Hello! I have two plotting questions, please forgive me if the questions seem trivial: 1. I'm trying to understand how I can plot hierarchical logistic regression in SPSS or alternatively in Excel after exporting the data. I have 3 models and would like to make a plot for the final one. All the variables (dependent and independent) are dichotomous (hierarchical binomial logistic regression). 2. This question is about plotting chi square results. The dependent variable is dichotomous, but not all independent variables are. Naturally, I will be making several plots, but I would be thankful for a simple explanation on what is the process. For now the only examples I've seen included ordinal or continuous dependent variables, which makes it easier. Thank you! Best, Kseniya. 
Maybe others understand what you are wanting to do but I’m confused. So, first, “hierarchical logistic regression”, to do this analysis are you using the logistic
command or the genlin or genlinmixed commands. “Hierarchical” has multiple meanings and I don’t know which you mean. Let’s say you are using logistic. What would the plots look like? Are you wanting one plot for each IV or something that displays multiple
IVs? So for a dichotomous IV, wouldn’t a bar chart work: percent Yes for IV1=0 and percent Yes for IV1=1. For a continuous IV, you are going to need to categorize the IV values so that you can get the percent Yes for each IV value segment. So far as I know you have two choices. One choice is GGraph; the other is Graph. From the Graphs dropdown, Chart builder is, I think, ggraph and Legacy dialogs
is Graph. If these are “lookat and discard” graphs, the legacy dialogs are much, much easier to use, but if you want much nicer looking graphs, then chart builder.
Also, if you will do a archives search for the Andy W, you can look at example ggraph examples. Andy is a graphing artist. Gene Maguin From: SPSSX(r) Discussion [mailto:[hidden email]]
On Behalf Of Kseniya Katsman Hello! I have two plotting questions, please forgive me if the questions seem trivial: Best, Kseniya. ===================== To manage your subscription to SPSSXL, send a message to
[hidden email] (not to SPSSXL), with no body text except the command. To leave the list, send the command SIGNOFF SPSSXL For a list of commands to manage subscriptions, send the command INFO REFCARD

Free forum by Nabble  Edit this page 