{smcl}
{* 31Aug2002}{...}
{hline}
help for {hi:loevH}
{hline}

{title:Loevinger's H coefficients}

{p 8 14}{cmd:loevH} {it:varlist} [{cmd:,} {cmdab:h} {cmdab:hj} {cmdab:hjk}
{cmdab:e} {cmdab:ej} {cmdab:ejk} {cmdab:e0} {cmdab:ej0} {cmdab:ejk0}]


{p}{it:varlist} is a list of two existing dichotomous variables or more.

{title:Options}

{p 0 4}{cmd:h} display the Loevinger H coefficient for all the items of the scale.

{p 0 4}{cmd:hj} display the Loevinger H coefficient for each item of the scale with respect of all the others items.

{p 0 4}{cmd:hjk} display the Loevinger H coefficient for each pair of items of the scale.

{p 0 4}{cmd:e} display the sum of the number of Guttman errors between all the pairs of items.

{p 0 4}{cmd:ej} display the sum of the number of Guttman errors for each item of the scale.

{p 0 4}{cmd:ejk} display the sum of the number of Guttman errors fror each pair of items of the scale.

{p 0 4}{cmd:e0} display the sum of the number of expected Guttman errors between all the pairs of items.

{p 0 4}{cmd:ej0} display the sum of the number of expected Guttman errors for each item of the scale.

{p 0 4}{cmd:ejk0} display the sum of the number of expected Guttman errors fror each pair of items of the scale.


{title:Description}

{p}{cmd:loevH} calculate the Loevinger's H coefficient between all the pairs of items of {it:varlist}, and compute the Loevinger's Hj coefficient for each item of {it:varlist} with respect of all the others items and the Loevinger's H coefficient for the set of items of {it:varlist}.


{title:Remarks} 

For detailed information on the Loevinger's H coefficients, see Loevinger (1948) or Hemker and al. (1995).

{cmd:loevH} display none result by default. {cmd:loevH} don't permit the use of polytomous items. 


{title:Example}

	{inp:. loevH item1 item2 item3 item4}

{title:Results}

The Loevinger's H coefficients between all the pais of items are saved in the matrix r(loevHjk).

The Loevinger's H coefficients for each item with respect of all the others items are saved in the matrix r(loevHj).

The Loevinger's H coefficient for the set of items is saved in the scalar r(loevH).

{title:References}

Hemker B. T., Sijtsma K. and Molenaar I. W., Selection of unidimensional scales from a multidimensional item bank in the polytomous Mokken IRT 
model, {it: Applied Psychological Measurement}, vol.19(4), 1995, pp. 337-352. 

Loevinger J., The technique of homogeneous tests compared with some aspects of "scale analysis" and factor analysis. {it:Psychological bulletin},
vol. 45, 1948, pp. 507-530.

{title:Author}

{p 4 8 2}Jean-Benoit Hardouin, Regional Health Observatory (ORS) - 1, rue Porte Madeleine - BP 2439 - 45032 Orleans Cedex 1 - France.
You can contact the author at {browse "mailto:jean-benoit.hardouin@neuf.fr":jean-benoit.hardouin@neuf.fr} and visit the websites {browse "http://anaqol.free.fr":AnaQol} and {browse "http://freeirt.free.fr":FreeIRT}