Optimal Research Design Research Articles

Practical behavioral trials to advance evidence-based behavioral medicine

There is a well-documented gap between research and practice in many areas of behavioral medicine. This gap is due in part to limitations in the capacity of the research database to address questions that are of central concern to clinicians, administrative decision makers, and policymakers. Thus, there has been a call for "practical clinical trials" that compare clinically viable alternative interventions and assess multiple outcomes important for clinical and policy decisions in diverse patient populations and settings. Such trials offer great potential, and they raise interesting challenges regarding optimal research design and source of funding. We discuss issues related to practical clinical trials in behavioral medicine, propose a need for practical behavioral trials (PBTs), and describe design features that will facilitate clinical and policy decision making. This type of PBT can help to close the gap between research and practice and advance the field of evidence-based behavioral medicine. We discuss potential challenges and objections to PBTs and conclude by providing recommendations for the design, conduct, reporting, and review of practical trials.

Comparing Experimental and Matching Methods Using a Large-Scale Voter Mobilization Experiment

In the social sciences, randomized experimentation is the optimal research design for establishing causation. However, for a number of practical reasons, researchers are sometimes unable to conduct experiments and must rely on observational data. In an effort to develop estimators that can approximate experimental results using observational data, scholars have given increasing attention to matching. In this article, we test the performance of matching by gauging the success with which matching approximates experimental results. The voter mobilization experiment presented here comprises a large number of observations (60,000 randomly assigned to the treatment group and nearly two million assigned to the control group) and a rich set of covariates. This study is analyzed in two ways. The first method, instrumental variables estimation, takes advantage of random assignment in order to produce consistent estimates. The second method, matching estimation, ignores random assignment and analyzes the data as though they were nonexperimental. Matching is found to produce biased results in this application because even a rich set of covariates is insufficient to control for preexisting differences between the treatment and control group. Matching, in fact, produces estimates that are no more accurate than those generated by ordinary least squares regression. The experimental findings show that brief paid get-out-the-vote phone calls do not increase turnout, while matching and regression show a large and significant effect.

Issues to Consider When Planning and Conducting Educational Research

This article is intended to provide students and clinicians aspiring to perform educational research with some background information pertaining to many of the issues inherent in performing research within this domain. It is not intended to provide a comprehensive review of the quantitative methods one might adopt, nor will it fully reflect all of the debate that currently exists within the educational research community. Rather, it is intended to offer an overview of issues and controversies within the field that will hopefully provide a starting point from which interested individuals can begin to engage in the study of educational effectiveness. Using investigations of the efficacy of problem-based learning as background, the article represents an attempt to guide new researchers through the process of generating and refining scientific research questions, identifying appropriate outcome measures, and selecting or adapting the optimal research design for the questions to be addressed. The article focuses on quantitative methods in general with particular attention paid to experimental designs.

Management of multiple sclerosis: current trials and future options

The present review of multiple sclerosis (MS) therapeutic trials published in 2002 is intended to assist the reader in understanding the most current advances in the care of their patients. A substantial number of pivotal and preliminary reports continue to demonstrate encouraging new evidence that advances are being made in the care of patients with MS. Several short-term studies in relapsing/remitting MS have demonstrated that it is possible to complete head-to-head comparison trials of active agents in MS (e.g. without a placebo control group). The findings of these trials remain open to interpretation and have generated considerable controversy, as expected. A phase 3 trial [the International MS Secondary Progressive Avonex Controlled Trial (IMPACT)] became the fourth study of the beta interferons (interferon-beta-1a, in this case) to demonstrate a partial effect on disease activity in secondary progressive MS. Two trials demonstrated apparent partial efficacy for the anthrecenedione mitoxantrone in active and progressive MS. Disappointing results were announced for a number of large pivotal trials, although those results have not yet been published (e.g. oral glatiramer acetate in relapsing/remitting MS, glatiramer acetate in primary progressive MS, and intravenous immunoglobulin in secondary progressive MS). The MS research community needs to determine how best to address two key unanswered questions. Is late clinical deterioration often or invariably tied to the initial inflammatory/demyelinating phase of the disease? What is the optimal research design to address whether current and future experimental strategies affect the later phases of MS (e.g. does early treatment delay or prevent clinical disability)?

Methodological, practical, and ethical challenges to inner-city health research.

Inner-city health research can be challenging because it deals with vulnerable populations and sometimes puts investigators in difficult situations. Some challenges are methodological, including selecting the optimal research design, implementing effective methods of recruitment and retention, and determining the best approach to data analysis. Other issues are practical, including addressing potential biases in social research; dealing with conflicting research agendas among investigators, community agencies, and funding agencies; and disseminating research findings effectively. Another set of issues relates to the ethical conduct of research, including ensuring privacy, maintaining confidentiality, and obtaining consent that is informed, not coerced, and not influenced by undue inducements. Throughout the research endeavor, the inner-city health researcher must carefully balance the roles of investigator, advocate, activist, and caregiver.

Treatment outcome in cleft lip and palate: issues and perspectives.

In the last 40 years, great progress has been made toward a better understanding of many aspects of the cleft lip and palate defect, but there is still a long way to go before there is agreement on the optimal treatment procedures. With regard to the primary operations, it can be stated, in a somewhat simplified form, that there are two main schools of thought in cleft treatment. One advocates early closure of the lip and palate, a procedure which imparts a high priority to early speech function. The other recommends delayed closure of the hard palate, thereby according a high priority to the growth of the maxilla. A number of intercenter and multicenter studies have been carried out recently in an effort to elucidate which procedures give the best result, both esthetically and functionally. The results are ambiguous, and this has led a number of researchers to suggest that the randomized clinical trial is the only way to resolve the ambiguity. The fact that it has proved difficult to identify the optimal procedures in the field of cleft lip and palate treatment need not only be due to a less than optimal research design; a contributory factor might also be the great variability in craniofacial morphology and in the response to treatment in patients who have exactly the same cleft lip and palate diagnosis. Intensive research has made it possible to state categorically that clefts occur due to many different factors in an interplay between genetics and environment. Therefore, it is not likely that a single gene can be responsible for clefting. Since scar tissue presents many problems-for instance, impairment of growth-the reduction or prevention of scar formation has long been a desirable goal. The discovery that a fetus can heal without scar formation has led to many animal experiments. The timing of the surgical intervention on fetuses is critical, since late-gestation fetuses heal with adult-like scarring. There are still many unsolved problems connected with fetal surgery, and at present prenatal surgery for repair of cleft lip and palate is not ethically defensible in humans. On the other hand, it appears that there are considerable possibilities for the reduction of human scarring after surgery with the introduction of various wound-healing medications.

Optimal design in psychological research.

Psychologists often do not consider the optimality of their research designs. However, increasing costs of using inefficient designs requires psychologists to adopt more efficient designs and to use more powerful analysis strategies. Common designs with many factor levels and equal allocations of observations are often inefficient for the specific questions most psychologists want to answer. Happenstance allocations determined by random sampling are usually even more inefficient and some common analysis strategies can exacerbate the inefficiency. By selecting treatment levels and allocating observations optimally, psychologists can greatly increase the efficiency and statistical power of their research designs. A few heuristic design principles can produce much more efficient designs than are often used. Experimental researchers outside psychology often carefully consider the efficiency of their research designs. For example, the high costs of conducting large-scale experiments with industrial processes has motivated the search for designs that are optimally efficient. As a consequence, a substantial literature on optimal design has developed outside psychology. In contrast, psychologists have not been as constrained by costs, so their research designs have been based on tradition and computational ease. Most psychologists are unaware of the literature on optimal research design; this topic receives little or no attention in popular textbooks on methods and statistics in psychology. Experimental design textbooks offer little if any advice on how many levels of the independent variables to use or on how to allocate observations across those levels to obtain optimal efficiency. When advice is offered, it is usually based on heuristics derived from experience rather than statistical principles. The purpose of this article is to review the basic concepts of optimal design and to illustrate how a few

Psychosocial interventions in mental health disorders

Current research into psychosocial treatment reflects different levels of quality of evidence and an increasing, but only partially met, need for well targeted and well evaluated interventions.Studies of family and psychoeducational interventions in psychotic disorders, and cognitive-behavioural therapies in depression and anxiety disorders are prominent, as are quasi-experimental studies of healthcare systems. Questions emerge over the optimal research designs to evaluate comprehensive systems of psychosocial care.

Empirical choice of sampling procedures for optimal research design in the longitudinal study of primate behavior

A method is suggested to evaluate on an empirical basis sampling plans for the longitudinal study of primate behavior in those very common situations in which the mathematical structure of behavior is unknown. The method is based on a randomization procedure applied to a pilot sample of the behavior organized so that cost of implementation of a sampling plan can be evaluated vis a vis the sampling error intrinsic to the plan.