Confidence Intervals for the Mean in Selecting an Appropriate Time-Dependent Distribution Model for Processes with Non-Normal Instantaneous Distributions

Purpose: This paper proposes the possibility of using confidence intervals for the mean and variance in selecting a suitable time-dependent distribution model for the process. Methodology/Approach: The approach describes a characteristic under consideration by the distribution, the location, the dispersion, and the shape, all of which are functions of time. The values of the characteristics under consideration are determined by taking samples from the process flow. Time-dependent distribution models are classified into four groups based on whether the location and dispersion moments remain constant or vary over time. Findings: The paper explains a method for creating random samples, along with the calculation, presentation, and interpretation of the confidence intervals for the mean and variance in choosing the appropriate time-dependent distribution model of the process. Research Limitation/Implication: The methods described in this document pertain exclusively to continuous quality characteristics. They can be applied to analyse processes across various industrial and economic sectors. The presented procedures assume that all instantaneous distributions are normal. Originality/Value of paper: Confidence intervals can improve decision-making when selecting a suitable time-dependent distribution model.

2662 Background: Immune checkpoint inhibitors (ICIs) have revolutionised cancer treatment but are only effective in a subset of patients. Evidence of a circadian dependence of the immune system has led to retrospective studies which suggested that the time of day of ICIs infusion influences treatment response, with better outcomes for early treatment times. Previous studies are limited by small sample size and methodological bias. We performed a retrospective study in patients with advanced solid tumours treated with ICIs at a large tertiary cancer centre. Methods: Patients who received regimens comprising ICIs for advanced/metastatic disease between January 2018 and December 2023 were grouped according to whether they received ≥50% (“late group”) or < 50% (“early group”) of cycles after the median time of all treatments. The primary endpoint was overall survival (OS). Hazard ratios (HRs) for OS after multivariable adjustments for age, sex, Eastern Cooperative Oncology Group (ECOG) performance status, cancer type and treatment were estimated using Cox models with and without time-dependent variables that allowed for group (early vs. late) assignment to change after baseline. Results: 2631 patients with lung cancer (45%), melanoma (23%), renal carcinoma (18%), head and neck (9%) and urothelial cancer (5%) were included. The median age was 68.2 years and 1602 (61%) were men. The median follow up was 38 months. The median infusion time was 12:49h. Median OS was 13.1 (95% confidence interval [CI] 11.8-14.4) vs. 21.4 (95% CI 19.8-24.5) months for late and early group. The late group was associated with shorter OS compared to the early group on both the standard multivariate analysis (HR 1.48, 95% CI 1.33-1.63) and the time dependent Cox model (HR 1.30, 95% CI 1.16-1.44). The association was significant for most regimens with ICIs alone (n = 1886) and for ICIs plus tyrosine kinase inhibitors (n = 163). There was no difference for regimens comprising chemotherapy (n = 582). A sensitivity analysis based on exposure at 3 months showed no difference between the groups with the standard model (HR 1.09, 95% CI 0.98-1.20) and a higher risk of death for the late group with the time dependent model (HR 1.14, 95% CI 1.02-1.26). Conclusions: This study suggests a benefit in OS with early administration of ICIs with a large sample size and a time-dependent Cox model which reduces the risk of immortal time bias. These findings could have a major clinical impact after small changes in the way services are provided. Exclusive morning administration for all doses in the first 3 months could be a feasible approach to minimise complexity of treatment slot allocation.

Reply

Serum Phosphorus and Cardiovascular Mortality in Type 2 Diabetes

This study addresses the challenge of limited data availability in animal science, particularly in modeling complex biological processes such as methane emissions from ruminants. We propose a novel rank-based method for generating synthetic databases with correlated non-normal multivariate distributions aimed at enhancing the accuracy and reliability of predictive modeling tools. Our rank-based approach involves a four-step process: 1) fitting distributions to variables using normal or best-fit non-normal distributions, 2) generating synthetic databases, 3) preserving relationships among variables using Spearman correlations, and 4) cleaning datasets to ensure biological plausibility. We compare this method with copula-based approaches to maintain a preestablished correlation structure. The rank-based method demonstrated superior performance in preserving original distribution moments (mean, variance, skewness, kurtosis) and correlation structures compared to copula-based methods. We generated two synthetic databases (normal and non-normal distributions) and applied random forest (RF) and multiple linear model (LM) regression analyses. RF regression outperformed LM in predicting methane emissions, showing higher R2 values (0.927 vs. 0.622) and lower standard errors. However, cross-testing revealed that RF regressions exhibit high specificity to distribution types, underperforming when applied to data with differing distributions. In contrast, LM regressions showed robustness across different distribution types. Our findings highlight the importance of understanding distributional assumptions in regression techniques when generating synthetic databases. The study also underscores the potential of synthetic data in augmenting limited samples, addressing class imbalances, and simulating rare scenarios. While our method effectively preserves descriptive statistical properties, we acknowledge the possibility of introducing artificial (unknown) relationships within subsets of the synthetic database. This research uncovered a practical solution for creating realistic, statistically sound datasets when original data is scarce or sensitive. Its application in predicting methane emissions demonstrates the potential to enhance modeling accuracy in animal science. Future research directions include integrating this approach with deep learning, exploring real-world applications, and developing adaptive machine-learning models for diverse data distributions.

Temporal distribution of earthquakes with M w > 6 in the Dasht-e-Bayaz region, eastern Iran has been investigated using time-dependent models. Based on these types of models, it is assumed that the times between consecutive large earthquakes follow a certain statistical distribution. For this purpose, four time-dependent inter-event distributions including the Weibull, Gamma, Lognormal, and the Brownian Passage Time (BPT) are used in this study and the associated parameters are estimated using the method of maximum likelihood estimation. The suitable distribution is selected based on logarithm likelihood function and Bayesian Information Criterion. The probability of the occurrence of the next large earthquake during a specified interval of time was calculated for each model. Then, the concept of conditional probability has been applied to forecast the next major (M w > 6) earthquake in the site of our interest. The emphasis is on statistical methods which attempt to quantify the probability of an earthquake occurring within a specified time, space, and magnitude windows. According to obtained results, the probability of occurrence of an earthquake with M w > 6 in the near future is significantly high.

One of the most important sectors of the economy in Russia is industry. In this regard, the state seeks to stimulate the development of innovations in this area. Over the past few years, many industrial sectors in Russia have been in a crisis situation, which is caused by several factors: a decrease in the level of real investment, a decrease in the solvent demand of enterprises-customers and public consumers, and the introduction of financial and economic sanctions in 2014 against Russia by the United States and the European Union countries, as well as the effect of other macroeconomic factors independent of the activities of industrial enterprises. This study aims to identify the main trends in the development of industrial production in Russia in recent years, and an explanation of its causes. This topic is relevant in connection with the foregoing and may be of interest to academic economists studying industry development trends in developing countries. The aim of the study is to analyze the state of industry in Russia from 2015 to 2018 during the period of sanction pressure on the industrial and financial sectors of the Russian economy. Having examined the latest data on the results of the activity of Russian industry as a whole, one can note positive trends in the development of industrial production in Russia despite a number of negative internal and external factors. It is concluded that today, for Russia, the strategic tasks in industrial policy are reduced to overcoming technological backwardness and carrying out technological modernization of industries based on the use of innovative achievements, as well as import substitution for the sectors of the economy that are sensitive to foreign sanctions.

The main objective of the study was to identify factors associated with neonatal, post-neonatal and child mortality. The study also investigated breastfeeding status as a time-dependent variable. The 2016-2017 Haitian Demographic and Health Survey was analysed. The analysis was done on 6530 live births. Time-constant and time-dependent multivariable Royston-Parmar spline models were used to identify associated factors for all three age groups. Restricted mean survival times were calculated for the different levels of the breastfeeding variable for each age group. Neonates and post-neonates who were not breastfed were associated with increased mortality, hazard ratio (HR) 22.13 (95% confidence interval (CI), 16.40-29.87) and HR 4.99 (95% CI, 3.29-7.56), respectively. Males in the child age group were associated with increased mortality, HR 2.04 (95% CI, 1.29-3.23) and HR 2.03 (95% CI, 1.28-3.21) under the time-constant and time-dependent models, respectively. Early initiation of breastfeeding and breastfeeding throughout the post-neonatal period is recommended. Outreach programmes that provide support and education for vulnerable families are also recommended.

Most related literature tackles quality characteristic(s) as single or simultaneous optimisation of multiple characteristics but through simple linear experimentation or mixture of linear orthogonal arrays. Due to their nature, characteristics demonstrate normal data distribution, analysed through traditional statistical methods or by computer aided solutions. This article tackles multiresponse quality characteristics through saturated non-linear OA experimentation that yields non-normal data distribution of a screening procedure in order to improve software design. Traditional analysis has limitations over such topics demanding a more sophisticated approach. Analysing such complex systems is achieved through artificial neural networks' function approximation ability which requires adequate data as training and testing exemplars that will produce a confident objective predicting system for the optimal control and level set. Experiment replication involves noise factors as being part of the screening process with a major role over the arrangements of the methodology proposed. E-mail spamming is used as a case study!

This article identifies the level of the expected utility (EU) risk aversion and Value‐at‐Risk (VaR) confidence level that yield the same choice from a given distribution of outcomes, and thus allow for consistent application of the two criteria. The result for a given distribution is an explicit mapping between risk aversion under EU and VaR, for both normal and nonnormal distributions. The Cornish–Fisher expansion is used to establish adjusted mean‐deviates for nonnormal outcome distributions and the investor's preference function is expanded to include elements for variance, skewness, and excess kurtosis. A farm‐level application with nonnormal revenue distribution illustrates these approaches.

Inclusive growth is progressing the diverse patterns, backgrounds, and sectors of an economy. As an equitable economy has more potential for prosperity so reducing the inequalities and enhancing the productivity of workers in all the sectors of the economy is a core concern for emerging policies. Sectoral interlinkages and patterns of production are the basis for economic growth and essential for welfare outcomes. Therefore, the study analyzes the sectoral integration of Pakistan and Indonesian economies using the dataset from 1980 to 2019. For this purpose, the productive efficiency of workers is focused on three major sectors of economies i.e., services, manufacturing, and agriculture sector. In this study, we have used the VAR model to assess the integration and causal relationship among sectors and found that the per capita value addition of labor is relatively higher in the manufacturing sector of Pakistan and Indonesia. More than 36 percent of employed labor is in the agriculture sector of Pakistan but it has a slow growth rate of only 0.97 percent in 2019. Indonesia has the second-highest employment in the agriculture sector (i.e., 3.6 percent) but the lowest per capita value-added. This indicates slow development and high deprivations in the agriculture sector of both economies particularly in terms of opportunities. The services sector of Pakistan is categorized as a major sector in terms of employment with the highest growth rate that is approximately 3.7 percent whereas the Indonesian services sector has also employed a large share of total employment i.e., 48.9 percent in 2019. But it is found that the value-added production of Indonesia has been lower in services than in the industrial sector. We found a positive association of the services sector with agriculture is found in both economies but there is a negative relationship between agriculture and industry for Pakistan. Therefore, it is suggested to focus the skill development programs aligned with sectoral requirements and provide incentives for efficient allocation of employment across sectors to get the benefits of growth in a broad base.

BackgroundMany carcinogenic chemicals are still used or produced in several economic sectors. The aim of this study is to investigate differences in occupational exposure patterns to carcinogens by gender in Italy.MethodsInformation about the most common carcinogens recorded in the Italian occupational exposures database (SIREP) for the period 1996–2015 was retrieved. Descriptive statistics were calculated for exposure-related variables (carcinogenic agent, occupational group, economic activity sector, and workforce size). The chi-square(χ2) test was used to verify differences between genders, and logistic regression analysis was performed to evaluate the association between gender and risk of having higher exposure levels, after adjusting for age. Concurrent exposures to multiple carcinogens were investigated using the two-step cluster analysis.ResultsA total of 166,617 exposure measurements were selected for 40 different carcinogens. Exposed workers were only in a small proportion women (9%), and mostly aged 20–44 years (70%) in both genders. Women were more likely to be exposed than men to higher levels for several carcinogens even after correction for age at exposure, and the exposure level was significantly (p < 0.01) associated with occupation, economic sector and workforce size. The five main clusters of co-exposures identified in the entire dataset showed a differential distribution across economic sectors between genders.ConclusionsThe exposures to occupational carcinogens have distinguishing characteristics in women, that are explained in part by work and job segregation. Because of the presence of high-exposed groups of female workers in many industrial sectors, further research and prevention efforts are recommended.

Among the economic sectors in Bangladesh, agriculture sector is the most important economic sector. The contribution of agriculture sector to GDP is about 22.25%. So, Agriculture sector influences the development of national economy. The research aims to analyze the comparative contribution of agriculture sector, the impediment factors in agriculture sector and to provide the recommendation for development of agriculture sector. A sample of ten years’ data is taken from 2000–01 to 2009–10 for analyzing the contribution of economic sectors and growth rate of each sector viz. service, industry and agriculture. The growth rate of agriculture sector (trend) is shown by graphical presentation. The average growth rate of agriculture sector has been compared with industry sector, service sector & total GDP using student's’ ‘t’ test. The average contribution of service sector, industry and agriculture sectors are 49.33%, 28.42%, 22.25% respectively. The growth rate of service sector, industry sector and agriculture sector are 6.17%, 7.49% and 3.21% respectively. For the given period the growth rate of agriculture sector is found to be lower than service sector and industry sector. The average employment in Agriculture, Industry, Service to total employment are 58.89%, 12.39% and 25.36% respectively. The paper provides the strategies for the development of agriculture sectors.

Control charts are customarily developed under the assumption of normal quality characteristics to be monitored. However, in many real dataset applications, the normality assumption is not easy to hold. The in-control (IC) robustness of the charting schemes has significant importance for the valid out-of-control (OOC) performance. This article intends to investigate the IC robustness of the unbiased-function-based adaptive cumulative sum (ACUSUM) chart and nonparametric ACUSUM (NPACUSUM) chart against the non-normal process distributions including symmetrical, skewed, and contaminated normal distributions. The OOC run length profiles of the ACUSUM and the proposed NPACUSUM charts for the individual measurements against the non-normal distributions are also a part of this study. The run length profiles of the proposed charting schemes have been computed using the Monte Carlo simulation method. The artificial datasets have been taken from some symmetric and skewed distributions to implement the proposals. An electrical engineering dataset has also been taken for the implementation of the proposal on a real dataset.

Sectoral growth and carbon dioxide emission in Africa: can renewable energy mitigate the effect?