Does participation in research lead to changes in attitudes among clinicians? Report on a survey of those involved in a French practice research network

Background/Objective: With increasing awareness of some of the limitations of randomised controlled trials as the ‘gold standard’ of psychotherapy evaluation, researchers at the start of the twenty‐first century have focused on a number of new priorities: developing studies in natural conditions; investigating the psychotherapeutic process to better understand the conditions, causes and mechanisms of change; and reducing the gap between clinicians and researchers. Can these three interrelated objectives be combined? Method: A French psychotherapy practice‐based research network (PRN) is used as a field of research for these issues. A survey was used to investigate the conditions that encouraged the clinicians to participate in the PRN study within the context of clinicians’ general opposition to research. Results: Several elements emerged as the key to clinicians’ positive involvement in research: the methodology implemented (intensive case studies during one year); the choice of measures; the constant attention to the practicalities and the potential contribution of studies to clinical practice; the organisation of work in peer groups; the training methods; the use of new information technologies and the sense of participation in a project that would support the profession. Implications: These elements are briefly discussed in relation to the question of how best to encourage clinicians to engage with research.     

What Causes the Mean Bias of the Likelihood Ratio Statistic with Many Variables?

Abstract

Survey data often contain many variables. Structural equation modeling (SEM) is commonly used in analyzing such data. However, conventional SEM methods are not crafted to handle data with a large number of variables (p). A large p can cause T_ml, the most widely used likelihood ratio statistic, to depart drastically from the assumed chi-square distribution even with normally distributed data and a relatively large sample size N. A key element affecting this behavior of T_ml is its mean bias. The focus of this article is to determine the cause of the bias. To this end, empirical means of T_ml via Monte Carlo simulation are used to obtain the empirical bias. The most effective predictors of the mean bias are subsequently identified and their predictive utility examined. The results are further used to predict type I errors of T_ml. The article also illustrates how to use the obtained results to determine the required sample size for T_ml to behave reasonably well. A real data example is presented to show the effect of the mean bias on model inference as well as how to correct the bias in practice.