When I started reading this thread, I thought that it was a perfect example of the kind of situation that is an ongoing sore spot for Professor Rubin and elicits a response from him. When I read his response, I was surprised to see that it wasn't exactly what I was expecting in that he addressed the specific question rather than the general issue.
After all these years of reading his general response, I must admit I've become a believer and, at the moment, am dealing with how I'll modify my own course next year. So, here's my current take on the general response. It seems particularly appropriate because the post was to sci.stat.EDU: Students need to understand about probability and random sampling and how they form the basis for statistical methods. If students were thoroughly grounded in theses areas, they would be able to work through many questions like this on their own. I am not being critical of the poster. It's a good question and the poster is doing the right thing by asking. The issue I'm trying to address is what we as educators might do to see that questions like this don't arise in the first place, once students have been introduced to statistics during their training. The poster asked, "Given the shortcomings of convenience samples, does one have to forego any type of meaningful analysis? Or, can an analysis be conducted provided an emphatic statement is included by the researcher about the shortcomings of convenience samples?" Others have spoken eloquently about the suitability of this sample. I'd like to add one comment about convenience samples and research in general, namely, "Research has consequences!" We have to be very careful with data like these. Once they are published, they will be used by scientists, planners, politicians, or even anyone with an ax to grind, for whatever goals and purposes the data might favor. The emphatic statement about the shortcomings will be lost. Some related comments from my webpage on study design: "Research is usually conducted with a view toward publication and dissemination. When results are reported, not only will they be of interest to other researchers, but it is likely that they will be noticed by the popular press, professionals who deal with the general public, and legislative bodies--in short, anyone who might use them to further his/her personal interests. "You must be aware of the possible consequences of your work. Public policy may be changed. Lines of inquiry may be pursued or abandoned. If a program evaluation is attempted without the ability to detect the type of effect the program is likely to produce, the program could become targeted for termination as a cost-savings measure when the study fails to detect an effect. If, for expediency, a treatment is evaluated in an inappropriate population, research on that treatment may improperly come to a halt or receive undeserved further funding when the results are reported. "One might seek comfort from the knowledge that the scientific method is based on replication. Faulty results will not replicate and they'll be found out. However, the first report in any area often receives special attention. If its results are incorrect because of faulty study design, many further studies will be required before the original study is adequately refuted. If the data are expensive to obtain, or if the original report satisfies a particular political agenda, replication may never take place." . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
