Re: st: Commands for cluster analysis

[Rose Medeiros <rosem@cisunix.unh.edu>]

Ping,
The base command is cluster, but there are a number of options, typing 
"help cluster" in stata will give you a list of all the commands.  
Specifying generate(varname) after the comma will generate a variable 
based on the clusters. I'd like to give you a strong word of caution 
against thinking about clusters as "natural" because they are strongly 
influenced by the decision you, as the researcher, make. As with other 
techniques, the variables you select to base the clusters on are very 
influential, but there are also a lot of other decisions the researcher 
has to make in the process of performing cluster analysis.  For example, 
whether hierarchical or nonhierarchical clustering is used, which 
specific method within these broad classes is used, the number of 
clusters to be formed, etc. These decisions are important because they 
will often have a strong influence on your results. The specific type of 
clustering to be used (e.g. kmeans versus kmedian) can be suggested by 
the distribution of your data, but most of the decisions will need to be 
informed by theory.
Best,
Rose


Ping Zheng wrote:


> Dear all
>
> We are conducting inward FDI locational determinants by using a panel
> data set with 28 home countries. we'd like to try a country cluster
> analysis to cluster the home countries into different groups naturally
> by Stata. What are the commands for this and what are the commands for
> regressing the different groups obtained from clustering by using OLS
> and Random Effects GLS?
>
> Many thanks for your help
> Ping
>
>
>
> *
> *   For searches and help try:
> *   http://www.stata.com/support/faqs/res/findit.html
> *   http://www.stata.com/support/statalist/faq
> *   http://www.ats.ucla.edu/stat/stata/
>
>  
*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/