heterogi



Stata help for heterogi

-------------------------------------------------------------------------------
help for heterogi
-------------------------------------------------------------------------------


Heterogeneity measures

heterogi #Q #df [, level(#) format(%fmt) ncchi2 ]

where

#Q is the Cochran's Chi-Square or Q-test #df is the degrees of freedom

Description

heterogi provides the statistics H and I^2 to quantify heterogeneity in a meta-analysis.

Remark

It is an immediate command, see help immed. The Q-test can be obtained by metan or meta command. Options

level(#) specifies the width of the confidence interval; see help level.

format(%fmt) specifies the display format for presenting numbers in the table's cells.

ncchi2 specifies the use of the noncentral chi-squared distribution to calculate confidence intervals. The default is the test-based confidence interval (Higgins and Thompson, 2002).

Examples

. heterogi 14.4 24 . heterogi 14.4 24, level(99) . heterogi 14.1 11, nc . heterogi 81.5 19, nc f(%3.2f) . heterogi 41.5 7 . heterogi 130.3 3

Authors

Nicola Orsini, Division of Nutritional Epidemiology, IMM, Karolinska Institutet, Sweden Julian P.T. Higgins, MRC Biostatistics Unit, Cambridge, UK Matteo Bottai, Arnold School of Public Health, University of South Carolina, USA Iain Buchan, Northwest Institute for Bio-Health Informatics, University of Manchester, UK

Reference

Higgins J.P.T. and Thompson S.G., Quantifying heterogeneity in a meta-analysis, Statistics in Medicine, 2002, 21: 1539-1558

Support

http://nicolaorsini.altervista.org nicola.orsini@ki.se

Also see

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

Worked examples for heterogi

Click here to run or save the do-file

. capture net install http://nicolaorsini.altervista.org/stata/heterogi

. which heterogi c:\ado\stbplus\h\heterogi.ado *! version 2.0 N.Orsini, I. Buchan, 25 Jan 06 *! version 1.0 N.Orsini, J.Higgins, M.Bottai, 16 Feb 2005

. . heterogi 14.4 24

------------------------------------------------------ Statistic | Estimate [95% Conf. Interval] ----------+------------------------------------------- H | 1.0 1.0 1.3 I^2 | 0 0 44 ------------------------------------------------------ Q-test = 14.4 d.f. = 24 p-value = 0.9371

. heterogi 14.4 24, level(99)

------------------------------------------------------ Statistic | Estimate [99% Conf. Interval] ----------+------------------------------------------- H | 1.0 1.0 1.5 I^2 | 0 0 53 ------------------------------------------------------ Q-test = 14.4 d.f. = 24 p-value = 0.9371

. heterogi 14.1 11, nc

------------------------------------------------------ Statistic | Estimate [95% Conf. Interval] ----------+------------------------------------------- H | 1.1 1.0 1.6 I^2 | 22 0 60 ------------------------------------------------------ Q-test = 14.1 d.f. = 11 p-value = 0.2275

. heterogi 81.5 19, nc f(%3.2f)

------------------------------------------------------ Statistic | Estimate [95% Conf. Interval] ----------+------------------------------------------- H | 2.07 1.64 2.49 I^2 | 76.69 62.79 83.81 ------------------------------------------------------ Q-test = 81.5 d.f. = 19 p-value = 0.0000

. heterogi 41.5 7

------------------------------------------------------ Statistic | Estimate [95% Conf. Interval] ----------+------------------------------------------- H | 2.4 1.8 3.3 I^2 | 83 68 91 ------------------------------------------------------ Q-test = 41.5 d.f. = 7 p-value = 0.0000

. heterogi 130.3 3

------------------------------------------------------ Statistic | Estimate [95% Conf. Interval] ----------+------------------------------------------- H | 6.6 5.1 8.6 I^2 | 98 96 99 ------------------------------------------------------ Q-test = 130.3 d.f. = 3 p-value = 0.0000


{Home | Author | Presentations | Publications | Software | Courses | Links}