Research Design

The acute respiratory distress syndrome (ARDS) continues as a contributor to the morbidity and mortality of patients in intensive care units throughout the world, imparting tremendous human and financial costs. During the last 10 years there has been a decline in ARDS mortality without a clear explanation. The American-European Consensus Committee on ARDS was formed to re-evaluate the standards for the ICU care of patients with acute lung injury (ALI), with regard to ventilatory strategies, the more promising pharmacologic agents, and the definition and quantification of pathologic features of ALI that require resolution. It was felt that the definition of strategies for the clinical design and coordination of studies between centers and continents was becoming increasingly important to facilitate the study of various new therapies for ARDS. Artlgas

The growing interest in Structured Equation Modeling (SEM) techniques and recognition of their importance in IS research suggests the need to compare and contrast different types of SEM techniques so that research designs can be appropriately selected. After assessing the extent to which these techniques are currently being used in IS research, the article presents a running example which analyzes the same dataset via three very different statistical techniques. It then compares two classes of SEM: covariance-based SEM and partial-least-squaresbased SEM. Finally, the article discusses linear regression models and offers guidelines as to when SEM techniques and when regression techniques should be used. The article concludes with heuristics and rule of thumb thresholds to guide practice, and a discussion of the extent to which practice is in accord with these guidelines. Note: The paper is written in such a way that readers with basic knowledge of multivariate statistics can follow the logic and examples. It does not assume the reader is already conversant with LISREL, PLS, or other SEM tools. This tutorial contains:

The primary rationale for the use of phylogenetically based statistical methods is that phylogenetic signal, the tendency for related species to resemble each other, is ubiquitous. Whether this assertion is true for a given trait in a given lineage is an empirical question, but general tools for detecting and quantifying phylogenetic signal are inadequately developed. We present new methods for continuous-valued characters that can be implemented with either phylogenetically independent contrasts or generalized least-squares models. First, a simple randomization procedure allows one to test the null hypothesis of no pattern of similarity among relatives. The test demonstrates correct Type I error rate at a nominal ␣ ϭ 0.05 and good power (0.8) for simulated datasets with 20 or more species. Second, we derive a descriptive statistic, K, which allows valid comparisons of the amount of phylogenetic signal across traits and trees. Third, we provide two biologically motivated branch-length transformations, one based on the Ornstein-Uhlenbeck (OU) model of stabilizing selection, the other based on a new model in which character evolution can accelerate or decelerate (ACDC) in rate (e.g., as may occur during or after an adaptive radiation). Maximum likelihood estimation of the OU (d) and ACDC (g) parameters can serve as tests for phylogenetic signal because an estimate of d or g near zero implies that a phylogeny with little hierarchical structure (a star) offers a good fit to the data. Transformations that improve the fit of a tree to comparative data will increase power to detect phylogenetic signal and may also be preferable for further comparative analyses, such as of correlated character evolution. Application of the methods to data from the literature revealed that, for trees with 20 or more species, 92% of traits exhibited significant phylogenetic signal (randomization test), including behavioral and ecological ones that are thought to be relatively evolutionarily malleable (e.g., highly adaptive) and/or subject to relatively strong environmental (nongenetic) effects or high levels of measurement error. Irrespective of sample size, most traits (but not body size, on average) showed less signal than expected given the topology, branch lengths, and a Brownian motion model of evolution (i.e., K was less than one), which may be attributed to adaptation and/or measurement error in the broad sense (including errors in estimates of phenotypes, branch lengths, and topology). Analysis of variance of log K for all 121 traits (from 35 trees) indicated that behavioral traits exhibit lower signal than body size, morphological, life-history, or physiological traits. In addition, physiological traits (corrected for body size) showed less signal than did body size itself. For trees with 20 or more species, the estimated OU (25% of traits) and/or ACDC (40%) transformation parameter differed significantly from both zero and unity, indicating that a hierarchical tree with less (or occasionally more) structure than the original better fit the data and so could be preferred for comparative analyses.

A consensus meeting was convened by the Initiative on Methods, Measurement, and Pain Assessment in Clinical Trials (IMMPACT) to provide recommendations for interpreting clinical importance of treatment outcomes in clinical trials of the efficacy and effectiveness of chronic pain treatments. A group of 40 participants from universities, governmental agencies, a patient self-help organization, and the pharmaceutical industry considered methodologic issues and research results relevant to determining the clinical importance of changes in the specific outcome measures previously recommended by IMMPACT for 4 core chronic pain outcome domains: (1) Pain intensity, assessed by a 0 to 10 numerical rating scale; (2) physical functioning, assessed by the Multidimensional Pain Inventory and Brief Pain Inventory interference scales; (3) emotional functioning, assessed by the Beck Depression Inventory and Profile of Mood States; and (4) participant ratings of overall improvement, assessed by the Patient Global Impression of Change scale. It is recommended that 2 or more different methods be used to evaluate the clinical importance of improvement or worsening for chronic pain clinical trial outcome measures. Provisional benchmarks for identifying clinically important changes in specific outcome measures that can be used for outcome studies of treatments for chronic pain are proposed.

The purpose of this article is to compare three qualitative approaches that can be used in health research: phenomenology, discourse analysis, and grounded theory. The authors include a model that summarizes similarities and differences among the approaches, with attention to their historical development, goals, methods, audience, and products. They then illustrate how these approaches differ by applying them to the same data set. The goal in phenomenology is to study how people make meaning of their lived experience; discourse analysis examines how language is used to accomplish personal, social, and political projects; and grounded theory develops explanatory theories of basic social processes studied in context. The authors argue that by familiarizing themselves with the origins and details of these approaches, researchers can make better matches between their research question(s) and the goals and products of the study.