Rigor AND Relevance

One of the conversations at the Institute of Education Sciences (the federal research agency) in 2010 is about rigor. How do we adhere to strict rules about what is accepted as scientific evidence while making the work sponsored by the agency more relevant to educators, as the director, John Easton, wants to do?

The conflict between rigor and relevance arises for a number of reasons that we will illustrate in this entry. The basic problem arises when rigor is defined in terms of specific methodologies such as randomized experiments or a specific criterion such as a 95% confidence interval. Defining rigor by such procedural rules restricts the body of evidence to a small number of studies and to a narrow range of questions that can be answered with the methods that would be considered acceptable. Our position is not that the education sciences have to become less rigorous in order to become more relevant. Instead, our position is that the concept of scientific rigor is being misunderstood.

Rigor, in ordinary English, is used to suggest rigidly following rules and procedures. However, because blind adherence to procedures is inappropriate in any area of science, the usage within the education sciences needs clarification and realignment. Our suggestion to IES is to focus on the underlying scientific principles rather than the procedures and criteria derived from the principles. Here are some examples.

The standard rules of research assume that a positive outcome identified in a study is very unlikely to be an artifact of a particular sample. There is a very important principle behind this that must be rigorously understood by researchers. And the appropriate statistical calculations must be applied. The rigor, however, is in understanding the trade-off between mistaking a false positive result for a real result or erroneously rejecting a positive effect of a new program as statistically insignificant when, in fact, there is a real difference. Scientific practice favors protecting against the first kind of mistake and conventionally sets the bar high. But changing the trade-off to favor avoiding the mistake of considering a program ineffective when it is really effective would not constitute less rigor. Faced with a very serious problem, a policy maker may prefer the risk of spending money on something that might not work rather than rejecting a promising program that narrowly missed the conventional threshold for statistical significance.

Randomization provides another example. The fundamental principle that has to be understood is how results of quantitative studies can be biased by confounding and how controlling for the effects of confounders produces a more accurate estimate of the treatment effect. While randomizing units (e.g., teachers, grade-level teams, schools) into treatment and control groups is recognized as the gold standard for controlling for the effects of potential confounding variables so as to isolate the impact of treatment, rigor is not accomplished by restricting education science to randomized experiments. A relevant study can often benefit from the use of observational data stored in school district information systems. Rigor would then consist of understanding how other designs and statistical controls can be appropriately applied to reduce potential bias (and when statistics can’t fix a bad design). There is nothing rigorous in discarding a dataset outright because it has not been created in a fully controlled experimental setting or because it is not free of measurement error.

While controlling selection bias through experimental designs and statistical adjustments must be understood by education scientists, it is also essential to attend to the context of the study and the range of its generalizability—what we can usefully conclude from the research. The experiment itself may have interfered with usual processes (a situation called ecological invalidity) such as when teacher-level randomization breaks up the existing team teaching within a grade-level team. We need a record of differences in program implementation that shows the relationship between quality of implementation and student performance and also prevents us from mistaking attributes of better-implementing teachers for attributes of the program. While the world of schools can be a messy place to conduct research, taking implementation issues seriously in the study design does not equal less rigor.

Ultimately, it comes down to knowing what we can say to the stakeholders, whether they are educators, publishers, or government agencies. What can be said derives from rigorous application of research principles and, to some extent, calls upon the art of careful audience-sensitive communication. It is not more rigorous to leave out the results of post-hoc explorations. Rigor in education science includes framing the results with appropriate cautions about preliminary findings, limitations on generalization, and results that are interesting and warrant continued tracking or more targeted investigations. Making progress in education science calls for rigor, and rigor includes clear communication and the participation of stakeholders in interpreting results.

Focusing Evaluations on Achievement Gaps

The standard design for experimental program evaluations in educational settings may not be doing justice to the questions that matter most to district decision makers. In many sites where we have worked, the most important question had to do with a gap between two populations within the district. For example, one district’s improvement plan specifically targeted the gap in science achievement between black students and white students. In another, there was a specific concern with the performance of new, and often uncertified, teachers compared to experienced teachers. NCLB, with its requirement for disaggregating the performance of specific subgroups, has reinforced this perspective. A new science curriculum that has a modest positive impact on performance across the district could be rejected if it had the effect of increasing the gap between the two populations of concern.

When a new program favors one kind of student or teacher over another, we call it an interaction, that is, an interaction between the experimental “treatment” and some pre-existing “trait” of the population involved. In experimental design, we call these characteristics of the people or the setting moderators because they are seen as moderating the impact of the new program. Moderators are often considered secondary or even exploratory outcomes in experimental program evaluations, which are designed primarily to find out whether the new program makes an overall difference for the study population as a whole. Who gets and doesn’t get the program can be manipulated experimentally. By contrast, the moderator is a pre-existing characteristic that (usually) can’t be manipulated. While the experiment focuses on a specific program (treatment), any number of moderators can be examined after the fact.

Many of our experiments in school systems are aimed at answering a question of local interest. In this case, we often find that the most important question concerns an interaction rather than the average impact of the experimental intervention itself. The potential moderator of interest, such as minority status, under-achievement, or certification can be specified in advance, based on the identified gap in performance the new program was intended to address in the first place. When the interaction is the primary outcome of interest, its status goes beyond even the emphasis that many experts put on interactions as a means for getting a fuller picture of the effectiveness of an intervention (Cook, 2002; Shadish, Cook, & Campbell, 2002). But because investigations of interactions are usually exploratory and not the primary question (except perhaps for the specific setting in which the experiment took place), it is difficult to look across studies of the same intervention to come to any generalization about the moderating effects of certain variables. Research reviews that synthesize multiple studies of the same intervention such as found on the What Works Clearinghouse and Best Evidence Encyclopedia are not concerned with interactions, even if an individual study finds one to be quite substantial. This is unfortunate because, in many studies that find no overall impact for a program, we may discover that it is differentially effective for an important subgroup. It would therefore be useful, for example, to examine whether the moderating effect of a certain variable varies more than is expected by chance across experimental settings. This would indicate whether the moderating effect is robust or whether it depends on local circumstances.

This situation points to the importance of conducting local program evaluations that can focus on the achievement gap of greatest concern. Fortunately, recent theoretical work by Howard Bloom (Bloom, 2005) of MDRC provides an indication that statistical power for detecting differences among subgroups of students in the impact of an intervention (that is, the interaction) can be larger than for detecting a net impact of the same size for that program. This means that a local experiment primarily interested in an interaction can be smaller, and less expensive, than a traditional experiment looking for an overall average effect. The need for information about gaps, as well as the possible greater efficiency of studying gaps, provides support for a strategy of conducting relatively small experiments to answer questions of local interest to a school district (Newman, 2008). Small, and less expensive, experimental program evaluations focused on moderating effects can provide more valuable information to decision makers than large-scale experiments intended for broad generalization, which cannot provide useful evidence for all interactions of interest to schools.

Empirical Education is now engaged in research to empirically verify Bloom’s observation about statistical power; we expect to be reporting the results next spring. —DN

Bloom, H. S. (2005). Randomizing groups to evaluate place-based programs. In H. S. Bloom (Ed)., Learning More From Social Experiments. New York, NY: Sage.

Cook, T. D. (2002). Randomized experiments in educational policy research: A critical examination of the reasons the education evaluation community has offered for not doing them, Educational Evaluation and Policy Analysis, 24, 175-199.

Newman, D. (2008) Toward School Districts Conducting Their Own Rigorous Program Evaluations: Final Report on the “Low Cost Experiments to Support Local School District Decisions” Project. Empirical Education Research Reports, Palo Alto, CA: Empirical Education Inc.

Shadish, W. R., Cook, T. D., & Campbell, D. T. (2002). Experimental and quasi- experimental designs for generalized causal inference. Boston: Houghton Mifflin.