A New Multistate Transition Model For Effect Estimation In Randomized Trials With Treatment Switching And A Cured Subgroup

Background: Many methods, including multistate models, have been proposed in the literature to estimate the treatment effect on overall survival in randomized trials with treatment switching permit after the disease progression. Nevertheless, the cured fraction of patients has not been considered. The cured would never experience the progressive disease, but they may suffer death with a hazard comparable to that of people without the disease. With the mix of the cured subgroup, existing methods yield highly biased effect estimation and fail to reflect the truth in uncured patients. Methods: In this paper, we propose a new multistate transition model to incorporate the cure, progression, treatment switching, and death states during trials. In the proposed model, the probability of cure and the death hazard of the cured are modeled separately. For the not cured patients, the semi-competing risks model is used with the treatment effect evaluated via transitional hazards between states. The particle swarm optimization algorithm is adopted to estimate the model parameters. Results: Extensive simulation studies have been conducted to evaluate the performance of the proposed multistate model and compare it with existing treatment switching adjustment methods. Results show that in all scenarios, the treatment effect estimation of the proposed model is more accurate than that of existing treatment switching adjustment methods. Besides, the application to diffuse large B-cell lymphoma data has also illustrated the superiority of the proposed model.Conclusions: The superiority and robustness of the proposed multistate transition model qualify it to estimate the treatment effect in trials with the treatment switching permit after progression and a cured subgroup.

Improving the causal treatment effect estimation with propensity scores by the bootstrap

When observational studies are used to establish the causal effects of treatments, the estimated effect is affected by treatment selection bias. The inverse propensity score weight (IPSW) is often used to deal with such bias. However, IPSW requires strong assumptions whose misspecifications and strategies to correct the misspecifications were rarely studied. We present a bootstrap bias correction of IPSW (BC-IPSW) to improve the performance of propensity score in dealing with treatment selection bias in the presence of failure to the ignorability and overlap assumptions. The approach was motivated by a real observational study to explore the potential of anticoagulant treatment for reducing mortality in patients with end-stage renal disease. The benefit of the treatment to enhance survival was demonstrated; the suggested BC-IPSW method indicated a statistically significant reduction in mortality for patients receiving the treatment. Using extensive simulations, we show that BC-IPSW substantially reduced the bias due to the misspecification of the ignorability and overlap assumptions. Further, we showed that IPSW is still useful to account for the lack of treatment randomization, but its advantages are stringently linked to the satisfaction of ignorability, indicating that the existence of relevant though unmeasured or unused covariates can worsen the selection bias.

The Effect of Corporate Social Responsibility and Board Gender Diversity on Bankruptcy: Evidence from Korea

This study investigates whether corporate social responsibility (CSR) activities and board gender diversity affect bankruptcy. The core issue focuses on the moderating effect between CSR activities and board gender diversity on bankruptcy. Using 4,654 firmyear observations from a sample of 581 non-financial firms listed on the Korean Stock Exchange over the period 2009–2017, we employ the fixed effect estimation and two-way fixed effect estimation of panel analysis to control endogenous. We find firms engaging more in CSR activities reduce the level of bankruptcy, but board gender diversity does not reduce the level of bankruptcy due to tiny portion of female director in the boardroom. The moderating effect on the relationship between CSR activities and board gender diversity reduce the level of bankruptcy. This result indicates that the influence of female directors on the boards of Korean listed firms is not yet strong but board gender diversity with good CSR activities positively operate to reduce the level of bankruptcy.

Impact of East African Community Integration on Trade: Gravity Model Approach

East African community (EAC) is a regional economic bloc established to foster economic corporation between Kenya, Rwanda, Burundi, Uganda and Tanzania. Using gravity model the study explores the short run and long run effect of East African community (EAC) on trade using parametric, random effect and fixed effect estimation techniques. Secondly, the study investigates whether formation of EAC led to trade creation or trade diversion in the long run among the member countries of EAC. Lastly, the study establishes the effect of entry of Burundi and Rwanda to the economic bloc of EAC on trade. The study used panel data obtained from the five countries of EAC for the period 1985 to 2019. Breausch Pagan LM test for restrictions in the parametric model and Hausman test for endogeinity in the gravity model found out that fixed effect estimation technique produced accurate and plausible results than parametric and random effect estimation techniques. The empirical results of fixed effect model established that trade across EAC member countries rose by 1.6% in the short run while random effect and parametric models recorded 3.6% increase in trade in the short run. This effect was insignificant meaning that trade between EAC member countries did not expand considerably in the short run. In the long run, fixed effect indicate that EAC increased trade by 24.2% while random effect and parametric model each show that EAC increased trade by 16%. The coefficients are statistically significant at 5% ceteris paribus. Secondly, economic corporation of EAC led to trade creation in Burundi, Kenya, Rwanda and Uganda by 41.6%, 12.2%, 33.9% and 30.1% respectively and trade diversion by 4.2% in Tanzania. Thirdly, entry of Burundi and Rwanda to EAC increased trade of EAC countries by 19.6%. The coefficient is statistically significant at 5% level. The results of random effect and parametric model each indicate a growth in trade by 19.1%. The results of parametric, random effect and fixed effect estimation techniques are all consistent. Lastly, the study established that countries in EAC ought to foster greater growth in GDP, to encourage and strengthen use of common language and to reduce cross border restrictions in order to realize more growth in trade.

Non-parametric treatment time-lag effect estimation

In general, the change point problem considers inference of a change in distribution for a set of time-ordered observations. This has applications in a large variety of fields, and can also apply to survival data. In survival analysis, most existing methods compare two treatment groups for the entirety of the study period. Some treatments may take a length of time to show effects in subjects. This has been called the time-lag effect in the literature, and in cases where time-lag effect is considerable, such methods may not be appropriate to detect significant differences between two groups. In this paper, we propose a novel non-parametric approach for estimating the point of treatment time-lag effect by using an empirical divergence measure. Theoretical properties of the estimator are studied. The results from the simulated data and the applications to real data examples support our proposed method.