Jul 11, 2012 ... Psychometrics With Stata. The Pilot Study. Item Response Characteristics. Item
Response Theory. What are the characteristics of each item?
Jul 11, 2005 - Reproducible Research Using Stata. reStructuredText. Examples. Reproducible .... Page 15 ... Two stata commands: stata2doc and s2d do-file.
Nov 3, 2003 - 91. 92. 93. 93. 94. 95. 96. 97. 98. 100. 100. 102. 103. 104. 105. 106. 106. 107. 109. 109 ...... The Stata manual [GS] Getting Started with Stata is very helpf1.u, especially [Gs]. 3 A sample ...... set obs 1000 obs Yas 0 , noY 1000.
Web: www.epigear.com. Email: [email protected] ...... The MetaXL menu also gives access to input templates for setting up your own meta- analysis, see the ...
Meta-regression using MetaXL to create the dataset and Stata to run the regression analysis . ..... MetaXL is free, but copyrighted software. MetaXL may be ...
The MetaXL menu also gives access to input templates for setting up your own meta- ... an Excel workbook, but that each must have a unique name (and this ...... thus, strictly speaking, a concept like SUCRA does not make sense. ..... that the pooled
Web: www.epigear.com. Email: [email protected] ...... The installation program installs an Excel add-in (called 'MetaXL.xll'), together with this documentation file ...
Jul 31, 2014 - Classification, or predictive discriminant analysis, involves the ... Methods available in statistics, machine learning, predictive analytics.
Mar 31, 2006 - gllamm y d1 c_r_d1 d2, i(id) eqs(load) l(ident logit) f(gauss binom) /*. */ lv(var) ..... Downloadable from http://www.statmodel.com/muthen1.pdf.
Marcello Pagano, Harvard School of Public Health ... Ian White, MRC Biostatistics Unit, Cambridge. Nicholas J. G. Winter, University of ... âbeyond the Stata manualâ in explaining key features or uses of Stata that are of interest to intermediate
Aug 11, 2000 - The Stata Technical Bulletin (STB) and the contents of the supporting files (programs, .... Christopher F. Baum, Boston College, [email protected].
Aug 11, 2000 - 17. cs5 float %8.4f. Spline at 4,070. 18. cs6 float %8.4f. Spline at 4,840 ...... For purposes of illustration, we use an example with only two independent ...... programming tutorials, illustrations of data analysis techniques, discus
Aug 11, 2000 - See www.stata.com/bookstore/stbj.html for details. Submissions to the STB, including submissions to the supporting files (programs, datasets, ...
commands ssc install tab_chi and ssc install ipf to get the most current ... Pearson
chi2(5) = 18.4557 Pr = 0.002 ... observed expected obs - exp Pearson |.
We can draw path diagrams using Stata's SEM Builder ... Generalized responses (binary, ordered, count, etc). â Multilevel data structures ... more pairs of endogenous variables ... Ha: diff != 0. Ha: diff > 0. Ho: diff = 0 degrees of freedom = 72 d
Jul 4, 2013 - likely that users will need to drop unneeded variables when loading the data. One possibility is to conver
Oct 6, 2015 - ABSTRACT. Students-t test is the most popular statistical test. ... Researchers would need to use statistical software and packages to conduct.
The HFCS has several particularities that make it a rather complex data set, though using the appropriate Stata .... for
relationship between two variables (i.e. X and Y) and 2) this relationship is additive ...... http://wps.aw.com/aw_stock_ie_2/50/13016/3332253.cw/index.html.For a ...
We use regression to estimate the unknown effect of changing one variable over another (Stock and .... Business/Repair S
T-test and ANOVA (Analysis of Variance) compare group means, assuming variables .... Detrended normal P-P and Q-Q plots
proportion of total observations and is more appropriate for large N samples (Figure ... Detrended normal P-P and Q-Q pl
Decomposition of the Gini coefficient using Stata. Alejandro López-Feldman. Universidad de Guanajuato. (Moving to CIDE in June) ...
Meta-Regression using MetaXL and STATA â Prevalence with categorical moderators. Download and ... Open STATA -> Data -> Data Editor -> Data Editor (Edit) ...
META-REGRESSION USING METAXL AND STATA Prevalence with categorical moderators
Dr Janni Leung National Drug and Alcohol Research Centre (NDARC) UNIVERSITY OF NEW SOUTH WALES 2018
Adapted from: MetaXL User Guide *https://www.epigear.com/index_files/metaxl.html
Meta-Regression using MetaXL and STATA – Prevalence with categorical moderators
Download and install MetaXL: https://www.epigear.com/index_files/metaxl.html
Open example: MetaXL -> MetaXL User Guide -> ThyCancerMetaRegres.xls
Adapted from MetaXL User Guide: https://www.epigear.com/index_files/metaxl.html
1
Set up data:
Get input data for meta-regression: MetaXL -> Results -> Meta-Regression data
Adapted from MetaXL User Guide: https://www.epigear.com/index_files/metaxl.html
2
Options -> Copy to Clipboard
Input data in STATA: Open STATA -> Data -> Data Editor -> Data Editor (Edit)
Adapted from MetaXL User Guide: https://www.epigear.com/index_files/metaxl.html
3
Edit - > Paste - > Variable names
Adapted from MetaXL User Guide: https://www.epigear.com/index_files/metaxl.html
4
Run analysis In Command, enter: regress t_es ib0.whole [aweight=weight], vce(robust)
Notes: • • •
“t_es” is the Transformed effect size; “whole” is the moderator variable, coded as 0 = not whole, 1 = whole; “ib0” specifies 0 as the reference; use “ib1” if 1 is the reference;
Adapted from MetaXL User Guide: https://www.epigear.com/index_files/metaxl.html
5
View results Results are presented for the comparison groups •
Compared to studies in the not whole group, studies in the whole group had significantly higher prevalence, coef = .27 (.14 to .41), p < .001
Adapted from MetaXL User Guide: https://www.epigear.com/index_files/metaxl.html
6
Subgroup analysis results We can use the meta-regression to view subgroup analysis results by the moderator variables •
•
The “_cons” result is the pooled prevalence in the reference subgroup; that is in this case, the not whole subgroup; o the pooled prevalence for the not whole subgroup is .41 (.35 to .47) If do “regress t_es ib1.whole [aweight=weight], vce(robust)”, the “_cons” result is the pooled prevalence in the whole subgroup; o the pooled prevalence for the whole subgroup is .68 (.56 to .81)
Adapted from MetaXL User Guide: https://www.epigear.com/index_files/metaxl.html
7
Analysis with more than one moderator Add moderator variables in, specifying reference groups as “ib” In the below code, the 3 moderators are • • •
whole (1 as reference) year (2 as reference age_cat (1 as reference)
Enter in Command: regress t_es ib1.whole ib2.year_cat ib1.age_cat [aweight=weight], vce(robust)
All the best! Adapted from MetaXL User Guide: https://www.epigear.com/index_files/metaxl.html