-
Notifications
You must be signed in to change notification settings - Fork 1
Home
The svyPVpack was developed while working with data from the PIAAC project. More than 20 countries participated in this large scale assessment, which examined 16-65 year old adults. These countries provided hunderts of variables from the background questionnaire as well as measurement variables of the three skill domains: Literacy, Numeracy and Problemsolving in technology rich environments. The international scaling procedure was conducted by means of Item Response Theory (IRT) methods to obtain ability measures for each person. The resulting variables, called plausible values, are not point estimates. Plausible values are random draws from the posterior distribution of each person. Therefore, for each examinee there are 10 plausible values available which depict the uncertainty of their ability estimate. The svyPVpack makes it easy to correctly estimate group statistics (e.g. the mean of the female examinees in austria) an the standard-errors (SE). It can be used in any situation where plausible values are provided (e.g. PISA etc.). To get more information about IRT, Plausible values or R see:
OECD (2013). Technical Report of the Survey of Adult Skills (PIAAC). Retrieved from: http://www.oecd.org/site/piaac/All\%20PIACC\%20Technical\%20Report\%20final.pdf
von Davier, M., Gonzalez, E., & Mislevy, R. (2009) What are plausible values and why are they useful? In M. von Davier and D. Hastedt (Eds.), IERI monograph series: Issues and methodologies in large scale assessments (vol. 2). IEA-ETS Research Institute.
Chambers, John M. (2008). Software for data analysis programming with R. Berlin: Springer. ISBN 0-387-75935-2.
After this short introduction it's time for some real data and some exciting computations with R. Therefore I suggest working through the tutorials mentioned below.
Tutorial 2