Hi,

Which one of the Metan or Meta commands do you run?

The following is the command that I used in my analysis:

metan or lowerci upperci, eform fixed second(random) effect (Odds Ratio) rcols(population) label (namevar=author, yearvar=yearofpublication) favours(MetS-#MetS+) textsize(200) xsize(20) ysize(20)

The command resulted in having a forest plot with the weight of each study.

Hope you find it helpful.

Thank you for your useful answer. I wonder whether you have a sample graphic output to demonstrate this or provide reference to your publications which may have similar output. Thanks.

Dear Wen Wu

In STATA you can perform analysis of diagnostic accuracy of diagnostic test by using the command

metandi true-positive false-positive false-negative true-negative

When performing the HSROC plot use the command

 metandiplot true-positive false-positive false-negative true-negative

For further information I suggest reading the following article

Harbord RM, Whiting P. metandi: Meta-analysis of diagnostic accuracy using hierarchical logistic regression. Stata Journal. 2009;9(2):211-29.

Kind Regards

Thank you all for the insightful answers above. What method I used for obtaining summary statistics is bivariate model.  

The bivariate model utilizes a hierarchical structure of the distribution of data in terms of two levels corresponding to variation within and between studies[EW1]  and preserves the two-dimensional nature of diagnostic accuracy. Considering the significant between-study heterogeneity, it is more appropriate to use this model. Secondly, it allows for a potential correlation between sensitivity and specificity and manages the differences in the precision of the two estimates. At last, the bivariate model takes into account the effect of covariates that affect sensitivity and specificity, which means explanatory variables can be added to the model. This model is currently regarded as the optimal method for acquiring pooled statistics for meta-analysis of diagnostic test accuracy trial and recommended by the Diagnostic Test Accuracy Working Group of the Cochrane Collaboration and the Agency for Healthcare Research and Quality (AHRQ).