A review and validation of overall survival extrapolation in health technology assessments of cancer immunotherapy by the National Institute for Health and Care Excellence: how did the initial best estimate compare to trial data subsequently made available?

Background: Validation of overall survival (OS) extrapolations of immune-checkpoint inhibitors (ICIs) during the National Institute for Health and Care Excellence (NICE) Single Technology Assessment (STA) process is limited due to data still maturing at the time of submission. Inaccurate extrapolation may lead to inappropriate decision-making. The availability of more mature trial data facilitates a retrospective analysis of the plausibility and validity of initial extrapolations. This study compares these extrapolations to subsequently available longer-term data.

Methods: A systematic search of completed NICE appraisals of ICIs from March 2000 to December 2017 was performed. A targeted search was also undertaken to procure published OS data from the pivotal clinical trials for each identified STA made available post-submission to NICE. Initial Kaplan-Meier curves and associated extrapolations from NICE documentation were extracted to compare the accuracy of OS projections versus the most mature data.

Results: The review identified 11 STAs, of which 10 provided OS data upon submission to NICE. The extrapolations undertaken considered parametric or piecewise survival models. Additional data cut-offs provided a mean of 18 months of OS beyond the end of the original data. Initial extrapolations typically under-estimated OS from the most mature data cut-off by 0.4–2.7%, depending on the choice of assessment method and use of the manufacturer- or ERG-preferred extrapolation.

Conclusion: Long-term extrapolation of OS is required for NICE STAs based on initial immature OS data. The results of this study demonstrate that the initial OS extrapolations employed by manufacturers and ERGs generally predicted OS reasonably well when compared to more mature data (when available), although on average they appeared to underestimate OS. This review and validation shows that, while the choice of OS extrapolation is uncertain, the methods adopted are generally aligned with later-published follow-up data and appear appropriate for informing HTA decisions.     

Modeling an HR shared services center: Experience of an MNC in the United Kingdom

An increasing number of large and multinational organizations are moving to shared services models in delivering the human resource function. It is commonly believed that the adoption of an HR shared services model can transform the role of HR by enabling the HR function to be more strategic at the corporate level and more cost‐effective at the operational level. However, few academic studies have been carried out to investigate challenges to implementing an HR services center successfully and the impact of adopting an HR shared services model on different groups of employees. Through a case study of a multinational corporation, this article reveals that there remains a significant gap between literature espousing the efficacy and utility of HR shared services and the extent to which the adoption of such a model is successful. The financial and emotional cost of moving to a shared services model can outweigh the tangible cost savings predicted by firms. The idea of separating the HR function into strategic, operational, and administrative components may prove to be too simplistic, although it underpins the initiative of HR shared services. © 2006 Wiley Periodicals, Inc.     

Why do reits engage in open-market repurchases?

We investigate why real estate investment trusts (REITs) still engage in open-market repurchases given the unique 95 percent payout requirement. We provide evidence that the motivations for REITs to repurchase stocks are different from those of unregulated firms found by the existing literature. Instead of using funds from operations, REITs appear to finance stock repurchases by issuing new debt and/or selling assets and investments. Unlike ordinary corporations, REITs stock repurchases are not motivated by cash distribution, capital structure, and undervalued equity. However, REITs are more likely to buy back stocks when employees own a higher level of stock options. Also, we find that REITs are more likely to buy back stocks when they have a higher institutional ownership and/or inside ownership.     

Endogeneity in quantile regression models: A control function approach

This paper considers a linear triangular simultaneous equations model with conditional quantile restrictions. The paper adjusts for endogeneity by adopting a control function approach and presents a simple two-step estimator that exploits the partially linear structure of the model. The first step consists of estimation of the residuals of the reduced-form equation for the endogenous explanatory variable. The second step is series estimation of the primary equation with the reduced-form residual included nonparametrically as an additional explanatory variable. This paper imposes no functional form restrictions on the stochastic relationship between the reduced-form residual and the disturbance term in the primary equation conditional on observable explanatory variables. The paper presents regularity conditions for consistency and asymptotic normality of the two-step estimator. In addition, the paper provides some discussions on related estimation methods in the literature.     

Restricted maximum likelihood estimation under Eisenhart model Ill

For a balanced two-way mixed model, the maximum likelihood (ML) and restricted ML (REML) estimators of the variance components were obtained and compared under the non-negativity requirements of the variance components by L ee and K apadia (1984). In this note, for a mixed (random blocks) incomplete block model, explicit forms for the REML estimators of variance components are obtained. They are always non-negative and have smaller mean squared error (MSE) than the analysis of variance (AOV) estimators. The asymptotic sampling variances of the maximum likelihood (ML) estimators and the REML estimators are compared and the balanced incomplete block design (BIBD) is considered as a special case. The ML estimators are shown to have smaller asymptotic variances than the REML estimators, but a numerical result in the randomized complete block design (RCBD) demonstrated that the performances of the REML and ML estimators are not much different in the MSE sense.     

Performance lies are hazardous to organizational health

Performance lies arise both from individual and from situational causes, but in this article, the attention is on situational causes. These are generally triggered by loyalty to the coalition, which is expressed through the continued use of performance lies. Because performance lies help create a boundary around the coalition that insulates its activities from top management, performance lies enable members of the coalition to exercise a greater degree of internal control. Naturally, such lies are dysfunctional, resulting in the avoidance of difficult issues and problems and compromising the organization's ability to adapt to a changing environment based on accurate information.     

A Note on Minimax Mixture of Distributions Free Procedure for Inventory Model with Variable Lead Time

In recent papers, Moon and Choi (1998) and Hariga and Ben-Daya (1999)considered a continuous review inventory model with a mixture of backordersand lost sales in which the lead time, the order quantity, and the reorder pointare decision variables was studied. Moreover, they also develop a minimaxdistribution free procedure for the problem. While the demands of differentcustomers are not identical in the lead time, then we can't only use a singledistribution (such as Moon & Choi (1998) and Hariga & Ben-Daya (1999))to describe the demand of the lead time. Hence, we correct and extend the modelof Moon and Choi (1998) and Hariga and Ben-Daya (1999) by considering thelead time demand with the mixture of distributions. In addition, we also applythe minimax mixture of distributions free approach to the model by simultaneouslyoptimizing the order quantity, the reorder point, and the lead time to devise a practical procedure which can be used without specific information on demand distribution.     

Revealed preference and differentiable demand

Summary. We prove that, for finitely many demand observations, the Strong Axiom of Revealed Preference tests not only the existence of a strictly concave, strictly monotone and continuous utility generator, but also one that generates an infinitely differentiable demand function. Our results extend those of previous related results (Matzkin and Richter, 1991; Chiappori and Rochet, 1987), yielding differentiable demand functions but without requiring differentiable utility functions.Received: 1 November 2001, Revised: 5 February 2004, JEL Classification Numbers: D11, D12. Correspondence to: Kam-Chau WongThis is a much revised version of Lee and Wong (2001). We are grateful to the Referee for valuable suggestions. We also thank Professor Marcel K. Richter for his comments.     

Improving perishable product inventory management using goal programming

The multiple objectives of perishable product inventory management are examined in this paper. These objectives include: (1) satisfying demand by carrying sufficient inventories, (2) holding down inventory carrying costs, (3) keeping the amount of product spoilage (outdating) at an acceptable level, and (4) maintaining quality by using the product while it is still fresh, and (5) keeping the cost of rotation low. Some of the above objectives are in conflict. Thus, certain redistribution policies may help attain one or more of these objectives to a greater extent. Redistribution involves the transfer of the product from outlets where demand is low to outlets where demand is high. A goal programming model for solving redistribution problems is presented. An example is provided and sensitivity analysis is performed in order to determine when redistribution is advantageous. Applicability of the model is discussed.