# Research

Topics Publications In progress publications Communications# Packages

AnaQol Project PRO-online R Packages Online R-package# Life of the unit

Projects Collaborations PhD thesis Traineeships Traineeships propositions Seminars# Next seminars

*27 juin 2019*

* *

# Last publications

*01 mai 2019*__ Perrot B__*Scandinavian Journal of Gastroenterology*, **8**: 1-7.

*09 avril 2019*__ Rouquette A____ Hardouin JB____ Sébille V__*PLOS One*, **14**(4): e0215073.

*15 mars 2019*__ Hardouin JB__*Gastrointestinal Endoscopy*, **89**(3): 626-636.

*07 mars 2019*__ Prudhomme T____ Rousselet M____ Feuillet F____ Grall-Bronnec M____ Victorri-Vigneau C__*BMC Oral Health*, **19**: 42.

*01 mars 2019*__ Leducq S____ Giraudeau B____ Tavernier E____ Maruani A__*J Am Acad Dermatol*, **80**(3): 735-42.

# Updated

24 mai 2019# The Stata module "Backrasch"

# Description

**Backrasch** realizes a backward procedure on a Rasch model: the items are removed one per one if they have a bad fit to the Rasch model. The fit of the items is valuated by a first-order statistics (test R1c, R1m or Q1). It is possible to build several sub-scales of items, the second sub-scale is build with the items unselected in the first sub-scales, the third one with the items unselected in the two first sub-scales, and so on... By default, the parameters of the Rasch model are estimated by conditional maximum likelihood (CML), but it is possible to estimate them by marginal maximum likelihood (MML) or generalized estimating equations (GEE).

# Download

Type "findit backrasch" or "ssc install backrasch" directly from your Stata browser.

# Syntax (version 2)

**backrasch** *varlist* [, ** method**(

*cml/mml/gee*)

**(**

__t__est*R/Q*)

**(**

__p__*#*)

**(**

__nbsc__ales*#*)

__nodetail__**]**

__noautog__roup# Notes

This program requires an access to the following program(s):

**(**

__raschtestv7__*version 7.2.1*): scc install raschtestv7

# Options:

(__m__ethod*cml/mml/gee*): defines the method of estimation of the difficulty parameters among conditional maximum likelihood (*cml*- by default), marginal maximum likelihood (*mml*) or generalized estimating equations (*gee*).(__t__est*R/Q*): defines the first order statistics to use between*R*-type test (R1c or R1m - by default) or the Q1 test of Van den Wollenberg (*Q*)(__p__*#*): defines the level of signification who define a significantly bad fitted item (0.05 by default)(__nbsc__ales*#*): defines the maximal number of sub-scales to build. By default, the program builds only one sub-scale: does not display the description of the algorithm__nodetail__: forces the program to compute the first order fit statistics with the groups defined by the value of the score. by default, the scores are grouped to obtained groups of 30 individuals or more__noautog__roup

# Examples:

**backrasch item***

**backrasch itemA* itemB*, p(0.2) method(mml) nodetail**

**backrasch itemA* itemB1-itemB7 , p(0.1) nbsc(5) noautog**

# Outputs:

**: Numer of the scale in which each item is selected**

__r(selection)__# Historic

- Possibility to estimate the parameters by GEE
- Possibility to use R1c or R1m tests to valuate the fit of the items
- Possibility to groups scores to made the first order tests more robust

- Realization of a backward procedure based on the Rasch model
- The selection of the items is based on the Q1 statistics
- Possibility to select several scales