• influence.ME now supports new lme4 1.0

    influence.ME is an R package for detecting influential data in multilevel regression models (or, mixed effects models as they are referred to in the R community). The application of multilevel models has become common practice, but the development of diagnostic tools has lagged behind. Hence, we developed influence.ME, which calculates standardized measures of influential data… Continue Reading

  • Influence.ME: Tools for Detecting Influential Data in Multilevel Regression Models

    Despite the increasing popularity of multilevel regression models, the development of diagnostic tools lagged behind. Typically, in the social sciences multilevel regression models are used to account for the nesting structure of the data, such as students in classes, migrants from origin-countries, and individuals in countries. The strength of multilevel models lies in analyzing data… Continue Reading

  • Applied R: Manual for the quantitative social scientist

    Applied R for the quantitative social scientist is a manual on R written specifically as an introduction for the quantitative social scientist. To my opinion, R-Project is a magnificent statistical program, ready to be accepted and implemented in the social sciences. The flexibility of this program and the way data are handled gives the user a sense of closeness to and control over the data. I think this inspires users to analyze their data more creatively and sometimes in a more advanced way.

  • Index of the R-Sessions

    The R-Sessions are a series of blog entries on using R. A large part consists of an R-manual I once wrote. Other posts include some tricks I found out, as well as entries detailing functions and packages I wrote for R. The series already entails over forty posts, so I decided to create an index.… Continue Reading

  • R-Sessions 30: Visualizing missing values

    It always takes some time to get a grip on a new dataset, especially large ones. The code-books are often as indispensable as they are massive, and not always as clear as one would want. Routings, and resulting and strange patterns of missing values are at times difficult to find.

    I found a nice way to plot missing values, using R. Basically, I thought it would be nice to calculate the percentage of missings on each variable, and do so for each year represented in the data. These numbers could be visualized using a levelplot(), which resulted in the graph below.

  • R-Sessions 29: Running R-Project twice on Apple Mac OS X

    Working with statistics can be quite time consuming. As anyone working with relatively advanced models and large amounts of data knows, especially the waiting can be excruciating. Your statistical software is locked up while crunching those numbers, while you’d actually prefer to run some minor procedures, such as post-estimations, testing some loops, or simply displaying the output of a previously estimated model. With Apple’s Mac OS X you now can run R-Project twice, making the most of your dual core processor.

  • R-Sessions 28: Impressive R Speeds

    Yesterday, I received my new Apple MacBook. It’s running a Core 2 Duo at 2.4 Ghz and it’s fast. Really fast! I tested it with using R-Project, doing some timings on matrix transformations.

    Apparently, it’s very cool to show of the speed of R-Project on your system. Optimized .DLL files help to speed up your R on Windows systems (and possibly other systems as well) with respect to matrix transformations, which has led to enormous speed increases. So, let’s perform a speed-test of our own.