Introduction to the special section on Campbell's and Rubin's conceptualizations of causality

Causality plays a fundamental role in scientific explanation. This introduction describes 2 target articles and 3 commentaries on 2 influential perspectives on causal inference, one developed by Donald Campbell and the other developed by Donald Rubin. One goal of this special section is to introduce Rubin's causal model to psychologists who may be largely unfamiliar with it. Another goal is to compare Rubin's conceptualization with Campbell's perspective, to enrich readers' understanding of both views. All of the authors of this special section perceive many similarities between the 2 approaches. Even so, by comparing and contrasting the 2 perspectives, the authors also believe that it is possible to strengthen both approaches.

Statistical methods for risk-outcome research: being sensitive to longitudinal structure

The relation between risk and outcome consists of myriad, complex, longitudinal processes. To study these relations requires research designs and statistical methods that are sensitive to the longitudinal structure of the risk, the outcome, and the risk-outcome relation. This review presents four longitudinal characteristics that can complicate psychopathology risk-outcome research. We represent each complication with an example data set. We demonstrate how conventional statistical approaches can yield highly misleading results. Finally, we review alternative statistical approaches that can handle these complications quite well.

Number fluctuations and energy dissipation in sodium spinor condensates

We characterize fluctuations in atom number and spin populations in F=1 sodium spinor condensates. We find that the fluctuations enable a quantitative measure of energy dissipation in the condensate. The time evolution of the population fluctuations shows a maximum. We interpret this as evidence of a dissipation-driven separatrix crossing in phase space. For a given initial state, the critical time to the separatrix crossing is found to depend exponentially on the magnetic field and linearly on condensate density. This crossing is confirmed by tracking the energy of the spinor condensate as well as by Faraday rotation spectroscopy. We also introduce a phenomenological model that describes the observed dissipation with a single coefficient.

Do Research Literatures Give Correct Answers?

The rationale for insisting on properly designed studies is to ensure the construction of research literatures that are not influenced by biases of any sort. Once a literature is established, however, whatever answers it gives (usually via meta-analysis) are accepted as valid. The results of our favored statistical techniques are understood best when significant relationships are present while the meaning of null results are unclear. Thus, significant findings are more likely to be published. This file drawer problem has been known for many years. However, the effect that the file drawer has on research literatures has never been probed empirically. A new method is described that tests the impact a file drawer has on a research literature. The results of the file drawer on four separate psychological research literatures are presented.

What's Wrong with Research Literatures? And how to Make Them Right

Meta-analysis is now the accepted procedure for summarizing research literatures in areas of applied psychology. Because of the bias for publishing statistically significant findings, while usually rejecting nonsignificant results, our research literatures yield misleading answers to important quantitative questions (e.g., How much better is the average psychotherapy patient relative to a comparable group of untreated controls? How much more aggressive are children who watch a great deal of violent TV than children who watch little or no violence on TV?). While all such research literatures provide overly optimistic meta-analytic estimates, exactly how practically important are these overestimates? Three studies testing the literature on implementation intentions finds only slightly elevated effectiveness estimates. Conversely, in three studies another growing research literature (the efficacy of remote intercessory prayer) is found to be misleading and is in all likelihood not a real effect (i.e., our three studies suggest the literature likely consists of Type I errors). Rules of thumb to predict which research literatures are likely invalid are offered. Finally, revised publication and data analysis procedures to generate unbiased research literatures in the future are examined.

Quantum phase transitions and continuous observation of spinor dynamics in an antiferromagnetic condensate

Condensates of spin-1 sodium display rich spin dynamics due to the antiferromagnetic nature of the interactions in this system. We use Faraday rotation spectroscopy to make a continuous and minimally destructive measurement of the dynamics over multiple spin oscillations on a single evolving condensate. This method provides a sharp signature to locate a magnetically tuned separatrix in phase space which depends on the net magnetization. We also observe a phase transition from a two- to a three-component condensate at a low but finite temperature using a Stern-Gerlach imaging technique. This transition should be preserved as a zero-temperature quantum phase transition.

Bias in cross-sectional analyses of longitudinal mediation

Most empirical tests of mediation utilize cross-sectional data despite the fact that mediation consists of causal processes that unfold over time. The authors considered the possibility that longitudinal mediation might occur under either of two different models of change: (a) an autoregressive model or (b) a random effects model. For both models, the authors demonstrated that cross-sectional approaches to mediation typically generate substantially biased estimates of longitudinal parameters even under the ideal conditions when mediation is complete. In longitudinal models where variable M completely mediates the effect of X on Y, cross-sectional estimates of the direct effect of X on Y, the indirect effect of X on Y through M, and the proportion of the total effect mediated by M are often highly misleading.

High-flux beam source for cold, slow atoms or molecules

We demonstrate and characterize a high-flux beam source for cold, slow atoms or molecules. The desired species is vaporized using laser ablation, then cooled by thermalization in a cryogenic cell of buffer gas. The beam is formed by particles exiting a hole in the buffer gas cell. We characterize the properties of the beam (flux, forward velocity, temperature) for both an atom (Na) and a molecule (PbO) under varying buffer gas density, and discuss conditions for optimizing these beam parameters. Our source compares favorably to existing techniques of beam formation, for a variety of applications.

Assessment of a multiple-dose drug interaction between ezetimibe, a novel selective cholesterol absorption inhibitor and gemfibrozil

OBJECTIVE

Ezetimibe is a novel lipid-lowering drug that prevents intestinal absorption of dietary and biliary cholesterol leading to significant reduction in total-C, LDL-C, Apo B, and TG and increases in HDL-C in patients with hypercholesterolemia. Gemfibrozil, a fibric acid derivative, is an effective lipid-modulating agent that increases serum high-density lipoprotein cholesterol and decreases serum TG. The objective of this study was to evaluate the potential for a pharmacokinetic (PK) interaction between ezetimibe and gemfibrozil.

METHODS

This was a randomized, open-label, 3-way crossover, multiple-dose study in 12 healthy adult male volunteers. All subjects received the following 3 treatments orally for 7 days: ezetimibe 10 mg once daily, gemfibrozil 600 mg every 12 hours, and ezetimibe 10 mg once daily plus gemfibrozil 600 mg every 12 hours. A washout period of > or = 7 days separated the 3 treatments. In each treatment, blood samples were collected on day 7 to assess the steady-state PK of ezetimibe and gemfibrozil. The oral bioavailability of ezetimibe coadministered with gemfibrozil relative to each drug administered alone was evaluated with an analysis-of-variance model.

RESULTS

Ezetimibe was rapidly absorbed and extensively conjugated to its glucuronide metabolite. Ezetimibe did not alter the bioavailability (based on AUC) of gemfibrozil. The mean AUC0-12 of gemfibrozil was 74.7 and 74.1 microg h/ml with and without ezetimibe coadministration, respectively (log-transformed geometric mean ratio (GMR) = 99.2; 90% confidence interval (CI) = 92 - 107%). Conversely, gemfibrozil significantly (p < 0.05) increased the plasma concentrations of ezetimibe and total ezetimibe (i.e. ezetimibe plus ezetimibe-glucuronide). Exposure to ezetimibe and total ezetimibe was increased approximately 1.4-fold and 1.7-fold, respectively (CI = 109 - 173% for ezetimibe and 142 - 190% for total ezetimibe), however, this increase was not considered to be clinically relevant. Ezetimibe and gemfibrozil administered alone or concomitantly for 7 days was well tolerated.

CONCLUSIONS

The coadministration of ezetimibe and gemfibrozil in patients is unlikely to cause a clinically significant drug interaction. The coadministration of these agents is a promising approach for patients with mixed dyslipidemia. Additional clinical studies are warranted.

The Persistence of Underpowered Studies in Psychological Research: Causes, Consequences, and Remedies

Underpowered studies persist in the psychological literature. This article examines reasons for their persistence and the effects on efforts to create a cumulative science. The "curse of multiplicities" plays a central role in the presentation. Most psychologists realize that testing multiple hypotheses in a single study affects the Type I error rate, but corresponding implications for power have largely been ignored. The presence of multiple hypothesis tests leads to 3 different conceptualizations of power. Implications of these 3 conceptualizations are discussed from the perspective of the individual researcher and from the perspective of developing a coherent literature. Supplementing significance tests with effect size measures and confidence intervals is shown to address some but not necessarily all problems associated with multiple testing.

Sample size for multiple regression: obtaining regression coefficients that are accurate, not simply significant

An approach to sample size planning for multiple regression is presented that emphasizes accuracy in parameter estimation (AIPE). The AIPE approach yields precise estimates of population parameters by providing necessary sample sizes in order for the likely widths of confidence intervals to be sufficiently narrow. One AIPE method yields a sample size such that the expected width of the confidence interval around the standardized population regression coefficient is equal to the width specified. An enhanced formulation ensures, with some stipulated probability, that the width of the confidence interval will be no larger than the width specified. Issues involving standardized regression coefficients and random predictors are discussed, as are the philosophical differences between AIPE and the power analytic approaches to sample size planning.

Obtaining power or obtaining precision. Delineating methods of sample-size planning

Sample-size planning historically has been approached from a power analytic perspective in order to have some reasonable probability of correctly rejecting the null hypothesis. Another approach that is not as well-known is one that emphasizes accuracy in parameter estimation (AIPE). From the AIPE perspective, sample size is chosen such that the expected width of a confidence interval will be sufficiently narrow. The rationales of both approaches are delineated and two procedures are given for estimating the sample size from the AIPE perspective for a two-group mean comparison. One method yields the required sample size, such that the expected width of the computed confidence interval will be the value specified. A modification allows for a defined degree of probabilistic assurance that the width of the computed confidence interval will be no larger than specified. The authors emphasize that the correct conceptualization of sample-size planning depends on the research questions and particular goals of the study.

Analytic methods for questions pertaining to a randomized pretest, posttest, follow-up design

Delineates 5 questions regarding group differences that are likely to be of interest to researchers within the framework of a randomized pretest, posttest, follow-up (PPF) design. These 5 questions are examined from a methodological perspective by comparing and discussing analysis of variance (ANOVA) and analysis of covariance (ANCOVA) methods and briefly discussing hierarchical linear modeling (HLM) for these questions. This article demonstrates that the pretest should be utilized as a covariate in the model rather than as a level of the time factor or as part of the dependent variable within the analysis of group differences. It is also demonstrated that how the posttest and the follow-up are utilized in the analysis of group differences is determined by the specific question asked by the researcher.

Testing Mediational Models With Longitudinal Data: Questions and Tips in the Use of Structural Equation Modeling

R. M. Baron and D. A. Kenny (1986; see record 1987-13085-001) provided clarion conceptual and methodological guidelines for testing mediational models with cross-sectional data. Graduating from cross-sectional to longitudinal designs enables researchers to make more rigorous inferences about the causal relations implied by such models. In this transition, misconceptions and erroneous assumptions are the norm. First, we describe some of the questions that arise (and misconceptions that sometimes emerge) in longitudinal tests of mediational models. We also provide a collection of tips for structural equation modeling (SEM) of mediational processes. Finally, we suggest a series of 5 steps when using SEM to test mediational processes in longitudinal designs: testing the measurement model, testing for added components, testing for omitted paths, testing the stationarity assumption, and estimating the mediational effects.

Power in randomized group comparisons: the value of adding a single intermediate time point to a traditional pretest-posttest design

Adding a pretest as a covariate to a randomized posttest-only design increases statistical power, as does the addition of intermediate time points to a randomized pretest-posttest design. Although typically 5 waves of data are required in this instance to produce meaningful gains in power, a 3-wave intensive design allows the evaluation of the straight-line growth model and may reduce the effect of missing data. The authors identify the statistically most powerful method of data analysis in the 3-wave intensive design. If straight-line growth is assumed, the pretest-posttest slope must assume fairly extreme values for the intermediate time point to increase power beyond the standard analysis of covariance on the posttest with the pretest as covariate, ignoring the intermediate time point.

The development of multiple domains of child and adolescent self-concept: a cohort sequential longitudinal design

The development of child and adolescent self-concept was examined as a function of the self-concept domain, social/developmental/educational transitions, and gender. In two overlapping age cohorts of public school students (Ns = 936 and 984), five dimensions of self-concept were evaluated every 6 months in a manner that spanned grades 3 through 11 (representing the elementary, middle, and high school years). Domains of self-concept included academic competence, physical appearance, behavioral conduct, social acceptance, and sports competence. Structural equation modeling addressed questions about the stability of individual differences over time. Multilevel modeling addressed questions about mean-level changes in self-concept over time. Significant effects emerged with regard to gender, age, dimension of self-concept, and educational transition.

Sample size and multiple regression analysis

Despite the development of procedures for calculating sample size as a function of relevant effect size parameters, rules of thumb tend to persist in designs of multiple regression studies. One explanation for their persistence may be the difficulty in formulating a reasonable a priori value of an effect size to be detected. This article presents methods for calculating effect sizes in multiple regression from a variety of perspectives and also introduces a new method based on an exchangeability structure among predictor variables. No single method is deemed superior, but rather examples show that a combination of methods is likely to be most valuable in many situations. A simulation provides a 2nd explanation for why rules of thumb for choosing sample size have persisted but also shows that the outcome of such underpowered studies will be a literature consisting of seemingly contradictory results.

Prenatal maternal predictors of cognitive and emotional delays in children of adolescent mothers

The present study examined relationships among prenatal characteristics of 121 adolescent mothers-including cognitive readiness for parenting, intelligence, social support, and personal adjustment-and intellectual-linguistic development, social-emotional functioning, and adaptive behavior in their children at three years of age. Only 28% of the children scored within normal ranges on all three types of outcomes. Intellectual and linguistic delays were predicted best by prenatal measures of maternal Performance IQ and social support from extended family. Socioemotional problems were predicted best by maternal internalizing problems and social support from partner and friends. Adaptive behavior was associated with parenting style. Implications for the early identification of high-risk children--and associated intervention programs--are discussed.

The proof of the pudding: an illustration of the relative strengths of null hypothesis, meta-analysis, and Bayesian analysis

Some methodologists have recently suggested that scientific psychology's over-reliance on null hypothesis significance testing (NHST) impedes the progress of the discipline. In response, a number of defenders have maintained that NHST continues to play a vital role in psychological research. Both sides of the argument to date have been presented abstractly. The authors take a different approach to this issue by illustrating the use of NHST along with 2 possible alternatives (meta-analysis as a primary data analysis strategy and Bayesian approaches) in a series of 3 studies. Comparing and contrasting the approaches on actual data brings out the strengths and weaknesses of each approach. The exercise demonstrates that the approaches are not mutually exclusive but instead can be used to complement one another.

Structural differences in parent and child reports of children's symptoms of depression and anxiety

Two cohorts of public elementary school children and their parents (assessed 3 years apart) completed child and parent forms of the Children's Depression Inventory (CDI) and the Revised Children's Manifest Anxiety Scale (RCMAS). Assessments were conducted twice, once during the fall (N = 562) and again during the spring (N = 630) of the 6th grade. Factor analyses revealed 3 factors for each measure. Two of the 3 parent CDI factors manifested some degree of congruence with their counterparts from the child CDI. Similarly, 2 of the 3 RCMAS factors were somewhat congruent across informant types. Differences between parent and child factor structures suggest that parents' and children's reports focus on somewhat different aspects of child psychopathology, and they can make qualitatively different contributions to the multiaxial assessment of children.

Structural differences in parent and child reports of children's symptoms of depression and anxiety

Two cohorts of public elementary school children and their parents (assessed 3 years apart) completed child and parent forms of the Children's Depression Inventory (CDI) and the Revised Children's Manifest Anxiety Scale (RCMAS). Assessments were conducted twice, once during the fall (N = 562) and again during the spring (N = 630) of the 6th grade. Factor analyses revealed 3 factors for each measure. Two of the 3 parent CDI factors manifested some degree of congruence with their counterparts from the child CDI. Similarly, 2 of the 3 RCMAS factors were somewhat congruent across informant types. Differences between parent and child factor structures suggest that parents' and children's reports focus on somewhat different aspects of child psychopathology, and they can make qualitatively different contributions to the multiaxial assessment of children.