perceptual map
Locked
 
|
Deal all,
I have 8 checklist variables (check for favor, uncheck for unfavor). There are 3000 cases categorized as faculty, staff, admin, and students. I know how to present the 8 checklist variables in a perceptual map. Do you know the syntax on how to include the categories (faculty, staff, admin, and students) in the perceptual map? Syntax is welcome. Thank you. Johnny Get your preferred Email name! Now you can @ymail.com and @rocketmail.com. http://mail.promotions.yahoo.com/newdomains/ph/ ====================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 |
|
|
What procedure are you using? If CATPCA, then on the Object and Variable Plots subdialog, choose to Label Objects by the variable containing the categories.
Alex -----Original Message----- From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Johnny Amora Sent: Tuesday, September 23, 2008 4:51 AM To: [hidden email] Subject: perceptual map Deal all, I have 8 checklist variables (check for favor, uncheck for unfavor). There are 3000 cases categorized as faculty, staff, admin, and students. I know how to present the 8 checklist variables in a perceptual map. Do you know the syntax on how to include the categories (faculty, staff, admin, and students) in the perceptual map? Syntax is welcome. Thank you. Johnny ===================== 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 |
|
|
In reply to this post by Johnny Amora
This can be done with CATPCA by specifying the categorical variable as a supplementary variable with multiple nominal scaling level. Then you can request a biplot of loadings (checklist variables represented as vectors) and centroids, or a joint plot with all the checklist variables (represented as points) and the categorical variable.
I might know how to do it if you are not using CATPCA, but then I would need to know how you make a perceptual map? Regards, Anita van der Kooij Data Theory Group Leiden University ________________________________ From: SPSSX(r) Discussion on behalf of Johnny Amora Sent: Tue 23/09/2008 11:51 To: [hidden email] Subject: perceptual map Deal all, I have 8 checklist variables (check for favor, uncheck for unfavor). There are 3000 cases categorized as faculty, staff, admin, and students. I know how to present the 8 checklist variables in a perceptual map. Do you know the syntax on how to include the categories (faculty, staff, admin, and students) in the perceptual map? Syntax is welcome. Thank you. Johnny Get your preferred Email name! Now you can @ymail.com and @rocketmail.com. http://mail.promotions.yahoo.com/newdomains/ph/ ======= 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 ********************************************************************** This email and any files transmitted with it are confidential and intended solely for the use of the individual or entity to whom they are addressed. If you have received this email in error please notify the system manager. ********************************************************************** ====================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 |
|
|
In reply to this post by Reutter, Alex
Hi Alex,
Thank you for your suggestion. But I have a couple of followup questions. As a background, there are 8 checklist variables (coded 1/2) and one grouping variable (called group) with 9 nominal categories. The questions are as follow: In the main dialog box of CATPCA, I placed the 8 checklist variables in the "Analysis variables"; then, the group variable in the "supplementary variables". In the Object and Variable Plots, I chose variable in the label Object, then I put the "group' under selected. My question is, why each of the 9 categories appeared many times on the biplot. I supossed that there would be 9 points corresponding to the categories. But the number of points appeared is equal to the number of cases. Everybody are welcome to give comments. Thanks. Johnny --- On Tue, 9/23/08, Reutter, Alex <[hidden email]> wrote: From: Reutter, Alex <[hidden email]> Subject: Re: perceptual map To: [hidden email] Date: Tuesday, 23 September, 2008, 9:30 PM What procedure are you using? If CATPCA, then on the Object and Variable Plots subdialog, choose to Label Objects by the variable containing the categories. Alex -----Original Message----- From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Johnny Amora Sent: Tuesday, September 23, 2008 4:51 AM To: [hidden email] Subject: perceptual map Deal all, I have 8 checklist variables (check for favor, uncheck for unfavor). There are 3000 cases categorized as faculty, staff, admin, and students. I know how to present the 8 checklist variables in a perceptual map. Do you know the syntax on how to include the categories (faculty, staff, admin, and students) in the perceptual map? Syntax is welcome. Thank you. Johnny ===================== 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 New Email addresses available on Yahoo! Get the Email name you've always wanted on the new @ymail and @rocketmail. Hurry before someone else does! http://mail.promotions.yahoo.com/newdomains/ph/ ====================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 |
|
|
Hi Johnny,
I think I misunderstood exactly what it was you wanted. IIRC, Anita van der Kooij also replied to your post, and I think her solution will give you what you're looking for. Alex ________________________________ From: Johnny Amora [mailto:[hidden email]] Sent: Wednesday, October 08, 2008 4:18 AM To: [hidden email]; Reutter, Alex Subject: Re: perceptual map Hi Alex, Thank you for your suggestion. But I have a couple of followup questions. As a background, there are 8 checklist variables (coded 1/2) and one grouping variable (called group) with 9 nominal categories. The questions are as follow: In the main dialog box of CATPCA, I placed the 8 checklist variables in the "Analysis variables"; then, the group variable in the "supplementary variables". In the Object and Variable Plots, I chose variable in the label Object, then I put the "group' under selected. My question is, why each of the 9 categories appeared many times on the biplot. I supossed that there would be 9 points corresponding to the categories. But the number of points appeared is equal to the number of cases. Everybody are welcome to give comments. Thanks. Johnny --- On Tue, 9/23/08, Reutter, Alex <[hidden email]> wrote: From: Reutter, Alex <[hidden email]> Subject: Re: perceptual map To: [hidden email] Date: Tuesday, 23 September, 2008, 9:30 PM What procedure are you using? If CATPCA, then on the Object and Variable Plots subdialog, choose to Label Objects by the variable containing the categories. Alex -----Original Message----- From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Johnny Amora Sent: Tuesday, September 23, 2008 4:51 AM To: [hidden email] Subject: perceptual map Deal all, I have 8 checklist variables (check for favor, uncheck for unfavor). There are 3000 cases categorized as faculty, staff, admin, and students. I know how to present the 8 checklist variables in a perceptual map. Do you know the syntax on how to include the categories (faculty, staff, admin, and students) in the perceptual map? Syntax is welcome. Thank you. Johnny ===================== 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 ________________________________ Yahoo! Toolbar is now powered with Search Assist. Download it now! <http://sg.rd.yahoo.com/ph/search/toolbar/mail/signature/*http:/ph.toolbar.yahoo.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 |
|
|
HOMALS was replaced with Multiple Correspondence in version ?? (13 I think): Analyze menu, Data Reduction, Optimal Scaling, choose All variables multiple nominal. Then the window title is Multiple Correspondence. If you have an older version, you can choose Some variables not multiple nominal (CATPCA), then choose optimal scaling level multiple nominal for all the checklist variables.
Select the categorical variable as supplementary variable and also choose multiple nominal. Then click Plots, Category and select all variables for the Joint plot. Is this what you want? Regards, Anita ________________________________ From: Johnny Amora [mailto:[hidden email]] Sent: Wed 08/10/2008 07:53 To: Kooij, A.J. van der Subject: RE: perceptual map Hi, I am sorry, I am using HOMALS procedure. The biplot is not useful because its too "cloudy". Thanks. ********************************************************************** This email and any files transmitted with it are confidential and intended solely for the use of the individual or entity to whom they are addressed. If you have received this email in error please notify the system manager. ********************************************************************** ====================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 |
|
|
In reply to this post by Reutter, Alex
I didn't receive the mail from Johnny below, in which it becomes clear what the problem is.
>In the main dialog box of CATPCA, I placed the 8 checklist variables in the "Analysis variables"; then, the >group variable in the "supplementary variables". In the Object and Variable Plots, I chose variable in the >label Object, then I put the "group' under selected. My question is, why each of the 9 categories appeared >many times on the biplot. I supossed that there would be 9 points corresponding to the categories. But the >number of points appeared is equal to the number of cases. In the objects and loadings biplot not the categories of the group variable are included, but the object scores (component/factor scores) for the persons, hence a points for all cases. If you want to display the categories of the group variable, you should choose Plot, Loadings, Include centroids (centroids for the group variable) or Plot, Categories, and select all variables for the Joint plot. Regards, Anita ________________________________ From: SPSSX(r) Discussion on behalf of Reutter, Alex Sent: Wed 08/10/2008 16:12 To: [hidden email] Subject: Re: perceptual map Hi Johnny, I think I misunderstood exactly what it was you wanted. IIRC, Anita van der Kooij also replied to your post, and I think her solution will give you what you're looking for. Alex ________________________________ From: Johnny Amora [mailto:[hidden email]] Sent: Wednesday, October 08, 2008 4:18 AM To: [hidden email]; Reutter, Alex Subject: Re: perceptual map Hi Alex, Thank you for your suggestion. But I have a couple of followup questions. As a background, there are 8 checklist variables (coded 1/2) and one grouping variable (called group) with 9 nominal categories. The questions are as follow: In the main dialog box of CATPCA, I placed the 8 checklist variables in the "Analysis variables"; then, the group variable in the "supplementary variables". In the Object and Variable Plots, I chose variable in the label Object, then I put the "group' under selected. My question is, why each of the 9 categories appeared many times on the biplot. I supossed that there would be 9 points corresponding to the categories. But the number of points appeared is equal to the number of cases. Everybody are welcome to give comments. Thanks. Johnny --- On Tue, 9/23/08, Reutter, Alex <[hidden email]> wrote: From: Reutter, Alex <[hidden email]> Subject: Re: perceptual map To: [hidden email] Date: Tuesday, 23 September, 2008, 9:30 PM What procedure are you using? If CATPCA, then on the Object and Variable Plots subdialog, choose to Label Objects by the variable containing the categories. Alex -----Original Message----- From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Johnny Amora Sent: Tuesday, September 23, 2008 4:51 AM To: [hidden email] Subject: perceptual map Deal all, I have 8 checklist variables (check for favor, uncheck for unfavor). There are 3000 cases categorized as faculty, staff, admin, and students. I know how to present the 8 checklist variables in a perceptual map. Do you know the syntax on how to include the categories (faculty, staff, admin, and students) in the perceptual map? Syntax is welcome. Thank you. Johnny ===================== 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 ________________________________ Yahoo! Toolbar is now powered with Search Assist. Download it now! <http://sg.rd.yahoo.com/ph/search/toolbar/mail/signature/*http:/ph.toolbar.yahoo.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 ********************************************************************** This email and any files transmitted with it are confidential and intended solely for the use of the individual or entity to whom they are addressed. If you have received this email in error please notify the system manager. ********************************************************************** ====================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 |
|
|
In reply to this post by Kooij, A.J. van der
That's right, it was v13. Just to clarify, Multiple Correspondence replaced Homogeneity Analysis in the dialogs, but HOMALS is still available via syntax; however, the newer Multiple Correspondence procedure is more feature rich.
Alex -----Original Message----- From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Kooij, A.J. van der Sent: Wednesday, October 08, 2008 9:21 AM To: [hidden email] Subject: Re: perceptual map HOMALS was replaced with Multiple Correspondence in version ?? (13 I think): Analyze menu, Data Reduction, Optimal Scaling, choose All variables multiple nominal. Then the window title is Multiple Correspondence. If you have an older version, you can choose Some variables not multiple nominal (CATPCA), then choose optimal scaling level multiple nominal for all the checklist variables. Select the categorical variable as supplementary variable and also choose multiple nominal. Then click Plots, Category and select all variables for the Joint plot. Is this what you want? Regards, Anita ________________________________ From: Johnny Amora [mailto:[hidden email]] Sent: Wed 08/10/2008 07:53 To: Kooij, A.J. van der Subject: RE: perceptual map Hi, I am sorry, I am using HOMALS procedure. The biplot is not useful because its too "cloudy". Thanks. ===================== 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 |
|
|
In reply to this post by Kooij, A.J. van der
I have a couple of follow-up questions about the outputs. 1. In the plot output particularly "joint plot of category Points", can we interpret the association of the group categories with the categories of the other variables considering that "group" is specified as supplementary variable? Yes. A supplementary variable is fitted into the component structure for the other variables. 2. In the same plot (joint plot of category Points), why are the points on the plot representing the categories are connected by lines? What are the connotations of such lines? The category points for a variable are always on a straight line through the origin (except for variables with Multiple nominal scaling level). This line has the same orientation as the loading vector (see loadings plot), but it's lenght does not indicate the VAF as the loading vector does. 3. In conjunction with question #2 above, is a syntax for removing the lines from the plot? I have more plots to construct and it would be impractical if I would erase/delete the lines manually from the plots usign the chart editor. Do you really want to remove the lines? they are helpful in locating the categories of a variable, because they are all on the same line, I would think. If you remove them in chart editor, save as template and apply template to all plots. I don't know of another way. Regards, Anita ________________________________ From: Johnny Amora [mailto:[hidden email]] Sent: 09 October 2008 05:21 To: [hidden email]; Kooij, A.J. van der Subject: Re: perceptual map Hi everyone, Using the paste facility of SPSS, I acquired the syntax of the CATPCA procedure which I executed. The syntax is presented below for everybody's scrutiny. I have a couple of follow-up questions about the outputs. 1. In the plot output particularly "joint plot of category Points", can we interpret the association of the group categories with the categories of the other variables considering that "group" is specified as supplementary variable? 2. In the same plot (joint plot of category Points), why are the points on the plot representing the categories are connected by lines? What are the connotations of such lines? 3. In conjunction with question #2 above, is a syntax for removing the lines from the plot? I have more plots to construct and it would be impractical if I would erase/delete the lines manually from the plots usign the chart editor. Thank you in advance for your kind help. Johnny Amora De La Salle-College of Saint Benilde Manila, Philippines CATPCA VARIABLES=S1 S2 S3 S4 S5 S6 S7 S8 S9 group /ANALYSIS=S1(WEIGHT=1,LEVEL=NOMI) S2(WEIGHT=1,LEVEL=NOMI) S3(WEIGHT=1 ,LEVEL=NOMI) S4(WEIGHT=1,LEVEL=NOMI) S5(WEIGHT=1,LEVEL=NOMI) S6(WEIGHT=1 ,LEVEL=NOMI) S7(WEIGHT=1,LEVEL=NOMI) S8(WEIGHT=1,LEVEL=NOMI) S9(WEIGHT=1 ,LEVEL=NOMI) group(LEVEL=NOMI) /MISSING=S1(PASSIVE,MODEIMPU) S2(PASSIVE,MODEIMPU) S3(PASSIVE,MODEIMPU) S4(PASSIVE,MODEIMPU) S5(PASSIVE,MODEIMPU) S6(PASSIVE,MODEIMPU) S7(PASSIVE ,MODEIMPU) S8(PASSIVE,MODEIMPU) S9(PASSIVE,MODEIMPU) group(PASSIVE,MODEIMPU) /SUPPLEMENTARY=VARIABLE( group ) /DIMENSION=2 /NORMALIZATION=VPRINCIPAL /MAXITER=100 /CRITITER=.00001 /PRINT=CORR LOADING /PLOT=BIPLOT( CENTR ) ( group ) (20) OBJECT ( group ) (20) JOINTCAT( S1 S2 S3 S4 S5 S6 S7 S8 S9 group ) (20) LOADING ( ( CENTR ) ) (20) . --- On Wed, 10/8/08, Kooij, A.J. van der <[hidden email]> wrote: From: Kooij, A.J. van der <[hidden email]> Subject: Re: perceptual map To: [hidden email] Date: Wednesday, 8 October, 2008, 10:31 PM I didn't receive the mail from Johnny below, in which it becomes clear what the problem is. >In the main dialog box of CATPCA, I placed the 8 checklist variables in the "Analysis variables"; then, the >group variable in the "supplementary variables". In the Object and Variable Plots, I chose variable in the >label Object, then I put the "group' under selected. My question is, why each of the 9 categories appeared >many times on the biplot. I supossed that there would be 9 points corresponding to the categories. But the >number of points appeared is equal to the number of cases. In the objects and loadings biplot not the categories of the group variable are included, but the object scores (component/factor scores) for the persons, hence a points for all cases. If you want to display the categories of the group variable, you should choose Plot, Loadings, Include centroids (centroids for the group variable) or Plot, Categories, and select all variables for the Joint plot. Regards, Anita ________________________________ From: SPSSX(r) Discussion on behalf of Reutter, Alex Sent: Wed 08/10/2008 16:12 To: [hidden email] Subject: Re: perceptual map Hi Johnny, I think I misunderstood exactly what it was you wanted. IIRC, Anita van der Kooij also replied to your post, and I think her solution will give you what you're looking for. Alex ________________________________ From: Johnny Amora [mailto:[hidden email]] Sent: Wednesday, October 08, 2008 4:18 AM To: [hidden email]; Reutter, Alex Subject: Re: perceptual map Hi Alex, Thank you for your suggestion. But I have a couple of followup questions. As a background, there are 8 checklist variables (coded 1/2) and one grouping variable (called group) with 9 nominal categories. The questions are as follow: In the main dialog box of CATPCA, I placed the 8 checklist variables in the "Analysis variables"; then, the group variable in the "supplementary variables". In the Object and Variable Plots, I chose variable in the label Object, then I put the "group' under selected. My question is, why each of the 9 categories appeared many times on the biplot. I supossed that there would be 9 points corresponding to the categories. But the number of points appeared is equal to the number of cases. Everybody are welcome to give comments. Thanks. Johnny --- On Tue, 9/23/08, Reutter, Alex <[hidden email]> wrote: From: Reutter, Alex <[hidden email]> Subject: Re: perceptual map To: [hidden email] Date: Tuesday, 23 September, 2008, 9:30 PM What procedure are you using? If CATPCA, then on the Object and Variable Plots subdialog, choose to Label Objects by the variable containing the categories. Alex -----Original Message----- From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Johnny Amora Sent: Tuesday, September 23, 2008 4:51 AM To: [hidden email] Subject: perceptual map Deal all, I have 8 checklist variables (check for favor, uncheck for unfavor). There are 3000 cases categorized as faculty, staff, admin, and students. I know how to present the 8 checklist variables in a perceptual map. Do you know the syntax on how to include the categories (faculty, staff, admin, and students) in the perceptual map? Syntax is welcome. Thank you. Johnny ===================== 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 ________________________________ Yahoo! Toolbar is now powered with Search Assist. Download it now! <http://sg.rd.yahoo.com/ph/search/toolbar/mail/signature/*http:/ph.toolb ar.yahoo.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 ********************************************************************** This email and any files transmitted with it are confidential and intended solely for the use of the individual or entity to whom they are addressed. If you have received this email in error please notify the system manager. ********************************************************************** ====================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 ________________________________ Yahoo! Toolbar is now powered with Search Assist. Download it now! <http://sg.rd.yahoo.com/ph/search/toolbar/mail/signature/*http://ph.tool bar.yahoo.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 |
|
|
Thank you for your help.
johnny --- On Thu, 10/9/08, Kooij, A.J. van der <[hidden email]> wrote: From: Kooij, A.J. van der <[hidden email]> Subject: Re: perceptual map To: [hidden email] Date: Thursday, 9 October, 2008, 7:23 PM I have a couple of follow-up questions about the outputs. 1. In the plot output particularly "joint plot of category Points", can we interpret the association of the group categories with the categories of the other variables considering that "group" is specified as supplementary variable? Yes. A supplementary variable is fitted into the component structure for the other variables. 2. In the same plot (joint plot of category Points), why are the points on the plot representing the categories are connected by lines? What are the connotations of such lines? The category points for a variable are always on a straight line through the origin (except for variables with Multiple nominal scaling level). This line has the same orientation as the loading vector (see loadings plot), but it's lenght does not indicate the VAF as the loading vector does. 3. In conjunction with question #2 above, is a syntax for removing the lines from the plot? I have more plots to construct and it would be impractical if I would erase/delete the lines manually from the plots usign the chart editor. Do you really want to remove the lines? they are helpful in locating the categories of a variable, because they are all on the same line, I would think. If you remove them in chart editor, save as template and apply template to all plots. I don't know of another way. Regards, Anita ________________________________ From: Johnny Amora [mailto:[hidden email]] Sent: 09 October 2008 05:21 To: [hidden email]; Kooij, A.J. van der Subject: Re: perceptual map Hi everyone, Using the paste facility of SPSS, I acquired the syntax of the CATPCA procedure which I executed. The syntax is presented below for everybody's scrutiny. I have a couple of follow-up questions about the outputs. 1. In the plot output particularly "joint plot of category Points", can we interpret the association of the group categories with the categories of the other variables considering that "group" is specified as supplementary variable? 2. In the same plot (joint plot of category Points), why are the points on the plot representing the categories are connected by lines? What are the connotations of such lines? 3. In conjunction with question #2 above, is a syntax for removing the lines from the plot? I have more plots to construct and it would be impractical if I would erase/delete the lines manually from the plots usign the chart editor. Thank you in advance for your kind help. Johnny Amora De La Salle-College of Saint Benilde Manila, Philippines CATPCA VARIABLES=S1 S2 S3 S4 S5 S6 S7 S8 S9 group /ANALYSIS=S1(WEIGHT=1,LEVEL=NOMI) S2(WEIGHT=1,LEVEL=NOMI) S3(WEIGHT=1 ,LEVEL=NOMI) S4(WEIGHT=1,LEVEL=NOMI) S5(WEIGHT=1,LEVEL=NOMI) S6(WEIGHT=1 ,LEVEL=NOMI) S7(WEIGHT=1,LEVEL=NOMI) S8(WEIGHT=1,LEVEL=NOMI) S9(WEIGHT=1 ,LEVEL=NOMI) group(LEVEL=NOMI) /MISSING=S1(PASSIVE,MODEIMPU) S2(PASSIVE,MODEIMPU) S3(PASSIVE,MODEIMPU) S4(PASSIVE,MODEIMPU) S5(PASSIVE,MODEIMPU) S6(PASSIVE,MODEIMPU) S7(PASSIVE ,MODEIMPU) S8(PASSIVE,MODEIMPU) S9(PASSIVE,MODEIMPU) group(PASSIVE,MODEIMPU) /SUPPLEMENTARY=VARIABLE( group ) /DIMENSION=2 /NORMALIZATION=VPRINCIPAL /MAXITER=100 /CRITITER=.00001 /PRINT=CORR LOADING /PLOT=BIPLOT( CENTR ) ( group ) (20) OBJECT ( group ) (20) JOINTCAT( S1 S2 S3 S4 S5 S6 S7 S8 S9 group ) (20) LOADING ( ( CENTR ) ) (20) . --- On Wed, 10/8/08, Kooij, A.J. van der <[hidden email]> wrote: From: Kooij, A.J. van der <[hidden email]> Subject: Re: perceptual map To: [hidden email] Date: Wednesday, 8 October, 2008, 10:31 PM I didn't receive the mail from Johnny below, in which it becomes clear what the problem is. >In the main dialog box of CATPCA, I placed the 8 checklist variables in the "Analysis variables"; then, the >group variable in the "supplementary variables". In the Object and Variable Plots, I chose variable in the >label Object, then I put the "group' under selected. My question is, why each of the 9 categories appeared >many times on the biplot. I supossed that there would be 9 points corresponding to the categories. But the >number of points appeared is equal to the number of cases. In the objects and loadings biplot not the categories of the group variable are included, but the object scores (component/factor scores) for the persons, hence a points for all cases. If you want to display the categories of the group variable, you should choose Plot, Loadings, Include centroids (centroids for the group variable) or Plot, Categories, and select all variables for the Joint plot. Regards, Anita ________________________________ From: SPSSX(r) Discussion on behalf of Reutter, Alex Sent: Wed 08/10/2008 16:12 To: [hidden email] Subject: Re: perceptual map Hi Johnny, I think I misunderstood exactly what it was you wanted. IIRC, Anita van der Kooij also replied to your post, and I think her solution will give you what you're looking for. Alex ________________________________ From: Johnny Amora [mailto:[hidden email]] Sent: Wednesday, October 08, 2008 4:18 AM To: [hidden email]; Reutter, Alex Subject: Re: perceptual map Hi Alex, Thank you for your suggestion. But I have a couple of followup questions. As a background, there are 8 checklist variables (coded 1/2) and one grouping variable (called group) with 9 nominal categories. The questions are as follow: In the main dialog box of CATPCA, I placed the 8 checklist variables in the "Analysis variables"; then, the group variable in the "supplementary variables". In the Object and Variable Plots, I chose variable in the label Object, then I put the "group' under selected. My question is, why each of the 9 categories appeared many times on the biplot. I supossed that there would be 9 points corresponding to the categories. But the number of points appeared is equal to the number of cases. Everybody are welcome to give comments. Thanks. Johnny --- On Tue, 9/23/08, Reutter, Alex <[hidden email]> wrote: From: Reutter, Alex <[hidden email]> Subject: Re: perceptual map To: [hidden email] Date: Tuesday, 23 September, 2008, 9:30 PM What procedure are you using? If CATPCA, then on the Object and Variable Plots subdialog, choose to Label Objects by the variable containing the categories. Alex -----Original Message----- From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Johnny Amora Sent: Tuesday, September 23, 2008 4:51 AM To: [hidden email] Subject: perceptual map Deal all, I have 8 checklist variables (check for favor, uncheck for unfavor). There are 3000 cases categorized as faculty, staff, admin, and students. I know how to present the 8 checklist variables in a perceptual map. Do you know the syntax on how to include the categories (faculty, staff, admin, and students) in the perceptual map? Syntax is welcome. Thank you. Johnny ===================== 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 ________________________________ Yahoo! Toolbar is now powered with Search Assist. Download it now! <http://sg.rd.yahoo.com/ph/search/toolbar/mail/signature/*http:/ph.toolb ar.yahoo.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 ********************************************************************** This email and any files transmitted with it are confidential and intended solely for the use of the individual or entity to whom they are addressed. If you have received this email in error please notify the system manager. ********************************************************************** ====================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 ________________________________ Yahoo! Toolbar is now powered with Search Assist. Download it now! <http://sg.rd.yahoo.com/ph/search/toolbar/mail/signature/*http://ph.tool bar.yahoo.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 How can I fight insomnia? Discover how on Yahoo! Answers! ====================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 |
«
Return to SPSSX Discussion
|
1 view|%1 views
| Free forum by Nabble | Edit this page |