Smoothing Corrections for Improving Sample Size Recalculation Rules in Adaptive Group Sequential Study Designs

Background An adequate sample size calculation is essential for designing a successful clinical trial. One way to tackle planning difficulties regarding parameter assumptions required for sample size calculation is to adapt the sample size during the ongoing trial.This can be attained by adaptive group sequential study designs. At a predefined timepoint, the interim effect is tested for significance. Based on the interim test result, the trial is either stopped or continued with the possibility of a sample size recalculation. Objectives Sample size recalculation rules have different limitations in application like a high variability of the recalculated sample size. Hence, the goal is to provide a tool to counteract this performance limitation. Methods Sample size recalculation rules can be interpreted as functions of the observed interim effect. Often, a “jump” from the first stage's sample size to the maximal sample size at a rather arbitrarily chosen interim effect size is implemented and the curve decreases monotonically afterwards. This jump is one reason for a high variability of the sample size. In this work, we investigate how the shape of the recalculation function can be improved by implementing a smoother increase of the sample size. The design options are evaluated by means of Monte Carlo simulations. Evaluation criteria are univariate performance measures such as the conditional power and sample size as well as a conditional performance score which combines these components. Results We demonstrate that smoothing corrections can reduce variability in conditional power and sample size as well as they increase the performance with respect to a recently published conditional performance score for medium and large standardized effect sizes. Conclusion Based on the simulation study, we present a tool that is easily implemented to improve sample size recalculation rules. The approach can be combined with existing sample size recalculation rules described in the literature.

Subseasonal prediction performance for austral summer South American rainfall

Skilful and reliable predictions of week-to-week rainfall variations in South America, two to three weeks ahead, are essential to protect lives, livelihoods and ecosystems. We evaluate forecast performance for weekly rainfall in extended austral summer (November–March) in four contemporary subseasonal systems, including a new Brazilian model, at 1–5 week leads for 1999–2010. We measure performance by the correlation coefficient (in time) between predicted and observed rainfall; we measure skill by the Brier Skill Score for rainfall terciles against a climatological reference forecast. We assess unconditional performance (i.e., regardless of initial condition) and conditional performance based on the initial phase of the Madden–Julian Oscillation (MJO) and the El Niño–Southern Oscillation (ENSO). All models display substantial mean rainfall biases, including dry biases in Amazonia and wet biases near the Andes, which are established by Week 1 and vary little thereafter. Unconditional performance extends to Week 2 in all regions except for Amazonia and the Andes, but to Week 3 only over northern, northeastern and southeastern South America. Skill for upper- and lower-tercile rainfall extends only to Week 1. Conditional performance is not systematically or significantly higher than unconditional performance; ENSO and MJO events provide limited “windows of opportunity” for improved S2S predictions that are region- and model-dependent. Conditional performance may be degraded by errors in predicted ENSO and MJO teleconnections to regional rainfall, even at short lead times.

Institutions of collective investment in Ukraine: scale and consequences of investment dysfunction

The development of collective investment institutions (CIIs) in Ukraine is characterized by rather ambiguous and stable trends, which at first glance do not have any objective economic basis. The dynamics of CIIs activities in Ukraine demonstrates their steady invulnerability to the crises in the global and national economy, maintaining positions (in quantity terms) against the background of reduced number of both professional stock market participants and other institutional investors, and despite the decrease in the financial instruments in circulation, and the gradual formation in public consciousness of a neutral negative view of the functioning of the national stock market. The authors' assumption that the key to such institutional viability consists in the tax preferences for the CIIs, which is confirmed by the analysis. It is noted that in this case both the economic sense and the declared "collectivity" of this investment institution are distorted. The use of CIIs solely to ease the tax burden, with gross legal and tax violations creates risks for both the beneficiaries of such tax schemes and for the very existence of the institution. The specificity of "investment areas" outside the stock market, the highly conditional performance of the function of accumulation of investment resources and, correspondingly, the profanation of the CIIs' issuer function, in particular as to the fair distribution of investment income, distortions of the essence of the ideology of collective investment in combination with extremely loyal regulation on the part of the NSSMC all presently call into question the entire possibility of considering CIIs as a full-fledged component of the stock market.

Comparación de la respuesta física, en términos absolutos y relativos a la competición, de diferentes demarcaciones en tareas jugadas de fútbol

El objetivo fue estudiar las demandas externas absolutas y relativas respecto a la competición de diferentes formatos de juego en el fútbol teniendo en cuenta las diferentes demarcaciones de los jugadores. Se registraron cuatro variables externas en 20 jugadores semiprofesionales en cuatro tipos de tareas jugadas (4vs4 o JRP, 6vs6 o JRM y 8vs8 o JRL) y partidos de entrenamiento (10vs10 o PE) para un total de 467 registros. Las variables externas fueron: la distancia total (DTmin y %DT) y carga del jugador (PLmin y %PL), en valores absolutos por minuto de práctica y en valores relativos al perfil de las demandas en competición. Los resultados fueron que: en formatos más pequeños (JRP y JRM) con pocos jugadores la demanda en términos absolutos (en m por min-1) fue similar entre las diferentes demarcaciones, pero no así en términos relativos a las demandas de la competición. Por el contrario, las diferencias entre las diferentes posiciones de juego se minimizan en los formatos más grandes JRL y PE cuando se expresaron en términos relativos a la competición, pero no así en términos absolutos, donde existen diferencias. La conclusión del estudio es que las diferencias en las demandas entre las demarcaciones varían entre los formatos de juego, y, además, estas diferencias se incrementan o se equiparan según se consideren los valores en términos absolutos o relativos al perfil de competición individual. Los resultados sugieren que los entrenadores deberían considerar todo el espectro de tareas (e.g., desde 1vs1 a 10vs10) para atender a las necesidades particulares de cada demarcación y contextualizado a los objetivos técnico-tácticos y condicionales deseados con el propósito de optimizar su rendimiento. The objective was to study the physical response to conditional performance in competition of different game formats in football taking into account the demarcation of players. Four external load variables were recorded in 16 semi-professional players in four types of tasks played (4vs4 [JRP], 6vs6 [JRM] and 8vs8 [JRL]) and training matches (10vs10 [PE]) for a total of 467 records. The physical variables analyzed were the following: (a) DTmin, total distance in absolute values per minute of activity, (b) %DT, total distance per minute in values relative to the profile of demands in competition, (c) PLmin, player load in absolute values per minute of activity, and (d) %PL, player load per minute in values relative to the profile of demands in competition. The results were that in the JRP and JRM formats for the variables DTmin and PLmin the values were similar between demarcations, but not being the same for the variables %DT and %PL. On the contrary, the differences between the different game positions were minimized in the large formats (JRL and PE) when the %DT and %PL variables were analyzed, as opposed to DTmin and PLmin, where there were more differences between demarcations. The conclusion was that, depending on whether the physical variables are considered in absolute terms or in relation to the competition, the differences between demarcations are not uniform: small formats equal the conditional response in absolute terms, while large formats equal the conditional response between players in terms of the individual profile in competition. O objetivo era estudar a resposta física ao desempenho condicional na competição de diferentes formatos de jogo no futebol, levando em conta a demarcação dos jogadores. Quatro variáveis de carga externa foram registradas em 16 jogadores semi-profissionais em quatro tipos de tarefas jogadas (4vs4 [JRP], 6vs6 [JRM] e 8vs8 [JRL]) e partidas de treinamento (10vs10 [PE]) para um total de 467 registros. As variáveis físicas analisadas foram as seguintes: (a) DTmin, distância total em valores absolutos por minuto de atividade, (b) %DT, distância total por minuto em valores relativos ao perfil de exigências na competição, (c) PLmin, carga de jogadores em valores absolutos por minuto de atividade, e (d) %PL, carga de jogadores por minuto em valores relativos ao perfil de exigências na competição. Os resultados foram que nos formatos JRP e JRM para as variáveis DTmin e PLmin os valores foram semelhantes entre as demarcações, mas não sendo os mesmos para as variáveis %DT e %PL. Pelo contrário, as diferenças entre as diferentes posições de jogo foram minimizadas nos grandes formatos (JRL e PE) quando as variáveis %DT e %PL foram analisadas, ao contrário do DTmin e PLmin, onde houve mais diferenças entre as demarcações. A conclusão foi que, dependendo se as variáveis físicas são consideradas em termos absolutos ou em relação à competição, as diferenças entre demarcações não são uniformes: formatos pequenos igualam a resposta condicional em termos absolutos, enquanto formatos grandes igualam a resposta condicional entre jogadores em termos do perfil individual em competição.