.-
help for ^koopman^, ^koopmani^                                      (STB-58: sg154)
.-

    ^koopman^    event_var group_var [weight] [^if^ exp] [^in^ range] [^,^ ^l^evel^(^#^)^]
 
    ^koopmani^   #x #m #y #n [^,^ ^l^evel^(^#^)^]


^fweight^s are allowed; see help @weights@.


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

^koopman^ computes the confidence intervals for the ratio of two binomial 
proportions based on two independent binomially distributed random 
variables using Koopman's method. Point estimates and confidence intervals for 
the odds ratio are calculated. 

^koopmani^ is the immediate form of ^koopman^; see help @immed@. 


Options
-------

^level(^#^)^ specifies the confidence level, in percent, for confidence intervals.
    
Examples:  Binomial data
------------------------

The table for binomial data is
        			       Event	
			           Yes       No     Total
		------------+----------------------------
		group 1     |       x      m-x       m
		group 2     |       y      n-y       n


The basic syntax for ^koopmani^ is "^koopmani^ #x #m #y #n".  For
example:

	. ^koopmani 36 40 16 80^
	. ^koopmani 36 40 16 80, level(99)^
	
The basic syntax for ^koopman^ is "^koopman^ event_var group_var".

event_var contains 1 if the observation represents event and 0 
otherwise. group_var indicates the group to which each observation 
belongs. The variable must have only two values. ^koopman^ obtains 
the table by summing across observations. Observations with missing 
values are not used.

	.^koopman event group^
	.^koopman event group, level(90)^
	.^koopman event group [freq=weight], level(90)^

If "^[freq=weight]^" is not specified, each observation contributes 1.


Author
-------

       Duolao Wang
       London School of Hygiene and Tropical Medicine, UK
       email: d.wang@@lshtm.ac.uk

Also see
--------

       STB: STB-58: sg154