-------------------------------------------------------------------------------
help for grby 
-------------------------------------------------------------------------------

Bar charts

        grby yvar xvar1 [xvar2] [if exp] [in range] [, format(%fmt) shading(#)
              yscale(# #) means ci(##) connect numbers vlabel v1label v2label
              title(text) saving(filename[,replace])]

           yvar     continuous or categorical variable on y-axis.
          xvar1     first categorical variable on x-axis.
          xvar2     second categorical variable on x-axis. 

Description

grby displays a bar chart for each covariate pattern.  Sums or means of yvar
determine the height of the bars.  In the latter case you can specify the level
of a confidence interval. This program works under Stata 7 and Stata 8 and it
is based on gph.

Options

    format(%fmt) specifies the display format for sums or means over the bars.
        
    shading(#) specifies the amount of shading on a scale 0 up to 4, with 0 bei
> ng the lightest and 4 the darkest.
        
    yscale(# #) specifies the minimum and maximum value of y-axis.
        
    means specifies that means of yvar determine the height of the bars (the de
> fault are the sums).
        
    ci(##) specifies the level to figure out a confidence intervals for the mea
> ns. This option is available only 
             with the option means. The mean value for a covariate pattern with
>  only one observation is signed by X.

    connect with a line the means on the graph. This option is available only w
> ith ci.

    numbers specifies the number (sum or mean) over the bar (or point if ci is 
> specified).
    
    vlabel specifies the variable label.
        
    v1label specifies the value label for xvar1.
        
    v2label specifies the value label for xvar2.
        
    title(text) specifies a title on the top of the graph.
    
    saving(filename[,replace]) saves the graph in the current directory

Examples

     . webuse lbw, clear  
     . xtile aged = age, nq(10)      
     . label var aged "decile age"    
     . label define smoke 0 "No" 1 "Yes"  
     . label values smoke smoke       
     . label var smoke "smoking"       
     . grby lwt race, nu format(%9.0g)   
     . grby lwt race smoke, nu format(%9.0g)      
     . grby lwt race smoke, nu format(%3.1f) mean v v1 v2        
     . grby lwt race smoke, nu format(%3.1f) mean ci(95)     
     . grby lwt race smoke, nu format(%3.1f) mean ci(95) v  v1 v2       
     . grby lwt race smoke, nu format(%3.1f) mean ci(95) v  v1 v2 connect    
     . grby lwt aged, nu                      
     . grby lwt aged smoke, mea ci(95)      
     . grby lwt aged race, mea ci(95) co v v2   
     . grby lwt aged race, mea ci(99) co v v2 yscale(100 200) 

Authors

    Nicola Orsini, Institute of Environmental Medicine, Karolinska
    Institutet, Stockholm, Sweden and Institute of Information Science and
    Technology, National Research Council of Italy, Pisa, Italy.

    Matteo Bottai, Arnold School of Public Health, University of South
    Carolina, Columbia, USA and Institute of Information Science and
    Technology, National Research Council of Italy, Pisa, Italy.

Support

        Nicola Orsini, http://nicolaorsini.altervista.org, Karolinska
            Institutet, Sweden
        nicola.orsini@imm.ki.se

Also see

 Manual: [G] gph
 Manual: [G] graph

 On-line:  help for gph, graph