-------------------------------------------------------------------------------
help for linkplot
-------------------------------------------------------------------------------

Linked scatter plots

        linkplot yvarlist xvar [if exp] [in range] [weight] , link(linkvar) [
                 asyvars cmissing({y|n}) sort(sort_varlist) plot(plot)
                 graph_options ]


Description

    linkplot plots yvarlist versus xvar such that data points are linked
    (i.e. connected) within groups defined by distinct values of linkvar. For
    example, with paired data it might be desired to link each pair, or with
    panel data it might be desired to link observations within each panel.

    aweights, fweights and pweights are allowed; see help weights.


Options
 
    link(linkvar) specifies that values of each variable in yvarlist are to
        be linked if they have the same value of linkvar. This option is
        required.

    asyvars specifies that the groups defined by linkvar should be plotted as
        if they were separate y variables.

    cmissing({y|n}) specifies whether missing values are ignored.  The
        default is to ignore missing values.  Note that this is a slight
        variant on cmissing() as explained at help connect_options.  The only
        allowed arguments are y, to ignore, and n, not to ignore.  These are
        automatically expanded to all variables plotted.

    sort(sort_varlist) specifies that values are to be linked in order of
        sort_varlist. By default values are linked in sort order of xvar, the
        last variable specified before the option comma.  Do not specify
        linkvar, as this will automatically be used.

    plot(plot) provides a way to add other plots to the generated graph; see
        help plot option.

    graph_options are options of twoway connected.


Examples 

    Box, Hunter and Hunter (1978, p.100) gave data for 10 boys on the wear of
    shoes made using materials A and B. The data are also analysed by Wild
    and Seber (2000, p.446). The units are not specified. Before exemplifying
    linkplot we make some general comments on graphing such paired data.  One
    natural data structure would be something like this:

         A          B         id
      13.2       14.0          1
       8.2        8.8          2
      10.9       11.2          3
      14.3       14.2          4
      10.7       11.8          5
       6.6        6.4          6
       9.5        9.8          7
      10.8       11.3          8
       8.8        9.3          9
      13.3       13.6         10

    This data structure permits some Stata graphs, but inhibits others.  A
    scatter plot such as scatter A B may be useful, but does not allow easy
    decoding of the difference, say A - B, which is here of central interest.
    Similarly, it is difficult to read off ratios such as A / B. If A and B
    are plotted versus id, or vice versa, the resulting graphs suffer from
    the arbitrariness of id. See also the possibilities offered by pairplot,
    which may be installed using ssc.

    Other possibilities are available after a reshape:

    . rename A wearA
    . rename B wearB
    . reshape long wear, string i(id) j(j)
    . encode j, gen(material)

    Now we have a choice, including

    . linkplot material wear, link(id) yla(1 2, valuelabel) ysc(r(0.5 2.5))
        yla(, ang(h))
    . linkplot wear material, link(id) xla(1 2, valuelabel) xsc(r(0.5 2.5))
        yla(, ang(h))


Acknowledgements

        
        Vince Wiggins made encouraging noises.


Author

        
        Nicholas J. Cox, University of Durham, U.K.
        n.j.cox@durham.ac.uk


References 

    Box, G.E.P., W.G. Hunter and J.S. Hunter. 1978.  Statistics for
        experimenters: an introduction to design, data analysis, and model
        building.  New York: John Wiley.

    Wild, C.J. and G.A.F. Seber. 2000.  Chance encounters: a first course in
        data analysis and inference.  New York: John Wiley.


Also see 

On-line: help for pairplot (if installed)