Efficiency in Education

Educators often feel ambivalent about the pursuit of efficiency in education. On the one hand, there is a basic belief that efficiency is a good and worthy goal; on the other hand, there is sense of worry that efforts to improve efficiency will ultimately undermine what lies at the heart of high-quality education. Part of the difficulty stems from a misunderstanding about the meaning of efficiency as well as from the legacy of past, sometimes misguided, efforts to improve the efficiency of educational systems. It is therefore useful to begin with a basic discussion of the efficiency concept.

The notion of efficiency applies to a remarkably large number of fields, including education. It is a disarmingly simple idea that presupposes a transformation of some kind. One can think in terms of what was in hand before the transformation, what was in hand after the transformation, and one can also think about the transformation process itself. The before elements are commonly referred to as ingredients, inputs, or resources while the after elements are called results, outputs, or outcomes. The transformation process is sometimes less obvious and can become confused with ingredients. For example, in an educational setting, a teacher can be thought of as an ingredient while teaching is an important part of the actual transformation process.

The concept of efficiency is often connected to a moral imperative to obtain more desired results from fewer resources. Efficiency needs to be thought of as a matter of degree. Efficiency is not a "yes/no" kind of phenomenon. It is instead better thought of in relative or comparative terms. One operation may be more efficient than another. This said, the more efficient of the two operations could become even more efficient. The quest for greater efficiency is never over, and this sense of a perennially unfinished agenda is one source of the generalized sense of anxiety that tends to surround the efficiency concept.

The Choice of Outcomes

If the goal is to obtain more desired results from fewer resources, then it is important to be clear about what is being sought. Society might have a very efficient system because a large amount of outcome is being obtained relative to the resources being spent or invested, but if the outcomes are out of sync with what is truly desired, there is a real sense in which the system is not very efficient. Of course, this invites important questions about who gets to decide what counts as a desirable outcome, and in education there are longstanding and ongoing debates over what the educational system ought to be accomplishing.

In the United States, education is viewed as a responsibility of the individual states rather than the national government, and the states have made efforts to define the outcomes they seek from their educational systems. These efforts have come to be known as standards-driven initiatives, where the standards constitute pronouncements from the states about the collective expectations for what the schools need to accomplish. The idea has been for each state to articulate the desired outcomes and then provide flexibility to the districts, schools, administrators, teachers, and students to meet the standards in ways that make the most sense given local circumstances.

States have handled this in different ways and there are interesting deeper questions about how to balance state judgments with judgments that are made at more localized levels. How, for example, should a disagreement between a duly constituted local school board and the state be settled? Going further, how should the views of local boards be considered as the state sets its standards? What is the proper role for minority views? And how should revisions be handled as time passes?

It is customary to think of the state's setting minimum standards that can be exceeded by individual localities if a locality resolves to do so and can muster the necessary resources. This thinking presupposes a hierarchical view of educational outcomes in the sense that outcome "C" builds upon outcome "B" while outcome "B" builds upon outcome "A." A problem is that outcomes may not always have this kind of hierarchical nature. Suppose a school wants to provide a high degree of personalized attention as part of its program. Is this an input or an outcome? Let us suppose that this is a costly thing to do. The school that pursues this strategy is going to consume more ingredients and if only the standard outcomes are looked at, this school is going to look like costs are high relative to the outcomes that are realized. Hence, the school could look inefficient for the simple reason that it has chosen to pursue a different set of educational goals. There is also the possibility that a locally selected goal can interfere with or undermine one of the state selected goals.

In addition to reaching agreement about the mix of outcomes to pursue, there are important measurement issues to consider. An interest in efficiency is frequently accompanied by an interest in measuring magnitudes. If one is seeking more out of less, one frequently wants to know "how much more," and the result has been a boom in the efforts by educational psychologists and others to develop valid and reliable measures of the learning gains of students. Critics of efficiency analysis in education worry that ease of measurement can unduly influence the selection of the outcomes that the system will be structured to achieve. In other words, the worry is that the drive for efficiency will lead, perhaps inadvertently, toward the use of educational outcomes that are chosen more because they are easy to measure than because of their intrinsic long-term value for either individual students or the larger society. Standardized tests of various kinds have been relied upon as measures of the outcomes of schooling and have been criticized on these grounds.

Sometimes there is interest in the economic consequences of schooling, and this interest has prompted analysts to use earnings as a measure of schooling outcomes. A rich literature has developed in the economics of education where efforts have been made to estimate the economic rate of return to different levels and types of schooling. This is a challenging area of research because earnings are influenced by many factors and it is difficult to isolate the effects of schooling. The goal of this research is to capture the value added by schooling activities.

The relevance of the value-added concept is not limited to economists' studies of rates of return. Even in cases where the focus is on learning outcomes as measured by tests or other psychometric instruments, there are questions to answer about the effects of schooling activities relative to the effects of other potentially quite significant influences on gains in students' capabilities. Serious studies of the efficiency of educational systems measure educational outcomes in value-added terms.

Measurement issues also arise from the collective nature of schooling. The results gained from schooling experiences are likely to vary among individual students and this prompts questions about how best to examine the result for the group in contrast to an individual student. Is one primarily interested in, say, the average performance level, or is there a parallel and perhaps even more important concern with what is happening to the level of variation that exists across all of the students within the unit, be it a classroom, grade level within a school, a school, a district, a state, or a nation? The early research on educational efficiency in the 1960s placed a heavy emphasis on average test score results for relatively large units like school districts. More recent work demonstrates greater interest in measures of inequality among students. The standards-driven reform movement includes a considerable amount of rhetoric about all students reaching high standards; the analysis of efficiency presupposes an ability to move beyond the easy rhetoric to make clear decisions about how uniform performance expectations are for students.

In addition, there is an important distinction to maintain between the level at which a system operates and the rate at which inputs are being transformed into outcomes. One can "get the outputs right" so that the desired items are being taught/learned in the correct proportion to one another. In such a case, gains in the understanding of mathematics are occurring in the correct proportion to, say, gains in language capabilities. But this says nothing about the absolute level at which the system is operating. The naive view might be that the system should operate at 100 percent of its capacity, but this overlooks the fact that scarce resources are needed to operate at this level and that education is not the only worthy use of these precious resources. Policy-makers must make often difficult trade-off decisions about the level at which the educational system will operate relative to the level of other competing social services. The early twenty-first century is witnessing a considerable amount of debate over the proper level at which to set the educational system, often as part of an effort to define what counts as an "adequate" education.

With respect to outcomes, the goal is to reach agreement about (1) the relative mix of performance outcomes to realize; (2) the degree of uniformity of performance across students; and (3) the level of capacity at which the system should operate. In addition, there needs to be an ability to measure what is being accomplished.

The Choice of Inputs

The outcomes that are selected drive the entire system. Input issues, in contrast, are more straightforward and almost mechanical in nature. Once what is to be accomplished is known, at what level, and for whom, society can then turn to the challenge of doing so in as economical a way that is possible. In other words the goal is to accomplish the desired results for as little cost as possible, and this involves making the best possible use of whatever ingredients or resources that are available.

Although this seems straightforward, there are a number of complexities that need to be considered. First, there is the dynamic nature of the process. As time passes, more is learned about how to make better and better use of the available resources and new resources may also become available. A good example of a new resource lies in the area of telecommunication and computing technology. These advances have great potential to affect the day-to-day life of educational practice. It is also important to keep in mind that the nature of how technology develops is not external to the system. Technology does not develop in a vacuum. Instead, there are sometimes powerful forces that shape the nature of how technology develops. For example, many existing instructional computing technologies are designed to supplement rather than to supplant existing classroom activities. This tendency for computing to be treated as the handmaiden of the traditional classroom structure may not be in the best long-term interest of the larger society.

Second, there is the technical versus cost dimension to consider. A particular resource or input might be highly productive in the sense that a small amount could make a significant difference, but this same highly productive resource might be extraordinarily costly. For example, suppose having one hour per week of a Nobel prize winning physicist's time turns out to be an extraordinarily productive input for high school students who are learning physics. Suppose further that such a resource is quite costly. In contrast, an hour per week of a local Ph.D. in physics might be less costly but let us also say that it is less productive. From an efficiency perspective, the question is: How do the ratios of benefit relative to cost compare? It is quite conceivable that the benefit/cost ratio for the Nobel prize winner is smaller than the comparable ratio for the local Ph.D., even though the absolute measure of the Nobel prize winner's effectiveness (i.e., the result per unit of input) is higher.

Third, in addition to making sense of benefits relative to costs, there is also the challenge of making the best possible use of whatever resource is being employed. For example, just because a Nobel prize winner has the potential to be a very productive input does not preclude the possibility of that resource being squandered in a particular setting, and the same can be said of the local Ph.D. in physics, or an artist who is hired to spend some time in a school. The quest for greater efficiency requires the parties to make the best possible use of whatever resources come into their possession.

Finally, there is the potential for the costs of inputs to influence the selection of outcomes. Some outcomes are more costly to produce than others. For example, a student who finds it difficult to learn will, by definition, be relatively costly to educate, and these extra costs could influence decisions that are made about how uniform to make the learning outcome standards. And thus, the distinction between outcomes and inputs begins to break down.

The Transformation Process and Implications for Policy

Policymakers are very interested in assessing the degree of efficiency in educational systems. One difficulty arises when indicators are used that fail to provide accurate information. For example, a widely available statistic is the level of spending on education expressed on a per pupil basis. At first glance, this looks like an efficiency indicator since it provides insight into the commitment of resources (the expenditure figure) and the result (the number of students being served by the system). Critics note that this statistic has been rising over time and conclude that the system is becoming less efficient. There are many reasons to be wary of using an expenditure per pupil statistic and its changes over time to reach such a conclusion. Even with a control for the effects of inflation, there remains a fundamental problem on the outcome side of the analysis since there is no direct measure of what the schools are accomplishing and how this might have changed over the period.

Even if accurate, noncontroversial measures of efficiency and its changes over time can be obtained, it is difficult to obtain clear insight into what policies should be developed to ensure gains in efficiency without undermining other key social goals like fairness and freedom of choice. Much of the challenge here depends on the fundamental nature of the transformation process that is presupposed as part of the efficiency concept. The efficiency concept derives from the field of economics where it was initially applied to industrial production processes such as the manufacture of automobiles. These industrial manufacturing processes involve the combination of numerous nonhuman ingredients such as lengths of steel, aluminum, glass, chrome, and so forth. These ingredients are transformed thanks to various physical and chemical processes whose scientific properties are relatively well understood, making the results quite predictable.

For a manager whose goal is to improve efficiency, this kind of information is invaluable. With this information the manager can compare higher performing units with lower performing units and make a diagnosis about the source of the inefficiency in the underperforming units. There may be problems with a unit's ability to get the most out of the inputs it is using; there may be a less than optimal mix of inputs being used; and/or the mix of outputs being produced may be misaligned. The "efficiency expert" in such a situation is able to pinpoint the source of the difficulty and can prescribe steps for improvements.

In contrast, the educational process is heavily committed to the use of human resources and the various inputs are brought together and transformed in ways that are sometimes difficult to predict. Without denying the significance of the human dimension within industrial manufacturing processes, it stands to reason that the production or transformation process that lies at the center of educational systems is fundamentally more complex and less well-understood than production in the industrial sector. A better comparison comes from studies of efficiency in crop production in the field of agricultural economics. But even here, the production process for growing a particular plant is better understood than is the process through which human minds mature and acquire knowledge and understanding. Indeed, it is possible to question whether the educational process really lends itself to the input-output, mechanical formulation that lies at the heart of the efficiency concept. According to this view, educational growth is inherently unpredictable, and the teacher is better thought of as a creative artist than as a productive input whose impact can be measured and predicted in a rigorous and scientific way.

While it is clear that knowledge of the technical properties of the educational process is more limited than what exists, say, in the area of automobile manufacturing, it does not follow that the educational process is inherently unknowable in this sense. In other words, the lack of progress to date in coming to grips with the technical properties of the education transformation process does not mean the process is inherently unpredictable and unmanageable. A more prudent conclusion is that care needs to be exercised in efforts to assess the efficiency of educational systems. It also follows that care needs to be exercised in the use of the efficiency assessment data that are gathered.

Consider the following example of how the results of an efficiency analysis in education can be misapplied. Suppose an analysis goes forward that suggests that a particular school or school district is less efficient than most others. Suppose the response is to penalize the less efficient unit by reducing the flow of state or federal resources. A byproduct of such a policy is a reduction in the funding of the education being provided to students who through no fault of their own find themselves located within an inefficient educational system. Those who work to improve the efficiency of educational systems must guard against this potential to "blame the ultimate victim" of the situation. Similarly, the use of incentives to encourage greater efficiency runs the risk of rewarding those who are already enjoying considerable success. If the problem lies with the unknown nature of the production process, it is perverse to be implicitly penalizing the underperforming districts because they do not have knowledge that is lacking elsewhere. Penalizing underperformers makes sense only if the knowledge is available and the penalties are meant to provide greater incentive to find it. States sometimes handle this by providing technical assistance but technical assistance really works only when it is based on bona fide knowledge, something which is not always possible, given the continued limited understanding of the properties of educational production under a wide range of circumstances.

At this stage of development in efforts to apply the efficiency concept to the field of education several conclusions can be reached.

1. It is important to make sure that the comparative information suggesting that one educational unit is more or less efficient than another is accurate.
2. This accurate comparative information needs to be used as a set of guidelines/suggestions and needs to stop short of becoming overly rigid and prescriptive.
3. Efforts need to be made to monitor very carefully the results of attempts to improve the efficiency of educational systems that are perceived to be below expectations.
4. Additional research efforts need to be made to better understand the technical properties of the transformation process that gives rise to desired educational results.

The results of this continuing research will be instrumental in future efforts to make further efficiency improvements in education and can go far toward reducing the ambivalence that historically has characterized educators' reaction to the efficiency concept and its application to the field of education.