Estimating stochastic volatility models using integrated nested Laplace approximations

Volatility in financial time series is mainly analysed through two classes of models; the generalized autoregressive conditional heteroscedasticity (GARCH) models and the stochastic volatility (SV) ones. GARCH models are straightforward to estimate using maximum-likelihood techniques, while SV models require more complex inferential and computational tools, such as Markov Chain Monte Carlo (MCMC). Hence, although provided with a series of theoretical advantages, SV models are in practice much less popular than GARCH ones. In this paper, we solve the problem of inference for some SV models by applying a new inferential tool, integrated nested Laplace approximations (INLAs). INLA substitutes MCMC simulations with accurate deterministic approximations, making a full Bayesian analysis of many kinds of SV models extremely fast and accurate. Our hope is that the use of INLA will help SV models to become more appealing to the financial industry, where, due to their complexity, they are rarely used in practice.     

Co‐owned Local Government Organisations: Conditions for Strategy Development

Local governments tend to join resources and create co‐owned organisations to solve the supply of public services. From a strategic perspective on local government cooperation, this paper analyses the conditions for strategy development in a co‐owned municipal organisation. The empirical data stem from a longitudinal case study of a Swedish provider of water and sewerage services. We show that difficulties in formulating and agreeing upon strategies are not dependent on the structural form. Instead, there is an intrinsic dilemma when municipalities are to create a joint strategy at the same time as each municipality is sovereign to decide on all local matters.     

State history and economic development: evidence from six millennia

The presence of a state is one of the most reliable historical predictors of social and economic development. In this article, we complete the coding of an extant indicator of state presence from 3500 BCE forward for almost all but the smallest countries of the world today. We outline a theoretical framework where accumulated state experience increases aggregate productivity in individual countries but where newer or relatively inexperienced states can reach a higher productivity maximum by learning from the experience of older states. The predicted pattern of comparative development is tested in an empirical analysis where we introduce our extended state history variable. Our key finding is that the current level of economic development across countries has a hump-shaped relationship with accumulated state history.     

Knowledge as a Set in Idea Space: An Epistemological View on Growth

This articlepresents a model of knowledge, seen as a set of ideas definedin a multidimensional idea space. Knowledge is created throughconvex combinations of older ideas and through paradigm shifts.When normal science has made the knowledge set convex, scientificopportunity is exhausted. Individual countries are endowed withdifferent knowledge sets, which gives rise to idea gaps. Thegrowth of a country's knowledge depends on diffusion from othercountries, on own production, and on the state of its human capitaland institutions. In the long run, economic growth will dependon knowledge growth, but only paradigm shifts can save R&Dfrom diminishing returns     

Budesonide with multi-matrix technology as second-line treatment for ulcerative colitis: evaluation of long-term cost-effectiveness in the Netherlands

Aims: Budesonide with multi-matrix technology (MMX) is an oral corticosteroid, shown to have high topical activity against ulcerative colitis (UC) while maintaining low systemic bioavailability with few adverse events. The aim of this study was to evaluate the cost-effectiveness of budesonide MMX versus commonly used corticosteroids, in the second-line treatment of active mild-to-moderate UC in the Netherlands.

Materials and methods: An eight-state Markov model with an 8 week cycle length captured remission, four distinct therapy stages, hospitalization, possible colectomy and mortality. Remission probability for budesonide MMX was based on the CORE-II study. Population characteristics were derived from the Dutch Inflammatory Bowel Disease South Limburg cohort (n?=?598) and included patients with proctitis (39%), left-sided (42%) and extensive disease (19%). Comparators (topical budesonide foam and enema, oral budesonide and prednisolone) were selected based on current Dutch clinical practice. Treatment effects were evaluated by network meta-analysis using a Bayesian framework. Cost-effectiveness analysis was performed over a 5 year time horizon from a societal perspective, with costs, health-state and adverse event utilities derived from published sources. Outcomes were weighted by disease extent distribution and corresponding comparators.

Results: Budesonide MMX was associated with comparable quality-adjusted life year (QALY) gain versus foam and oral formulations (+0.01 QALYs) in the total UC population, whilst being cost-saving (EUR 366 per patient). Probabilistic sensitivity analysis evaluated an 86.6% probability of budesonide MMX being dominant (cost-saving with QALY gain) versus these comparators. Exploratory analysis showed similar findings versus prednisolone.

Limitations: Differing definitions of trial end-points and remission across trials meant indirect comparison was not ideal. However, in the absence of head-to-head clinical data, these comparisons are reasonable alternatives and currently offer the only comparison of second-line UC treatments.

Conclusions: In the present analysis, budesonide MMX was shown to be cost-effective versus comparators in the total UC population, for the second-line treatment of active mild-to-moderate UC in the Netherlands.     

Recombination in the open-ended value landscape of digital innovation

Digital innovation introduces a new open-ended value landscape to anyone seeking to generate or capture new value. To understand this landscape, we distinguish between design recombination and use recombination, explore how they play out together, and redirect the attention from products and services toward digital resources. Digital resources serve as building-blocks in digital innovation, and they hold the potential to simultaneously be part of multiple value paths, offered through design recombination and assembled through use recombination. Building on this perspective, we offer the value spaces framework as a tool for better understanding value creation and capture in digital innovation. We illustrate the framework and offer the early contours of a research agenda for information systems researchers.     

Impacts of Norwegian Milk Quotas on Output Growth: A Modified Distance Function Approach

Quota regulations that prevent output expansion of farms and reallocation of output between farms can cause lower growth in output and productivity. The aim of this study was to explain the output growth rate of Norwegian dairy farms since 1976, and to decompose it into output, input, socioeconomic and technical change components. Instead of using the standard distance function approach for multi‐output technologies, we use a growth rate formulation, which automatically removes the farm‐specific effects. This formulation also helps to impose non‐negativity constraints on marginal products of inputs (input elasticities), which are often violated for many observations, especially when flexible functional forms are used. The farm‐level panel data cover three periods: before the quota scheme was introduced (1976–1982); the period with the most output‐restricting quota scheme (1983–1996); and the period with a more flexible quota scheme (from 1997 onwards). Results show that the milk quota regulations had a significant constraining effect on output growth, in particular on milk output in the period 1983–1996. Furthermore, the output mix has shifted towards meat production for the average farm. What emerges from this study is that output growth and technical change are negatively influenced by policy aims where productive performance has not been the primary objective, and that there is scope for increased farm growth if the quota regime is liberalised.     

Self-enforcing contracts in agriculture

This article examines a self-enforcing contract between a risk-neutralprincipal and a risk-averse agent who is able to hold up valuesex post. It shows that risk aversion and variance can only partlyexplain the contract's incentive intensity. Ex post bargainingpower and outside options will also determine contract choice.If the agent's ex post bargaining position is weak, the principalcannot commit to high-powered incentives, whereas if the agent'sex post bargaining position is good, the agent cannot committo low-powered incentives. The model may thus explain some puzzlesin agricultural contracts, in particular why risk-averse agentssometimes accept to be governed by high-powered incentive contractsthat are quite similar to fixed rental contracts, and why risk-neutralagents are sometimes offered share contracts with lower-poweredincentives.     

Product Innovation in Small and Large Enterprises

Innovation networks, establishment characteristics and the regional environment are likely to play different roles in product innovation in enterprises of different size. This paper focuses on the influence of the regional environment on the early adoption of micro-electronic components in product development in small and medium-sized enterprises (SMEs) and large enterprises (LEs). Drawing upon existing literature we compare the role of enterprise characteristics, innovation networks and, in particular, the regional environment for an early use of micro-electronic components in product development in SMEs and LEs using a tobit model. Our central hypothesis is that SMEs are more dependent upon their regional environment than LEs for an early adoption. However, this hypothesis is rejected by our empirical results that show that location in a large, dense region has a significant positive effect on product innovation in LEs, while it has a negative but non-significant effect on product innovation in SMEs. Our results imply peripheral regions are able to provide an innovative environment for SMEs, whereas LEs need the richer environment offered by the core regions. The results are also interesting from a policy point of view because they indicate that SMEs can be early users of new technologies even if they are located outside the large urban areas.