{smcl}
{* 12April2004}{...}
{hline}
help for {hi:meta_lr}
{hline}
 
{title:Graph of positive and negative likelihood ratios in diagnostic test}


	{cmd:meta_lr} {theta1} {se_theta1} {theta2} {se_theta2} {stratavariables} [{cmd:if}{it:exp}] [{cmd:in}{it:range}]
	[{cmd:,} {cmdab:st:ratify} {cmd:combine} {cmdab:we:ighting} {cmd:id(strvar)} {cmdab:f:ix} {cmdab:e:form} {cmd:ylab} {cmd:graphoption}]
 

{title:Description}
{p 4 4 2}

	{cmd:meta_lr} does mainly two things: it can do stratified meta-analysis of individual estimates 
	{it:theta1} and {it:theta2} by {it:stratavariables}, save the stratified pooled estimates and 
	their confidence intervals in new data set and draw them in one graph; if stratified variables are not
	given, {cmd:meta_lr} draw {it:theta1} and {it:theta2} and their confidence interval by individual study
	in one graph, with or without weighting. Combined meta-analysis results are shown in star.

	This command is mainly used to draw graph in diagnostic test.The user provides the effect estimate as thetas 
	(e.g., log positive likelihood ratio and log negative likelihood ratio). Likewise, the user provides the 
	standard error of thetas. 
	
	Commands {help meta} and {help metareg} must be installed before using this command.

{title:options for stratified analysis}

	{cmd:stratify} must be given when do the stratified analysis. Meanwhile, at least one {it:stratavariable} must be given.

	{cmd:fix} indicates statified meta-analysis using fixed model. Default is random effect model. 

	{cmd:eform} is the same option as in {help meta}. It requests that the output of stratified meta-analysis
	is exponentiated. When this option is chosen, option {cmd:xscale(log)} is suggested to use. 
	
	{cmd:ylab} gives labels on y axis. These labels are the strata variables. 
	
	{cmd:graphoption} the following graph options of STATA 8 can be used in this command. {cmd:symbol() msize()}
	{cmd:mcolor() xscale() xline() xlabel() blpattern() blcolor() ytitle() xtitle() scheme()}

{title:options for not stratified analysis}

	Option {cmd:stratify} must not be given.

	{cmd:id(strvar)} is a character variable which is used to label the studies. A string variable must be given.
	
	{cmd:combine} provide the combined estimates of {it:theta1} and {it:theta2} with their confidence intervals. In graph, they 
	are shown in star with two vertical lines to show the combined point estimates. {cmd:combine} can be chosen together with 
	{cmd:fix} which means that fixed meta-analysis model is used, random model is the default one.
	
	{cmd:weighting} gives individual study weights. If {cmd:fix} is chosen, weights are reverse of variance of {it:theta1} and
	{it:theta2}. If {cmd:fix} is not chosen, weights are 1/(tau^2 + variance).
	
	{cmd:fix} define that combined estimates are obtained from fixed meta-analysis and weighting is reverse of variance. Default 
	is that combined estimates are from random effect model and weights are 1/(tau^2 + variance). 
	
	{cmd:graphoption} the same as for stratified analysis.
	
{title:Required input variables}

	{cmd:theta1}	 the first effect estimate (for example log negative likelihood ratio)
	{cmd:se_theta1}  the corresponding standard error


	{cmd:theta2}	 the second effect estimate (for example log positive likelihood ratio)
	{cmd:se_theta2}  the corresponding standard error
	
	{cmd:theta1} and {cmd:theta2} can be the same effect estimates. This means that stratified meta-analysis will 
	be done only on one effect estimate and the graph only shows for one estimate. Hence, this command also can be
	used in meta-analysis of randomised controlled trails which will show the similar graph as {help meta}. However
	{cmd:meta_lr} provide more options, with or without combine, weighting and more graph options. The disadvantage is 
	that the user needs to type the same theta and its corresponding standard error twice.
	
	{cmd:stratavariable} are the stratified variables. They must be discrete or binary variables. These variables are re-grouped
	before drawing the graph. For example, if the user has a variable called test which can be 0, 0.5 or 1. This variable 
	is re-grouped to 1, 2 and 3. This change is made in order to label y axis. But the user's data set will not be changed
	at all.
	
	
{title:Example}

	.{cmd: meta_lr llrpos llrposse llrneg llrnegse test funding, stratify fix eform xscale(log) xline(1)}
	.{cmd: meta_lr llrpos llrposse llrneg llrnegse, id(author) combine weighting}
	.{cmd: meta_lr logitsens se_sens logitsens se_sens, id(author) combine}
	
{title:Author}

	Aijing Shang
	Institute of Social and Preventive Medicine, University Berne, Switzerland
	Email: shang@ispm.unibe.ch
	
{title:Also see}

	On-line: help for {help meta} (if installed), {help metan} (if installed), {help metareg} (if installed)