List,
This must be incredibly simple, but I'm new to CTables (15.0) and I just can't get it to display the columns I need. Data in rows is categorical types of property A through E. Columns is binned 10 categories of property tax increases (e.g., 0-5%, 5-10%, etc.). I've computed 5 different scenarios of property tax laws with a different binned variable for each, all with the same bin categories. In a single table, I need to display the count and row % for each bin of all 5 scenarios so the user can see results for the scenarios side-by-side. This should be easy enough since the bin categories are identical. Any syntax and/or drop-and-drag solutions would be much appreciated! Lise ********************* Lise Valentine, Ph.D. Vice President and Director of Research The Civic Federation 177 N. State Street, Suite 400 Chicago, IL 60601 phone (312) 201-9028 fax (312) 201-9041 [hidden email] |
Depending on what you want to make easiest to compare, there are several ways to do this using the Ctables canvas.
I'll assume that you have variables PropType, scenario1,..., scenario5. These should all have categorical measurement level and value labels for each category. The simplest way to do this is to drag PropType to the rows and all five scenario variables to the columns. Then - here is the key - in the category control in the lower right of the dialog, choose column labels in rows. (This is called a comperimeter table if you want to impress your boss, though there is some argument about the spelling). This places the scenarios side by side with the % increase categories shown for each property type. You can add the percentage statistics to the default count. If you want to make it easiest to look at the effect of each scenario across the property types, drag the five scenario variables to the rows and put PropType in the columns. In that case, with more than one statistic, you will probably want to put the statistics in the rows to make it easy to read across the columns, which show property types. You do that by choosing Position: Rows in the Summary Statistics control at the bottom of the dialog. Other variations can be constructed depending on what comparisons you want to facilitate. You might also consider putting the statistics in the layer dimension of the table. HTH, Jon Peck SPSS (a few blocks west of your address) -----Original Message----- From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Lise Valentine Sent: Sunday, February 18, 2007 2:25 PM To: [hidden email] Subject: [SPSSX-L] CTables columns display List, This must be incredibly simple, but I'm new to CTables (15.0) and I just can't get it to display the columns I need. Data in rows is categorical types of property A through E. Columns is binned 10 categories of property tax increases (e.g., 0-5%, 5-10%, etc.). I've computed 5 different scenarios of property tax laws with a different binned variable for each, all with the same bin categories. In a single table, I need to display the count and row % for each bin of all 5 scenarios so the user can see results for the scenarios side-by-side. This should be easy enough since the bin categories are identical. Any syntax and/or drop-and-drag solutions would be much appreciated! Lise ********************* Lise Valentine, Ph.D. Vice President and Director of Research The Civic Federation 177 N. State Street, Suite 400 Chicago, IL 60601 phone (312) 201-9028 fax (312) 201-9041 [hidden email] |
Free forum by Nabble | Edit this page |