Dear all,

to produce a bivariate scatterplot of two variables X and Y, I use this simple syntax:

GRAPH

/SCATTERPLOT(BIVAR)= X WITH Y

/MISSING=LISTWISE.

However, both X and Y represent mean scores aggregated from individual values of 20 different samples. Given that sample sizes are very different (ranging from n=20 to n=1350), I'would also like to show horizontal error bars in the graph visualizing the standard error of each mean. Can anyone suggest a syntax that could produce such a scatterplot?

Many thanks in advance!

Nina

=====================

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