# 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

*21 septembre 2018*

*18 octobre 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

19 juillet 2018# The Stata module "Clv"

# Description

**Clv** clusters variables around latent components. The variables are clustered stepwise by seeking to minimize at each step the decrease of the T criterion, computed as the sum of the first eigenvalues of the matrices of data of all the clusters. A hierarchical cluster analysis based on this criterion is performed. A consolidation procedure can be run subsequently which allows each variable to be assigned to the latent component it is the most correlated with.

# Download

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

# Syntax (version 2.14)

**clv** *[varlist]* [**if** *expr*] [**in** *range*] [*weight*] [, __nostand__ardized__bar__** consolidation**(

*#*)

__noden__dro**(**

__cut__number*#*)

__deltaT__

__hor__izontal

__show__count**(**

__abb__rev*#*)

**(**

__tit__le*string*)

**(**

__cap__tion*string*)

**(**

__ker__nel*numlist*)

**(**

__meth__od*string*)

__nobip__lot

__add__var**(**

__genlv__*string*)

__rep__lace**(**

__texts__ize*string*)

**(**

__saved__endro*filename[,replace]*)

__std__**(**

__dim__*string*) ]

# Notes

If no *varlist* is indicated, the procedure uses the *varlist* from the last **clv** procedure, but does not perform the hierarchical cluster analysis.

Only **fweights** are allowed. The biplots are disabled if weights are used.

The individuals with one or several missing values are omitted.

With the *polychoric* and *polychoricv2* methods, the **nostandardized** option is disabled.

This module uses the following modules downloadable on SSC: **polychoric**, **biplotvlab** and **genscore**.

The author thanks Ronan Conroy for its propositions of improvements.

# Options:

: uses centered variables instead of standardized variables__nostand__ardized: displays a chart of the decrease in the T criterion at each step__bar__(__cons__olidation*#*): performs a consolidation procedure with the obtained partition into the specified number of clusters (by default, no consolidation procedure is performed): suppresses the display of the dendogram.__noden__dro(__cut__number*#*): limits the dendrogram to the specifed number of clusters: uses the variation of the T criterion as height variable for the dendrogram__deltaT__: displays an horizontal (instead vertical) dendrogram__hor__izontal: displays the number of variables in each cluster (usefull with the__show__count**cutnumber**option)(__abb__rev*#*): defines the length of the variables labels on the dendrogram (15 characters by default)(__tit__le*string*): defines the title of the dendrogram(__cap__tion*string*): defines the caption of the axis of the dendrogram which indicates the names of the variables(__ker__nel*numlist*): defines one or several kernels of variables (variables which are clustered together in an initial step). The first number indicates that the first variables are clustered together, the second number indicates that the following variables are clustered together...(__meth__od*string*): indicates the method to cluster the variables among*classical*(by default) for the method described by Vigneau and Qannari,*polychoric*for a use of the matrix of polychoric coefficients of correlation (instead of Pearson coefficients of correlation),*v2*for a modified algorithm wich search to minimize the maximum second eigenvalue among the clusters of 2 variables and more,*polychoricv2*which correspond to the*v2*option with the matrix of polychoric coefficients of correlation, and*centroid*which is defined by Vigneau and Qannari as an adaptation of CLV when the sign of the correlation coefficients between the variables is important.: avoids to display a biplot of the latent variables with the__nobip__lot**consolidation**option: adds the variables on the biplot realized with the latent variables (only with the__add__var**consolidation**option)(__genlv__*string*): saves the latent variables in new variables with the string as prefix (followed by a number). This option must be used in conjonction with the**consolidation**option.: allows replacing the variables creates with the__rep__lace**genlv**option if they already exist.(__texts__ize*string*): defines the size of the labels of the variables on the dendrogram (see help textsizestyle).(__saved__endro*filename[,replace]*): saves the dendrogram in the file defined by this option. If this file already exists, it is possible to replace it with the**replace**option.: allows standardizing the latent variables for the graphical representation on the biplot.__std__(__dim__*string*): allows choosing the axes represented on the biplot.

# Examples:

**clv var1-var15**

**clv var1-var15, cons(6) bar nodendro**

**clv, cons(3)**

# Outputs:

# Historic

- DIM and STD options for biplots

- corrections of bugs in KERNEL option and with METHOD(centroid)

**savedendro**option

- Size of the text in the dendrogram

- 2nd order relative variation of the T criterion
- Allows saving the latent variables

- allows following the polychoric methods by a consolidation process
- Allows using weights

- Allows using the matrix of polychoric correlation coefficients (instead of the Pearson correlation coefficients)
- Draws a biplot of the latent variables Allows to consider the sign of the correlation coefficients
- Graphical improvements

- Fix a bug in the consolidation procedure when there is negative correlations between the variables

- Fix a bug in the consolidation procedure when there is cluster(s) with only one variable

- Implementation of the basic version of the CLV procedure (without consideration of the sign of the correlation coefficients between the variables, and without consideration of external variables)
- Implementation of the consolidation procedure