مؤتمر
Comparison of Methods of Data Analysis in Nonrandomized Experiments.
العنوان: | Comparison of Methods of Data Analysis in Nonrandomized Experiments. |
---|---|
اللغة: | English |
المؤلفون: | Blumberg, Carol Joyce |
Peer Reviewed: | N |
Page Count: | 31 |
تاريخ النشر: | 1983 |
نوع الوثيقة: | Speeches/Meeting Papers Reports - Research |
Descriptors: | Comparative Analysis, Control Groups, Data Analysis, Data Collection, Evaluation Methods, Mathematical Models, Research Design, Research Methodology, Simulation |
مستخلص: | Various methods have been suggested for the analysis of data collected in research settings where random assignment of subjects to groups has not occurred. For the purposes of this paper the set of allowable nonrandomized designs is made up of those research designs where data are collected for one or more groups of subjects at two or more time points on some measure of interest. Further, none of the groups need be a control group. The main purpose of the paper is to describe and report the results of a Monte Carlo simulation study that was carried out to determine which of several data analysis methods developed by either Blumberg and Porter or Olejnik yields the best point estimates of treatment effects under various constraints. When growth on the measure of interest is linear over time, Blumberg and Porter's methods provide the best estimates. When growth is exponential over time, the results are mixed: under some constraints Olejnik's method is best, but usually Blumberg and Porter's methods provide the best estimates. (Author) |
Entry Date: | 1983 |
رقم الأكسشن: | ED228316 |
قاعدة البيانات: | ERIC |
الوصف غير متاح. |