parse_dissim.hlp

是一个经济学管理应用软件 很难找的 但是经济学学生又必须用到

{smcl}
{* 10mar2005}{...}
{cmd:help parse_dissim}{right:also see:  {help undocumented}}
{hline}

{title:Title}

{p 4 22 2}
{hi:parse_dissim} {hline 2} Parse similarity and dissimilarity measures


{title:Syntax}

{p 8 21 2}
{cmd:parse_dissim} [{it:{help measure_option:measure}}]
[{cmd:,} {cmd:default(}{it:default_{help measure_option:measure}}{cmd:)} ]


{title:Description}

{pstd}
{cmd:parse_dissim} takes the similarity or dissimilarity name found in
{it:measure} and checks it against the list of those provided by Stata, taking
account of allowed minimal abbreviations and aliases.  Aliases are resolved
(for instance, {cmd:Euclidean} is changed into the equivalent {cmd:L2}).  The
resolved name and other information about the {it:measure} is returned in
{cmd:s()} (see below).  An error message is produced and return code 198 is
returned if {it:measure} is not one of the allowed similarity and
dissimilarity measures.  See {help measure option} for a listing of allowed
similarity and dissimilarity {it:measure}s and their definitions.


{title:Option}

{phang}
{opt default(default_measure)}
    specifies the default similarity or dissimilarity measure when
    {it:measure} is not specified.  The default for {cmd:default()} is
    {cmd:L2} (alias Euclidean distance).  See {help measure option} for a list
    of allowed measures.


{title:Example}

    Within a program

	...
	{cmd:parse_dissim `sim'}
	{cmd:local sim "`s(dist)'"}
	{cmd:if "`s(dtype)'" != "similarity" | "`s(binary)'" != "binary" {c -(}}
		{cmd:di as error "only binary similarity measures are allowed"}
		{cmd:exit 198}
	{cmd:{c )-}}
	...


{title:Saved results}

{pstd}
{cmd:parse_dissim} saves in {cmd:s()}:

    Macros
{p2colset 9 22 26 2}{...}
{p2col:{cmd:s(dist)}}
	(dis)similarity measure name unabbreviated and with aliases resolved
	{p_end}
{p2col:{cmd:s(unab)}}
	(dis)similarity measure name unabbreviated but without aliases resolved
	{p_end}
{p2col:{cmd:s(darg)}}
	argument (enclosed in parentheses) of (dis)similarities that take them,
	such as {cmd:L(}{it:#}{cmd:)}
	{p_end}
{p2col:{cmd:s(dtype)}}
	the word {cmd:similarity} or {cmd:dissimilarity}
	{p_end}
{p2col:{cmd:s(drange)}}
	range of measure (most similar to most dissimilar); a dot means
	infinity
	{p_end}
{p2col:{cmd:s(binary)}}
	the word {cmd:binary} if the measure is for binary observations
	{p_end}
{p2colreset}{...}


{title:Also see}

{psee}
Online:
{help cluster programming},
{helpb matrix dissimilarity},
{help measure option}
{p_end}