Frankfurt School of Finance & Management

Missing data is a common issue in structural equation modeling, including partial least squares structural equation modeling, which can lead to biased results and weaker statistical conclusions. Despite the popularity of partial least squares structural equation modeling in multivariate analysis, there is a lack of rigorous handling and reporting of missing data in the literature. Most studies rely on complete case analysis and mean imputation, overlooking modern techniques. Recent works have applied and evaluated modern approaches but lack insights into parameters that influence performance. This paper addresses this gap by evaluating the performance of various imputation methods, including expectation maximization and multiple imputation, through the analysis of simulated datasets with varying sizes and levels of missingness. In contrast to previous works, this study considers the effects of factors such as multivariate distribution and model complexity. The findings provide evidence for the superior performance of donor-based multiple imputation techniques and the impact of properties of data and model. In addition, we present recommendations for researchers on how to effectively manage missing data in partial least squares structural equation modeling, enhancing the reliability and validity of their results.

Variance decomposition approaches are often used to identify key sources of heterogeneity in firm performance. While previous variance decomposition studies have decomposed the drivers of firm performance in product markets (financial performance), we focus on differences in firms' abilities to create the resources that underlie such product market successes. Specifically, we focus on innovation performance. We identify the relative importance of technology area, corporation, business unit, and star inventor effects in determining firms' (1) innovation output, (2) innovation social value, (3) innovation value appropriation, and (4) innovation financial value. We find, across our four measures of innovation performance, the business unit effect is by far the largest (32.6 per cent), followed by the star inventor effect (11.5 per cent), the corporate effect (5.5 per cent), and the technology area effect (1.9 per cent). We discuss the implications of these findings for future innovation studies.

The objective of precision medicine is to tailor interventions to an individual patient’s unique characteristics. A key technology for this purpose involves medical digital twins, computational models of human biology that can be personalized and dynamically updated to incorporate patient-specific data. Certain aspects of human biology, such as the immune system, are not easily captured with physics-based models, such as differential equations. Instead, they are often multi-scale, stochastic and hybrid. This poses a challenge to existing control and optimization approaches that cannot be readily applied to such models. Recent advances in neural-network control methods hold promise in addressing complex control problems. However, the application of these approaches to biomedical systems is still in its early stages. This work employs dynamics-informed neural-network controllers as an alternative approach to control of medical digital twins. As a first use case, we focus on the control of agent-based models (ABMs), a versatile and increasingly common modelling platform in biomedicine. The effectiveness of the proposed neural-network control methods is illustrated and benchmarked against other methods with two widely used ABMs. To account for the inherent stochastic nature of the ABMs we aim to control, we quantify uncertainty in relevant model and control parameters. This article is part of the theme issue ‘Uncertainty quantification for healthcare and biological systems (Part 1)’.

Background The German government has recently drafted a bill proposing a reduction in the prescription threshold for statin use. This study aims to determine the cost-saving risk threshold for statin use in Germany to inform this proposed change. Methods An economic evaluation utilizing a decision-analytic model was performed, using secondary data to compare statin use versus no statin use from the perspective of German sickness fund insurees. The analysis focused on cost savings from avoided cardiovascular (CV) events, translating these avoided events into net savings after accounting for treatment costs and potential side effects. The study considered the German adult population insured by sickness funds and used a lifetime horizon for the analysis. Results The maximum number needed to treat (NNT) to achieve cost savings over 10 years was found to be 39, leading to a minimum CV risk threshold for savings of 10.2%. It was estimated that approximately 19% of the adult population in Germany has a 10-year CV risk of ≥ 10.2%, potentially avoiding between 271,739 and 581,363 CV events over 10 years, with net population savings of approximately €15 billion. Conclusions A threshold for statin prescription in Germany set at a 10.2% 10-year CV risk could significantly increase the number of patients benefiting from statin therapy, reducing CV events and generating substantial cost savings. These findings suggest that adjustments to prescription guidelines could improve cardiovascular outcomes and economic efficiency within the German healthcare system.

Mit der Verschärfung von Berichtspflichten im Bereich der (ökologischen) Nachhaltigkeit sind für Unternehmen unter anderem Herausforderungen verbunden, den CO 2 -Fußabdruck ihrer Produkte (Product Carbon Footprint, PCF) prüfungssicher zu bestimmen. Dazu sind unternehmensinterne und externe Datenquellen zu integrieren. Anhand eines praktischen Beispiels zeigt der Beitrag, wie eine solche PCF-Bestimmung automatisiert und prüfungssicher erfolgen kann.

Aim The aim of this study is to quantify the effectiveness and cost-effectiveness of the outpatient and inpatient sectors (specifically intensive care units, ICUs) and local health departments in managing the first three waves of the COVID-19 pandemic in Germany. Methods The analysis is based on a modelling approach using secondary data. The effectiveness of each sector was measured by determining the reduction in the case fatality rate (CFR) of COVID-19 patients by May 7, 2021. A counterfactual scenario assuming the absence of each sector was used to quantify their effectiveness. Direct medical costs for each sector were calculated from a statutory health insurance perspective, utilizing reimbursement rates for both the inpatient and outpatient sectors. Incremental cost-effectiveness ratios (ICERs) were determined, representing the costs per death avoided. Results The ICUs achieved the greatest reduction in the CFR of COVID-19 patients during the first three waves (1.9%). The outpatient sector followed with a reduction of 1.4%, and the local health departments contributed to a 0.3% decrease in the CFR. In terms of spending, ICUs had the highest expenditures among the sectors, resulting in an ICER of €59,055 per death avoided. On the other hand, local health departments were costlier but less effective than the outpatient sector. Results remained consistent across various input assumptions. Conclusion During the first three waves of the COVID-19 pandemic in Germany, the inpatient sector (ICUs) made the largest contribution to preventing deaths while also incurring the highest costs.

Two weeks after becoming the General Secretary of the CCP in November 2012, Xi Jinping introduced the narrative of the China Dream, which articulates the Two Centenary Goals into a framework, based on national revitalisation, quality of life improvements, and the overall enhancement of China’s international status.

This chapter provides a comprehensive insight into the corporate sector of China’s real and financial economy by covering four areas.

Building on the general description of China’s reform path, this chapter describes and analyses the various reforms over time in detail.

The internationalisation of China’s economy since Reform and Opening Up in 1978 marked the start of what is currently known as globalisation. Since then, China has developed into one of the most open and integrated economies in the world. In terms of trade, it had already become the largest trading nation by 2014. Presently, the country accounts for 15% of global exports and receives 11% of all imports. However, globalisation has been on the retreat since the global financial crisis in 2008, and today, geopolitical fragmentation and economic security are at the top of the agenda.

The structure of China’s economy is unique, as is its economic policy. It has a surprisingly high degree of decentralisation and heterogeneity despite being a centralised party-state. This chapter provides an overview of its most important contemporary features. Some of the key insights are as follows.

Even though China’s economic growth rate saw some substantial volatility in recent years, mainly due to the Covid-19 pandemic, it almost steadily declined since 2008 as shown in Chapter 4. From a purely statistical perspective, this decline can be attributed to the increasing absolute value of China’s GDP. As the GDP increases, the impact of any given change diminishes, naturally reducing the growth rate. For example, 10% growth in 1978 resulted in a GDP expansion of approximately 15 billion USD, whereas the same growth rate in 2022 would require a GDP expansion of approximately 1.7 trillion USD. Thus, the larger the base, the more challenging it becomes to achieve high growth rates.

In the final chapter of this book, we argue that it is unlikely that the dominant policy approach of an innovation-led growth model, guided by the party-state, will be able to move China’s economy back to a sustainable long-term growth path that avoids the middle-income trap. The approach has two significant shortcomings: first, it still underestimates consumption as a growth driver; second, it tends to produce industrial overcapacity instead of the creation of breakthrough innovations. These weaknesses are the inherent result of the steering approach as the preferred economic model of the current policy.

This chapter provides a summary of the development of China’s economic reform trajectory since 1978 until today, in a highly aggregated way.

The relative importance of firm and industry effects, contrasting resource-based and industrial organization theories, is often discussed in the strategy and international business literature. Several studies indicate that firm effects (i.e., variability in firm-specific internal resources) are the primary drivers of competitive differences between firms. Leveraging insights from several theoretical lenses such as location economics, relational strategy, and institutional theory, we argue that considering the micro-geographic locations (neighborhoods) of firms challenges two implicit but potentially unrealistic assumptions in the firm vs. industry effects academic debate: That (a) firm boundaries are clearly defined, and (b) industry effects are spatially homogenous. We argue that including a neighborhood and neighborhood-industry interaction effect is thus more appropriate to contextualize the classic firm vs. industry debate. We demonstrate that firm effects are much smaller than previously identified (e.g., dropping from 43.9 to 11.5%). Our results thus challenge conventional wisdom and established empirical findings, while adding nuance to the fundamental debate regarding the locus of competitive advantage of firms.

Recent years have seen incredible advances in our abilities to gather and store data, as well as in the computational power and methods—most prominently in machine learning—to do things with those data. These advances have given rise to the emerging field “data science.” Because of its immense power for providing practically useful information about the world, data science is a field of increasing importance. This paper argues that a core part of what data scientists are doing should be understood as conceptual engineering. At all stages of the data science process, data scientists need to deliberate about, evaluate, and make classificatory choices in a variety of ways, including as part of training and evaluating machine learning models. Viewing these activities as involved in conceptual engineering offers a new way to think about them, one that helps to clarify what is at stake in them, what sorts of considerations are relevant, and how to systematically think about the choices faced. Given the increasing importance of data science, if conceptual engineering is relevant for activities in data science, this also highlights the relevance and impact of conceptual engineering as a method. Furthermore, the paper also suggests that machine learning opens distinctive and novel ways in which data scientists engage in conceptual engineering.

This paper describes and validates an algorithm to solve optimal control problems for agent-based models (ABMs). For a given ABM and a given optimal control problem, the algorithm derives a surrogate model, typically lower-dimensional, in the form of a system of ordinary differential equations (ODEs), solves the control problem for the surrogate model, and then transfers the solution back to the original ABM. It applies to quite general ABMs and offers several options for the ODE structure, depending on what information about the ABM is to be used. There is a broad range of applications for such an algorithm, since ABMs are used widely in the life sciences, such as ecology, epidemiology, and biomedicine and healthcare, areas where optimal control is an important purpose for modeling, such as for medical digital twin technology.