BMJ Basic Concepts for Reading Health Articles

Basic Concepts for Reading Health Articles by BMJ

• How to read a paper
• Epidemiology for the uninitiated
• Academic medicine
• Statistics at square one
• Photographs of twentieth century doctors

Tips - Stata: How to do a trend analysis using Stata

• -nptrend- performs the nonparametric test for trend across ordered groups.

    .nptrend exposure, by(grp)
    also see How can I test for a trend across a categorical variable?

• -vwls- estimates a linear regression using variance-weighted least squares.

    .vwls prev year,sd(se_prev)

• Does Stata provide a test for trend?

• Usually, after an analysis like regression you can test trend, I use -contrast- and orthogonal polynomial coefficient contrast to examine the linear or higher order trend.
• I also use other software like Joinpoint Regression Program, a handy tool by NCI, for trend analysis.

Where can we find the citation number of our published article?

Where can we find the citation count of our published articles?

Usually I use Web of Knowledge by Thomson Reuters Science:

• Go to the Web of Knowledge.
• Click on the tab of Web of Science.
• Click on the sub-tab of Advance Search.
• Use your name and some restrictions (e.g. AU=(Cheng, YJ) AND OG=(XYZ))
• Double-check and exclude the articles not published by yourself.
• Click the Create Citation Report on the up-right corner of the first article (if you still cannot find it, press Ctrl-F, and type create citation on that webpage).
• Click and you get and play around the report.

There are also free citation count search engines:

• Google Scholar
• Google Scholar Universal Gadget enables users to search for the total number of citations of author(s). It provides a total citation count, total number of cited publications and Jorge E. Hirsch's H-Index.
• Microsoft Academic Search

Related articles: 

• A plot of my citations in Google Scholar vs. Web of Science using R! is a blog compared the citation search capability of Google Scholar and Web of Knowledge.

Sex-Specific Reporting of Scientific Research A Workshop Sum...

Sex-Specific Reporting of Scientific Research: A Workshop Summary

Editors

Institute of Medicine (US) Board on Population Health and Public Health Practice.

Source

Washington (DC): National Academies Press (US); 2012.
The National Academies Collection: Reports funded by National Institutes of Health.

Excerpt

On August 30, 2011, the Institute of Medicine hosted a workshop, Sex-Specific Reporting of Scientific Research, sponsored by the Office of Research on Women's Health (ORWH) of the National Institutes of Health (NIH). The workshop explored the need for sex-specific reporting of scientific results; potential barriers and unintended consequences of sex-specific reporting of scientific results; experiences of journals that have implemented sex-specific requirements, including the challenges and benefits of such editorial policies; and steps to facilitate the reporting of sex-specific results. Presenters and participants included current and former editors of scientific journals, researchers, and scientists and policymakers from government, industry, and nonprofit organizations. Presentations and discussions highlighted the importance to both women and men of having sex-specific data, the problems with sample size and financial constraints for conducting the research, the appropriateness of sex-specific analyses, and the limitations of journal policies to change experimental designs. During closing remarks, the planning committee chair summarized some of the individual suggestions discussed for advancing sex-specific reporting as: identifying the sex of populations in journal populations, sharing of sex-identified raw data, giving extra credit in review to manuscripts that include sex-specific information, and requiring sex-stratified analyses where applicable.
Copyright © 2012, National Academy of Sciences.

Sections

• THE NATIONAL ACADEMIES
• PLANNING COMMITTEE ON SEX-SPECIFIC REPORTING OF SCIENTIFIC RESEARCH: A WORKSHOP
• Reviewers
• OVERVIEW
• INTRODUCTION
• INCLUSION OF WOMEN IN CLINICAL TRIALS FUNDED BY THE NATIONAL INSTITUTES OF HEALTH
• WHY SEX-SPECIFIC REPORTING IS IMPORTANT
• THE RESEARCHER PERSPECTIVE: COLLECTING, ANALYZING, AND REPORTING SEX-SPECIFIC DATA
• THE EDITOR PERSPECTIVE: IMPLEMENTING JOURNAL EDITORIAL POLICIES
• IMPLICATIONS FOR JOURNALS OF SEX-SPECIFIC REPORTING POLICIES OF JOURNALS
• LOOKING FORWARD
• CLOSING REMARKS
• REFERENCES
• APPENDIXES

PMID:22379657[PubMed]

Books & DocumentsFree full text

Sex-Specific Reporting of Scientific Research: A Workshop SummaryFree full text

Tips - Stata: How to get rate

Tips – Stata: How to get rates by multiple variables for complex sampling designed data (-svy-)

If one wants to get the rates of variable 'dmb20' (0, 1) among adults with 'DM' by 'survey' and 'age3grp', he/she can use different ways to get them, three basic approaches are listed below:  

1. Use –subpop-

.svy, subpop(if DM==1 & age3grp==1): tab survey dmb20, obs row percent ci format(%5.1f)

.svy, subpop(if DM==1 & age3grp==2): tab survey dmb20, obs row percent ci format(%5.1f)

.svy, subpop(if DM==1 & age3grp==3): tab survey dmb20, obs row percent ci format(%5.1f)

2. Use –proportion-

.svy, subpop(if DM==1): proportion dmb20, over(survey age3grp)

3. Use –ratio-

.svy, subpop(if DM==1): ratio (dmb20/DM), over(survey age3grp)

NOTES: The better part of -svy: tab- is using a logit transform to produce confidence intervals of estimates, which makes the confidence interval always between 0 and 1.

However, the one advantage of using 2 & 3 is you can use post estimation commands, such as -testnl- or -nlcom-, flexibly.

we also can use -svy: total- to get the total numbers like use -count- of -svy: tab-, and followed by the post estimation commands.

Difference Between Factor Analysis & Principal Component Analysis | eHow.com

Difference Between Factor Analysis & Principal Component Analysis | eHow.com


Definition of Variables
Confirmatory Variables
Latent Variables
Variance

Tips - Stata: Building complicated expressions the easy way

Tips - Stata: Building complicated expressions the easy way


Step-by-step:

• run a command of analysis
• .db display
• click 'Create...'
• use 'expression builder' to create the complicated formula. It will help to use correct expressions
• click 'ok' and 'submit'.
• then, copy and paste the formula to a 'do' or 'ado' file for further use.

You can find a more detailed article here

Objective measurement of physical activity: best practices and future directions

Objective Measurement of Physical Activity:  Best Practices and Future Directions

source: Medicine & Science in Sports & Exercise


This journal supplement summarizes and builds upon a workshop which convened researchers from diverse sectors and organizations to critically review the state-of-the-science.


The supplement discusses current technologies for objective physical activity monitoring, provides recommendations for the use of these technologies, and explores future directions in the development of new tools and approaches. It presents best practices for using physical activity monitors in population-based research, explores modeling of physical activity outcomes from wearable monitors, and discusses statistical considerations in the analysis of accelerometry-based activity monitor data. It also examines monitor equivalency issues and discusses current use and best practices for accelerometry with particular populations—children, older adults, and adults with functional limitations. 


Open-access, full-text of all articles is available at here.

Tips - Stata: function and extended function to -generate- and -egen-

Tips - Stata: function vs. extended function & -generate- vs. -egen-


Stata provids two kinds of functions: regular functions and extended functions (or called egen function). These functions need to be used with other Stata commands, usually -generate- and -egen-. -generate- is for regular function, or -egen- for egen function and only -egen- may be used to run egen function. some function may look similar but different:

• sum(var) and total(var) (a -egen- function)
• Sum() is a regular function. When you use .gen sum1=sum(var), it will generate a new variable named 'sum1' with cumulative summation of 'var' from top to bottom in order of group.
• However, total() as a egen function used in .egen sum2=total(var), it will generate a new variable named 'sum2' with summation of 'var' of all observation from top to bottom in that group. All the cases in that group have the same values of 'sum2'.
• recode(var,cutpt1,cutpt2,cutpt3,...) and group(varlist) (a -egen- function)