Data‐driven treatment selection for seamless phase II/III trials incorporating early‐outcome data

Seamless phase II/III clinical trials are conducted in two stages with treatment selection at the first stage. In the first stage, patients are randomized to a control or one of k > 1 experimental treatments. At the end of this stage, interim data are analysed, and a decision is made concerning which experimental treatment should continue to the second stage. If the primary endpoint is observable only after some period of follow‐up, at the interim analysis data may be available on some early outcome on a larger number of patients than those for whom the primary endpoint is available. These early endpoint data can thus be used for treatment selection. For two previously proposed approaches, the power has been shown to be greater for one or other method depending on the true treatment effects and correlations. We propose a new approach that builds on the previously proposed approaches and uses data available at the interim analysis to estimate these parameters and then, on the basis of these estimates, chooses the treatment selection method with the highest probability of correctly selecting the most effective treatment. This method is shown to perform well compared with the two previously described methods for a wide range of true parameter values. In most cases, the performance of the new method is either similar to or, in some cases, better than either of the two previously proposed methods. © 2014 The Authors. Pharmaceutical Statistics published by John Wiley & Sons Ltd.     

The Effects of Knowledge Management on Team Members' Ratings of Project Success and Impact*

Many organizations are trying to improve the generation and utilization of knowledge. The activities associated with these efforts are identified as organizational knowledge management (KM). While much has been written about knowledge management from the organizational level, the success of such efforts over the long run will depend upon on how KM activities impact important outcomes as perceived by those at the employee level who actually implement the activities. This study used the input‐process‐output framework of team effectiveness to investigate the relationship between selected KM‐related activities on integrated product and process development team members' satisfaction with their project's success and the impact they expected it to have on the organization. The results indicate that team‐level leadership and support (i.e., inputs), along with knowledge generation and dissemination (i.e., processes), are key drivers of member performance‐related ratings (i.e., outputs). Finally, and possibly most importantly, a number of interactions were evident suggesting that the KM processes moderate the effects of the KM inputs. These findings and their implications are discussed.     

Fiscal Foresight and Information Flows

News—or foresight—about future economic fundamentals can create rational expectations equilibria with non‐fundamental representations that pose substantial challenges to econometric efforts to recover the structural shocks to which economic agents react. Using tax policies as a leading example of foresight, simple theory makes transparent the economic behavior and information structures that generate non‐fundamental equilibria. Econometric analyses that fail to model foresight will obtain biased estimates of output multipliers for taxes; biases are quantitatively important when two canonical theoretical models are taken as data generating processes. Both the nature of equilibria and the inferences about the effects of anticipated tax changes hinge critically on hypothesized information flows. Different methods for extracting or hypothesizing the information flows are discussed and shown to be alternative techniques for resolving a non‐uniqueness problem endemic to moving average representations.     

Re-examining female labor supply responses to the 1994 Australian pension reform

Many governments are aiming to extend working lives by raising the age at which people can claim retirement pensions. This makes it vital to understand how these policies affect retirement decisions. In this paper, I revisit the labor supply effects of a major Australian reform that increased women’s pension age from 60 to 65. Atalay and Barrett (2015) studied these effects using repeated household surveys and a differences-in-differences design in which male cohorts form the comparison group. They estimate that the reform increased female labor force participation by 12 percentage points. Using earlier data, I show that the parallel-trends assumption did not hold before the reform because of a strong female-specific trend in participation rates across the relevant cohorts. Accounting for this trend, the estimated effect on female participation falls by two-thirds and becomes statistically insignificant at conventional levels. This highlights the importance of carefully assessing and controlling for trends across cohorts when evaluating pension reforms, which are typically phased in across cohorts.