Creating an evidence-based framework to support biodiversity ...
Gavin Stewart Centre for Evidence-Based Conservation Bangor University, UK Software for Meta-analysis With thanks to Will Shadish & Julio Sanchez-Meca Outline Commercial stand-alone programs Freeware Meta-analysis macros in general packages Reviews of meta-analytic software Personal view *Note this data has not been systematically collated and critically
appraised in a uniform manner! Stand alone-1(3) Johnson, B.T. (1993). D-Stat: Software for the metaanalytic review of research literatures (version 1.1). Hillsdale, New Jersey: Erlbaum. (Lawrence Erlbaum, www site: www/erlbaum.com; email: [email protected]). Does various meta-analytic statistics including some effect size calculation. Mullen, B. (1989). Advanced BASIC Meta-Analysis. Hillsdale, New Jersey: Erlbaum. (Lawrence Erlbaum, email: [email protected]). Like Johnson. CMA-Michael Bornstein has just finished a reputedly excellent program. Order information at http://www.metaanalysis.com Does effect size calculation and metaanalysis, good graphics.
Stand alone-2 Shadish, W.R., Robinson, L., & Lu, C. (1999). ES: A Computer Program and Manual for Effect Size Calculation. St. Paul, Minnesota: Assessment Systems Corporation.: A program for computing standardized mean difference statistics with over 40 different methods. See http://188.8.131.52/wshadish/es.htm or http:// www.assess.com/ES.html. Lipsey, M.W., & Wilson, D.B. (1996). Practical MetaAnalysis. Newbury Park CA: Sage Publications. This book also makes reference to SPSS, SAS, and STATA macros that implement many analyses, and that can be downloaded for free at http:// mason.gmu.edu/~dwilsonb/ma.html. Also available is the authors' EXCEL macros for doing effect size calcuation.
Stand alone-3 M. Rosenberg, D.C. Adams, J. Gurevitch. (1999). MetaWin: Statistical Software for Meta-Analysis with Resampling Tests (Version 2.0). MetaWin can be ordered from: Sinauer Associates, Inc., P.O. Box 407, Sunderland, Massachusetts 01375-0407; fax: 413-549-1118; e-mail: [email protected]; internet: http:// www.metawinsoft.com/. Costs about $70. Does fixed and random effects models including categorical tests; and it does mixed model regression. Can handle up to 500 studies belonging to 25 classes in each of 10 grouping categories. Unique feature is that it incorporates resampling statistics (percentile bootstrap confidence limits and bias-corrected bootstrap confidence limits), and you can test for differences among classes of studies using a randomization test to evaluate between-group homogeneity.
Eddy, D.M. & Hasselblad, V. (1992). FAST*PRO: Software for Meta-analysis by the Confidence Profile Method. Boston, MA: Academic Press. Note: Book no longer in print, and software may not otherwise be available today. Freeware-1(5) Meta: Meta-analysis Programs (Vers. 5.3) (1989) [R. Schwarzer]. Raleigh, NC: National Collegiate Software Clearinghouse (http://www.RalfSchwarzer.de) MA.EXE, by Joseph Cappelleri, Pfizer Central Research, Biometrics Department, Eastern Point Road, Groton, CT 06340 ([email protected]) MACALC.EXE, by Larry Lyons, Multimedia and CBT
Development, Information and Aviation Engineer Group, Advanced Engineering and Research Associates, 1919 South Eads Street, Suite 400, Arlington, Virginia 22203, ( [email protected]). Downloadable from http:// www.lyonsmorris.com/MetaA/index.htm . Freeware-2 Carlette, W.L. (1987). The meta-analysis effect size calculator: A BASIC program for reconstructing unbiased effect sizes. Educational and Psychological Measurement, 47, 373-384. EasyMA by M. Cucherat, J.P. Boissel, A. Leizorovicz, M.C. Haugh, P. Nony, & F. Gueyffier. Can be downloaded from http://www.spc.univ-lyon1.fr/~mcu/easyma/. Developed in France
for use by clinical pharmacologists to perform meta-analyses of clinical trial data with binary outcomes using fixed or random effects methods. Meta-Analysis Easy To Answer (META), by David Kenny at the University of Connecticut (http://davidakenny.net/meta.htm). A few fairly simple effect size computations can be done, and weighted or unweighted averages can be computed using any of several systems. Freeware-3 EPIMETA (http://ftp.cdc.gov/pub/Software/epimeta/) was written for the Centers for Disease Control and is a DOS program. It has no effect size computation capacity, but does fixed and random effects modeling on
epidemiological data (e.g., risk ratios). Meta-Analyst (1995) [J. Lau]. Boston, MA: New England Medical Center. E-mail: [email protected] Meta-Test (1997) [J. Lau]. Boston, MA: New England Medical Center. E-mail: [email protected]; http:// hiru.mcmaster.ca/cochrane/cochrane/sadt.htm/; http:// som.flinders.edu.au/FUSA/Cochrane/COCHRANE/sadt.ht m /; Freeware-4 RevMan: The Cochrane Collaborations Review Manager (Vers. 5.0) (2001). The Cochrane Collaboration.
http://www.cochrane.org/cochrane/revman.htm/. MetaStat: This software is written by Lawrence M. Rudner, Gene V Glass, David L. Evartt, and Patrick J. Emery, and it does a variety of meta-analytic statistics. It can be downloaded at http://ericae.net/meta/metastat.htm. http://web.uccs.edu/lbecker/Psy590/escalc3.htm. This www page is devoted to effect size calculation, computing d or r from means and standard deviations, or from t and df. Freeware-5 www.work-learning.com/effect_sizes.htm. This web site allows you to download an excel effect size calculator with basic effect size computation capacity, along with a
manual showing the formulas and how to use the program. MIX (http://www.mix-for-meta-analysis.info): MIX stands for Meta-analysis with Interactive eXplanations. It is analytical software with extensive educational interactive tutoring. It is especially meant for students and teachers, although it provides professional numerical and graphical output and, besides analyzing the built-in data sets, one can also enter one's own data. Metadisc Zamora, Khan et al. BMC Med Res Methodol. 2006; 6: 31. observational studies/diagnostic data Macros in general packages-1(2)
BUGS y WinBUGS. http://www.mrc-bsu.cam.ac.uk//bugs/. R. http://cran.r-project.org/. SAS . Wang, M.C. & Bushman, B.J. (1999). Integrating Results through Meta-analytic Review Using SAS(R) Software. Cary, NC: SAS Institute, Inc. Kus, O. & Koch, A. (1996). Meta-analysis macros for SAS. Computational Statistics & Data Analysis, 22, 325333. http://www.prw.le.ac.uk/epidemio/personal/ajs22/meta/macros.sas/ . http://www.sas.com/. SPSS. The Lipsey and Wilson macros. See http://www.wam.umd.edu/~wilsondb/ma.html. S-Plus. http://www.mathsoft.com/splus/. http://www.prw.le.ac.uk/epidemio/personal/ajs22/meta/routine.html/ . http://www.research.att.com/~dumouchel/bsoft.html/. Macros-2
StataTM. Sterne, J.A.C., Bradburn, M.J. & Egger, M. (2001). Meta-analysis in StataTM. In M. Egger, G. Davey Smith & D.G. Altmann (Eds.), Systematic Reviews in Health Care: Meta-analysis in Context (pp. 347-369). London, UK: BMJ Pub. Group. http://www.stata.com/. StatsDirect. http://www.camcode.com/. StatXact. http://www.cytel.com/statxact True Epistat. Epistat Services, 2011 Cap Rock Circle, Richardson TX 75080-3417, phone: (214) 680-1376 (Note, this address is old, and True Epistat may not be available today). Reviews of meta-analytic software
Arthur, W., Bennett, W. & Huffcutt, A. (1994). Choice of software and programs in meta-analysis research: Does it make a difference? Educational & Psychological Measurement, 54, 776-787. Egger, M., Sterne, J.A.C. & Davey Smith, G. (2000). Meta-analysis software. British Medical Journal, 316. http://www.bmj.com/archive/7126/7126ed9.htm/ (accesed 21.11.2000). Normand, S.L. (1995). Meta-analysis software: A comparative review. American Statistician, 49, 298-309. Sterne, J.A.C., Egger, M. & Sutton, A.J. (2001). Meta-analysis software. In M. Egger, G. Davey Smith & D.G. Altmann (Eds.), Systematic Reviews in Health Care: Meta-analysis in Context (pp. 336-346). London: BMJ Pub. Group. Sutton, A.J., Lambert, P.C., Hellmich, M., et al. (2000). Meta-analysis in
practice: A critical review of available software. In D.A. Berry & D.K. Stangl (Eds.), Meta-analysis in Medicine and Health Policy. New York: Marcel Dekker. Personal view Different Paradigms Different Data Different Skills Freeware, Metawin, Stata, winbugs Check out CMA collaboration
A Framework for Human Evaluation of Search Engine Relevance Kamal Ali Chi Chao Chang Yun-fang Juan Outline The Problem Framework of Test Types Results Expt. 1: Set-level versus Item-level Expt. 2: Perceived Relevance versus Landing-Page Relevance Expt. 3: Editorial Judges...
They did this to elude their enemies and American officials, all those who were potential threats to them" (46). b. "I'm invisible" "I've stolen my brother's name. I've lost my own name and replaced it with a dead boy's. I...
Diagnostics. Symptoms (pain, functional discomfort, aesthetic discomfort) Lump in the wrist (not visible for occult ganglions) Patients seek treatment when these ganglions become associated with pain, weakness, interference with activities, and an increase in size.
The Decision-making Unit Initiator Influencer Decider Buyer User Gatekeeper Virgin Media Virgin Media targets its advertising at all members of the household decision-making unit, with the customer benefit of multiple online usage. Post-purchase evaluation of alternatives The consumer decision ...
Do not model reliabilities and are again top-heavy. Also typically assume complete rankings. Crowdsourcing: Estimating worker (grader) reliability is key component. ... Score-weighted Mallows (MALS). Bradley-Terry model (BT). Thurstone model (THUR). Plackett-Luce model (PL).
Malaria parasites in thick and thin blood films are best stained at pH 7.1 - 7.2 using a Romanowsky stain The thick film is a concentration method that may be used to detect the presence of organisms. The thin film...
Ready to download the document? Go ahead and hit continue!