# 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

*25 juin 2018*

* *

# Last publications

*06 juin 2018*__ Tessier P__*The European Journal of Health Economics*: .

*06 juin 2018*__ Tessier P__*BMJ Open*, **8**(2): .

*15 mai 2018*__ Maruani A__*Oral Dis*, **24**(4): 552-60.

*15 mai 2018*__ Sautenet B__*Am J Kidney Dis*, **71**(5): 690-700.

*02 mai 2018* __ Hardouin JB__*Trials*, **19**(1): 260.

# Updated

20 juin 2018# The Stata module "Hcavar"

# Description

**hcavar** realizes a Hierarchical Clusters Analysis on variables. The variables can be numerous, ordinal or binary. The distances (dissimilarity measures for binary variables) between two variables are computed as the squared root of 2 times one minus the Pearson correlation. For binary variables, it is possible to use other similarity coefficients as Matching, Jaccard, Russel or Dice. The distance matrix is computed as the squared root of one minus the value of these coefficients. In the field of Item Response Theory, it is possible to define conditional measures to the score as defined by Roussos, Stout and Marden (1998): conditional correlations, conditional covariance, or Mantel-Haenszel measures of similarity. In the same field, it is possible to compute, for a set of obtained partition of the items, the DETECT, Iss and R indexes defined by Zhang and Stout (1999).

# Download

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

# Syntax (version 3.2)

**hcavar** *varlist* [, **prox**(

*jaccard(alias a)/ matching(alias ad)/ pearson(alias corr)/ russel/ dice/ ccov/ ccor/ mh*)

**(**

__method__*single/ complete/ average(alias upgma)/ waverage(alias wpgma)/ median/ wards*)

**(**

__partition__*numlist*)

__measures__**(**

__mat__rix*matrix*)

__detect__**]**

__nodendro__gram# Notes

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

**(**

__detect__*version 3.1*): ssc install detect

**(**

__genscore__*version 1.4*): ssc install genscore

The old name of **hcavar** is **hcaccprox** (versions 1 et 2).

# Options:

(__prox__*jaccard(alias a)/ matching(alias ad)/ pearson(alias corr)/ russel/ dice/ ccov/ ccor/ mh*): allows chosing the proximity measures (*pearson*by default)(__method__*single/ complete/ average(alias upgma)/ waverage(alias wpgma)/ median/ wards*): allows defining the aggregation method (*waverage*- by default). The keyword can be, or not, followed by "linkage"(__partition__*numlist*): allows giving details about the partitions defined in*numlist*: displays the proximity matrix between the items__measures__(__mat__rix*matrix*): Use the*matrix*matrix as distance matrix between the variables: computes, for the partitions defined in the__detect__**partition**option, the indexes DETECT, Iss and R: enables the displaying of the dendrogram.__nodendro__gram

# Examples:

**hcavar var1-var10**

**hcavar var*, partition(1/6) measures method(single)**

**hcavar itemA1-itemA7 itemB1-itemB7, prox(ccor) method(single) detect part(1/4)**

# Outputs:

**: distance matrix between the variables**

__r(measures)__**: Number of variables**

__r(nbvar)__**: matrix obtained with the**

__r(clusters)__**partition**option containing the composition of the partitions defined with this option

**: obtained with the**

__r(indexes)__**detect**option. This matrix contain the DETECT, Iss and R indexes associated to each partition defined with the

**partition**option.

# Historic

- Possibility to use Polytomous Items with CCOR, CCOV and MH

- Correction if there is only one individual with a given score

- Allows numerous or ordinal variables to be used
- All the aggregation methods defined in Stata are allowed
- New dissimilarity distances for binary variables (Russel, Dice)
- Corrections for the
*ccor*,*ccov*and*mh*dissimilarity measures - Allows a matrix to be used as distance matrix between the variables

- Improvements about the outputs

- Hierarchical Clusters Analysis
- 6 proximity measures (a, ad, cor, ccov, ccor, mh)
- 3 aggregation methods (simple linkage, complete linkage, Unweighted Pair-Group Method of Averages)
- Can compute the DETECT indexes for obtained partitions
- The associated Stata program partition permit to detail some specific partition after hcaccprox
- The Stata program Detect is required