{smcl}
{* 14june2007}{...}
{hline}
help for {hi:traces}{right:Jean-Benoit Hardouin}
{hline}

{title:Graphical representations of the traces of dichotomous and polytomous items}

{p 8 14 2}{cmd:traces} {it:varlist} [{cmd:,} {cmdab:s:core} {cmdab:r:estscore}
{cmdab:ci} {cmdab:t:est} {cmdab:cum:ulative} {cmdab:l:ogistic}
{cmdab:repf:ile}({it:directory}) {cmdab:scoref:iles}({it:string})
{cmdab:restscoref:iles}({it:string}) {cmdab:logisticf:ile}({it:string})
{cmdab:nod:raw} {cmdab:nodrawc:omb} {cmdab:rep:lace} {cmdab:only:one}({it:varname}) {cmdab:thr:esholds}({it:string})]


{title:Description}

{p 4 8 2}{cmd:traces} builds graphical representations of various kinds of
traces (non parametric Item Response Functions) for dichotomous or polytomous items.

{title:Options}

{p 4 8 2}{cmd:score} displays the graphical representations of the traces of the
items as a function of the total score. This is the defaut option if none {cmd:score},
none {cmd:restscore}, none {cmd:logistic} are indicated.

{p 4 8 2}{cmd:restscore} displays the graphical representations of the
traces of the items as a function of the rest-score (total score unless the item).

{p 4 8 2}{cmd:ci} displays the confidence interval at 95% of the traces.

{p 4 8 2}{cmd:test} tests the nullity of the slope of dichotomous items traces
with a linear model.

{p 4 8 2}{cmd:cumulative} displays cumulative traces for polytomous
items instead of classical traces.

{p 4 8 2}{cmd:logistic} displays the graphical representation of the logitic
traces of the items as a function of the score: each trace is the result of a
logistic model with the response to the item as variable to explicate and the
score (and a constant) as explicative variable. This kind of trace is possible
only for dichotomous items. All the logistic traces are represented in the same
graph.

{p 4 8 2}{cmd:repfile}({it:directory}) is the directory where the files are saved.

{p 4 8 2}{cmd:scorefiles}({it:string}) defines the generic name of the files containing the graphical representations of the traces as a function of the score. 
The name will be followed by the name of each item and by the .gph extension. If this option is not
indicated, the corresponding graphs will be not saved.

{p 4 8 2}{cmd:restscorefiles}({it:string}) defines the generic name of the files containing the graphical representations of the traces as a function of the rest-scores.
The name will be followed by the name of each item and by the .gph extension. If this option is not
indicated, the corresponding graphs will be not saved.

{p 4 8 2}{cmd:logisticfile}({it:string}) defines the name of the file containing the graphical representations of the logistic traces. This name will be followed by the .gph extension. 
If this option is not indicated, the corresponding graph will be not saved.

{p 4 8 2}{cmd:nodraw} does not display the graphs by items.

{p 4 8 2}{cmd:nodrawcomb} does not display the combined graphs by items.

{p 4 8 2}{cmd:replace} replaces graphical files when they already exist.

{p 4 8 2}{cmd:onlyone} displays only the trace of a given item.

{p 4 8 2}{cmd:thresholds} groups the individuals as a function of the (rest-)score. The string contains the maximal values of the (rest-)score in  each group.



{title:Example}

	{p 4 8 2}{cmd:. traces item1 item2 item3 item4 , score repfile(c:\graphs) scorefiles(score) nodraw nodrawcomb replace} /*creates the graphs files of the
traces as a function of the score but do not display them.*/

	{p 4 8 2}{cmd:. traces item1 item2 item3 item4 , score restscore} /*displays
the graphical representations of the traces of the items as a function of the
score and of the rest-scores, but does not save them*/

	{p 4 8 2}{cmd:. traces itemA*}  /*displays the graphical
representations of the traces of the items as a function of the score, by
default*/

	{p 4 8 2}{cmd:. traces itemA*} ,only(itemA2) thresholds(2 3 5)/*displays the graphical
representations of the traces of the item A2 as a function of the score. Individuals are grouped: a first group of individuals with scores from 0 to 2, a second group with a score of 3, a third group with a score between 4 and 5 and a last group with a score superior to 5*/

{title:Author}

{p 4 8 2}Jean-Benoit Hardouin, PhD, assistant professor{p_end}
{p 4 8 2}Team of Biostatistics, Clinical Research and Subjective Measures in Health Sciences{p_end}
{p 4 8 2}University of Nantes - Faculty of Pharmaceutical Sciences{p_end}
{p 4 8 2}1, rue Gaston Veil - BP 53508{p_end}
{p 4 8 2}44035 Nantes Cedex 1 - FRANCE{p_end}
{p 4 8 2}Email:
{browse "mailto:jean-benoit.hardouin@univ-nantes.fr":jean-benoit.hardouin@univ-nantes.fr}{p_end}
{p 4 8 2}Websites {browse "http://www.anaqol.org":AnaQol}
and {browse "http://www.freeirt.org":FreeIRT}

{title:Also see}

{p 4 13 2}Online: help for {help graph}, {help loevH} and {help gengroup} if installed.{p_end}