.-
help for ^truncreg^                                               [STB-52: sg122]
.-

Truncated Regression
---------------------------

	^truncreg^ depvar [varlist] [weight] [^if^ exp] [^in^ range] [^,^ 
			^noc^onstant ^lev^el^(^#^)^ ^m^arginal ^at(^matname^)^
			^ll(^varname|#^)^ ^ul(^varname|#^)^ ^r^obust 
			^cl^uster^(^varname^)^ maximize_options ] 


^aweight^s, ^pweight^s and ^fweight^s are allowed ; see help @weights@.  

^truncreg^ shares the features of all estimation commands; see help @est@.


The syntax of @predict@ following ^truncreg^ is

	^predict^ [type] newvarname [^if^ exp] [^in^ range] [^,^ statistic ]

where statistics is

	^xb^			fitted values; the default
	^p^r^(^a^,^b^)^               Pr(a<y<b)      (a and b may be numbers
	^e(^a^,^b^)^                E(y |a<y<b)     or variables; a=. means
						-inf; b==. means inf)
	^stdp^ 			standard error of the prediction 
        ^stdf^                  standard error of the forecast

These statistics are available both in and out of sample; type "^predict^ ...
^if e(sample)^ ..." if wanted only for the estimation sample.


Description
-----------

^truncreg^ estimates a model of depvar on indepvars from a sample drawn from
a restricted part of the population. 


Options
-------

^noconstant^ suppresses the constant term (intercept) in the regression.

^level(^#^)^ specifies the significance level, in percent, for confidence intervals
    of the coefficients; see help @level@.

^ll(^varname|#^)^ and ^ul(^varname|#^)^ indicate the censoring points.  You may specify
    one or both.  ^ll()^ indicates the lower limit for left truncation.  
    Observations with depvar<=^ll()^ are left-truncated; observations with 
    depvar>=^ul()^ are right -truncated.  

^robust^ specifies that the Huber/White/sandwich estimator of variance is to be 
    used in place of the conventional MLE variance estimator. ^robust^ combined 
    with ^cluster()^ further allows observations which are not independent 
    within cluster (although they must be independent between clusters)

    if you specify ^pweights^s, ^robust^ is implied. See ^[U] 23.11 Obtaining 
    robust variance estimates^.

^cluster(^varname^)^ specifies that the observations are independent across groups.
    varname specifies to which group each observation belongs. ^cluster()^ can 
    be used with ^pweight^s to produce estimates for unstratified cluster-
    sampled data.
     
    ^cluster()^ implies ^robust^; that is, specifying ^robust cluster()^ is 
    equivalent to typing ^cluster()^ by itself.

^marginal^ estimates the marginal effects in the model in the subpopulation. 
    Whether the marginal effect or the coefficient itself is of interest 
    depends on the intended inferences of the study. If the analysis if to 
    be confined to the subpopulation, then marginal effect is of interest. 
    If the study is intended to extend to the entire population, however, 
    then it is the coefficients that are actually of interest.

^at(^matname^)^ specifies the point around which the marginal effect is to be
    estimated. The default is to estimate the effect around the mean of the
    independent variables. ^at(^matname^)^ can be specified only when ^marginal^
    is also specified.

maximize_options control the maximization process; see help maximize.  Use the
    trace option to view parameter convergence.  Use the ltol(#) option to
    relax the convergence criterion; default is 1e-6 during specification
    searches.


Options for @predict@
-------------------

^xb^, the default, calculates the linear prediction for the entire population.

^stdp^ calculates the standard error of the linear prediction.

^pr(^a^,^b^)^ calculates the Pr(a < xb+u < b), the probability that y|x would be
      observed in the interval (a,b). 
      
      a and b may be specified as numbers or variable names; ^pr(ll,ul)^ 
      calculates the probability that y|x will not be truncated. 

      a==. means minus infinity; b==. means plus infinity.

^e(^a^,^b^)^ calculates E(xb+u | a< xb+u < b), the expected value of y|x conditional
      on y|x being in the interval (a,b). ^e(ll,ul)^ calculates the expected 
      value of y|x conditional on y|x being in the subpopulation. 


Examples
--------

	. ^truncreg price mpg for, ll(4000) ul(10000)^
	. ^truncreg, marginal^
	. ^mat B=(25,1)^
	. ^truncreg, marginal at(B)^


Author
------

    Ronna Cong
    Stata Corporation 
    rcong@@stata.com


Also see
--------

 Manual:  ^[U] 23 Estimation and post-estimation commands^,
	  ^[U] 29 Overview of model estimation in Stata^,
	  ^[R] tobit^

On-line:  help for @est@, @postest@, @tobit@