{smcl}
{* 1 October 2004}{...}
{hline}
help for {hi:tolerance}  {right:Peter Lachenbruch program}
{hline}

{title:Generate tolerance intervals from input data}
{p 8 17 2}
{cmdab:tolerance}
{it: varname  }
[{cmd:if} {it:exp}]
[{cmd:in} {it:range}] 
[,{cmd:p(}{it:#}) {cmdab:g:amma(}{it:#})]

{title:Description}
{p 4 4 2}{cmd:tolerance} generates lower and upper tolerance limits for varname assuming it is normally distributed. It also produces the multiplier for the tolerance interval. The variable name is required.  

{p 4 4 2}
{hilite: You must have a data set in memory before using this command }

{p 4 4 2}
{title:Options}

{p 4 4 2} {cmd:p(}{it:#}{cmd:)} Gives the value of the confidence level.  Default=0.95 }

{p 4 4 2} {cmdab:g:amma(}{it:#}{cmd:) }Gives the value of the coverage proportion. Default=0.9 It can be abbreviated by g({it:#})

{p 4 8 2}

{title:Examples} 

{p 4 8 2}{it:95% 95% tolerance interval for price}{p_end}

{p 4 8 2}{cmd: tolerance price, p(.95) g(.95)}

{p 4 8 2}{it:99% 95% tolerance interval for mpg}{p_end}

{p 4 8 2}{cmd: tolerance mpg, p(.99) g(.95)}   

{title:References}

{p 4 4 2}
Hahn, G. and Meeker, W. Q. {bf:Statistical Intervals} 1991 New York:John Wiley
& Sons

{title:Author}

{p 4 4 2}Peter A. Lachenbruch FDA/CBER/OBE{break} 
peter.lachenbruch@fda.hhs.gov
{p 4 4 2}with thanks to Nick Cox for comments and improvements in the program