What is the most useful Stata command that "nobody" uses? A particular favorite of mine is "plotbeta" written by Adrian Mander, a public health researcher at the University of Cambridge in the UK. His program enables you to plot regression coefficients graphically in one simple, easy-to-use command. Too often social scientists (especially economists) present results in tables when they could be displaying their results in pie charts, bars charts, and scatterplots. The end result is that we create tables that are difficult to interpret, obscure patterns in the data, and foster an undue obsession on focusing on only those coefficients with an adequate number of "stars" next to them! Graphs are undoubtedly superior to tables in several respects: first, they present results in a way are easier everyone, including people who do not read academic journal articles, to interpret and understand; second, they encourage the researcher to examine patterns in the data that might otherwise be missed (for example, increasing returns to education on income); and finally, they help shift focus away from evaluating coefficients on whether or not they are statistically "significant" (an inherently arbitrary cutoff) and toward whether or not coefficients are large or small, positive or negative, and accompanied with a confidence interval that is wide, narrow, or in-between. Kudos to Adrian Mander for creating "plotbeta," the most useful Stata .ado file that "nobody" uses. Let's hope more people take advantage of it.
- R in the NYT
- Top Ten Must-Have R Packages for Social Scientists...
- Multilevel and Longitudinal Modeling in Stata
- Sociology = Hedge Fund?
- A Quantitative Tour of the Social Sciences
- Creating Summated Scales
- Simpson's Paradox Strikes Again
- The Relative Size of Things
- Multiple Imputation with Deletion
- The Paradox of Choice
- Abandoned Sociology
- LaTeX or MS Word?
- Why You Have No Friends
- The Language of Economists
- A Neat Mathematical Trick
- Do Social Networks Affect Health?
- Economists > Political Scientists > Sociologists?
- An Extraordinarily Useful Command
- ▼ December (18)