a multiple nominal optimally scaled variable from CATPCA be an option? Interpretation requires a good understanding of the method, and detailed exploration and interpretation of the associated charts/images, but it's the most common way I know of for trying to create a composite variable out of a set of attributes or nominal characteristics.
Matthew J Poes Research Data Specialist Center for Prevention Research and Development University of Illinois 510 Devonshire Dr. Champaign, IL 61820 Phone: 217-265-4576 email: [hidden email] -----Original Message----- From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of John F Hall Sent: Wednesday, May 23, 2012 3:00 PM To: [hidden email] Subject: Re: how to combine 5 categorical variables I missed out on the earlier part of this, but in addition to what Art and David have suggested, I would go back a stage and create some dummy variables using COUNT. These could be counts of all tasks done by any females, females only, any males. Males only etc. Without knowing what your variables are called, and using the categories from your value labels (assuming codes 1 to 7 in order as printed, you need to do something like this: COUNT HUSBAND = HOUSEWORK TO <var1> to <varn> (1) /FEMKIDS = HOUSEWORK TO <var1> to <varn> (2) /MALEKIDS = HOUSEWORK TO <var1> to <varn> (3) /Feminlaw = HOUSEWORK TO <var1> to <varn> (4) /Maleinlaw = HOUSEWORK TO <var1> to <varn> (5) /nobody = HOUSEWORK TO <var1> to <varn> (6) /other = HOUSEWORK TO <var1> to <varn> (7). FREQUENCIES FEMKIDS TO OTHER. TEMP. RECODE FEMKIDS TO OTHER (1 THRU HI = 1). MULT RESPONSE GROUPS = HOUSEWORK (FEMKIDS TO OTHER (1)). /FREQ HOUSEWORK. The problem is you have very small numbers in most categories, but it's the LOGIC AND process that matter in arriving at useful intermediate variables. Using COUNT as above, you may find you have larger groups which you can then use to understand your data. Hope this helps. John Hall John F Hall (Mr) Email: [hidden email] Website: www.surveyresearch.weebly.com -----Original Message----- From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of dodo Sent: 23 May 2012 19:09 To: [hidden email] Subject: Re: how to combine 5 categorical variables The variables look like: Housework - cooking Frequency Percent Valid Percent Cumulative Percent Valid Respondent 7414 91.8 91.8 91.8 Husband 19 .2 .2 92.1 Female children 170 2.1 2.1 94.2 Male children 2 .0 .0 94.2 Mother/mother-in-law 265 3.3 3.3 97.5 Father/father-in-law 2 .0 .0 97.5 Other females in the household 174 2.2 2.2 99.7 Other males in the household 2 .0 .0 99.7 Paid servant/maid 11 .1 .1 99.8 Nobody does the job 7 .1 .1 99.9 Other 7 .1 .1 100.0 Total 8073 100.0 100.0 Missing 99 2 .0 Total 8075 100.0 Housework - setting table main person Frequency Percent Valid Percent Cumulative Percent Valid Respondent 7030 87.1 87.1 87.1 Husband 34 .4 .4 87.5 Female children 689 8.5 8.5 96.0 Male children 11 .1 .1 96.2 Mother/mother-in-law 55 .7 .7 96.9 Father/father-in-law 1 .0 .0 96.9 Other females in the household 232 2.9 2.9 99.7 Other males in the household 3 .0 .0 99.8 Paid servant/maid 5 .1 .1 99.8 Nobody does the job 3 .0 .0 99.9 Other 10 .1 .1 100.0 Total 8073 100.0 100.0 Missing 99 2 .0 Total 8075 100.0 ... and I want to combine them into one(Routine Housework) that looks like Routine Housework 1)Wife(respondent).... 2)Husband .... 3)Everybody else .... -- View this message in context: http://spssx-discussion.1045642.n5.nabble.com/Re-how-to-combine-5-categorica l-variables-tp5713334p5713339.html Sent from the SPSSX Discussion mailing list archive at 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 ===================== 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 |
Re: how to combine 5 categorical variables
|
Administrator
|
In reply to this post by Melissa Ives
You could also create the Count variables (or not) then use VARSTOCASES but I don't have a crystal ball and my ESP is over rated.
Please reply to the list and not to my personal email.
Those desiring my consulting or training services please feel free to email me. --- "Nolite dare sanctum canibus neque mittatis margaritas vestras ante porcos ne forte conculcent eas pedibus suis." Cum es damnatorum possederunt porcos iens ut salire off sanguinum cliff in abyssum?" |
Automatic reply: how to combine 5 categorical variables
|
|
I am out of the office the afternoon of May 23rd and will reply to emails at that time.
If you need immediate assistance, please contact Kay Gates 303-982-6565 or
[hidden email] Heather
|
«
Return to SPSSX Discussion
|
1 view|%1 views
| Free forum by Nabble | Edit this page |