Can you show an example of what you want for a 2-d version of your graph?   I would think most understandable might be just a box with the number of school mean programs. Something like this example: https://support.sas.com/kb/24/900.html only use the number to display instead of the state abbreviation. Use CBOX with CBACK=white to have the numbers appear on a white background for readability and to draw attention. Probably  still need to play with locations for some of the New England states like Connecticut and Rhode Island as may not be room   If you want to overlay a 2-dimensional rectangle then you could create an annotate data set drawing rectangles that look like a 2-d bar at each state.   Or maybe use a fill pattern to represent the bar information ... View more

The only way I can imagine fitting a mixed model, rather than a fixed effects model, that includes the predictors you have is if the census regions included are not exhaustive of all possible census regions to which you wish your inferences to apply (G-side effect), or that some sort of spatial correlation is to be applied to that variable (R side effect). In either case, a generalized estimating equation (GEE) where census_region is the clustering variable may be more tenable in terms of model convergence and run times.    SteveDenham ... View more