Performance of methods to conduct mediation analysis with time-to-event outcomes

Previous studies have discouraged the use of the Cox proportional hazards (PH) model for traditional mediation analysis as it might provide biased results. Accelerated failure time (AFT) models have been proposed as an alternative for Cox PH models. In addition, the use of the potential outcomes framework has been proposed for mediation models with time-to-event outcomes. The aim of this paper is to investigate the performance of traditional mediation analysis and potential outcomes mediation analysis based on both the Cox PH and the AFT model. This is done by means of a Monte Carlo simulation study and the illustration of the methods using an empirical data set. Both the product-of-coefficients method of the traditional mediation analysis and the potential outcomes framework yield unbiased estimates with respect to their own underlying indirect effect value for simple mediation models with a time-to-event outcome and estimated based on Cox PH or AFT.     

Hedonic price models and indices based on boosting applied to the Dutch housing market

We create a hedonic price model for house prices for six geographical submarkets in the Netherlands. Our model is based on a recent data-mining technique called boosting. Boosting is an ensemble technique that combines multiple models, in our case decision trees, into a combined prediction. Boosting enables capturing of complex nonlinear relationships and interaction effects between input variables. We report mean relative errors and mean absolute error for all regions and compare our models with a standard linear regression approach. Our model improves prediction performance by up to 39% compared with linear regression and by up to 20% compared with a log-linear regression model. Next, we interpret the boosted models: we determine the most influential characteristics and graphically depict the relationship between the most important input variables and the house price. We find the size of the house to be the most important input for all but one region, and find some interesting nonlinear relationships between inputs and price. Finally, we construct hedonic price indices and compare these with the mean and median index and find that these indices differ notably in the urban regions of Amsterdam and Rotterdam. Copyright © 2008 John Wiley & Sons, Ltd.     

Turning over Turnover

This article applies the methodology of Bai and Ng (2002, 2004)for decomposing panel data into systematic and idiosyncraticcomponents to both stock returns and turnover panels. This approachworks well for both returns and turnover, despite the presenceof severe heteroscedasticity and nonstationarity of individualstocks' turnover. We test the mutual fund separation model ofLo and Wang (2000). Trading due to systematic risk in returnscan account for 66% of systematic turnover. Thus, portfoliorebalancing due to systematic risk is a very important motivefor stock trading. Finally, several common turnover measuresmay understate the impact of stock trading.     

The relationship between cost system complexity,purposes of use,and cost system effectiveness

This paper uses survey data from 133 Dutch, medium-sized manufacturing firms to examine the associations between cost system complexity (in terms of the applied overhead absorption procedures), purposes of use, and cost system effectiveness. First, factor analysis identifies two underlying dimensions of cost system purposes of use, which refers to the range (scope) of purposes for which the cost system is used, among nine widely used purposes: cost system usage for product planning and cost management purposes. Next, the joint effect of cost system complexity and usage for product planning and cost management purposes on cost system effectiveness, as proxied by the intensity of use of and level of satisfaction with the cost system, is examined. The results robustly indicate that at higher (lower) levels of usage for product planning purposes, cost system complexity negatively (positively) affects cost system intensity of use, while at higher (lower) levels of usage for cost management purposes, cost system complexity positively (negatively) affects cost system intensity of use and satisfaction. This implies that when cost system design (i.e., its level of complexity) and its purposes of use are better aligned, the cost system is more effective.     

Surges and stops in greenfield and M&A FDI flows to developing countries: analysis by mode of entry

This paper investigates the factors associated with foreign direct investment “surges” and “stops”, defined as sharp increases and decreases, respectively, of foreign direct investment inflows to the developing world and differentiated based on whether these events are led by waves in greenfield investments or mergers and acquisitions. Greenfield-led surges and stops occur more frequently than mergers-and-acquisitions-led ones and different factors are associated with the onset of the two types of events. Global liquidity is the factor significantly and positively associated with a surge, regardless of its kind, while a global economic growth slowdown and a surge in the preceding year are the main factors associated with a stop. Greenfield-led surges and stops are more likely in low-income countries and mergers-and-acquisitions-led surges are less likely in resource-rich countries than elsewhere in the developing world. Global growth accelerations and increases in financial openness, domestic economic and financial instability are associated with mergers-and-acquisitions-led surges but not with greenfield-led ones. These results are particularly relevant for developing countries where FDI flows are the major type of capital flows and suggest that developing countries’ macroeconomic vulnerability increases following periods of increased global liquidity. As countries develop they typically become more exposed to merger-and-acquisition-led surges, which are more likely than greenfield-led surges and stops to be short-lived and associated with domestic macroeconomic policies.     

Random incentive systems in a dynamic choice experiment

Experiments frequently use a random incentive system (RIS), where only tasks that are randomly selected at the end of the experiment are for real. The most common type pays every subject one out of her multiple tasks (within-subjects randomization). Recently, another type has become popular, where a subset of subjects is randomly selected, and only these subjects receive one real payment (between-subjects randomization). In earlier tests with simple, static tasks, RISs performed well. The present study investigates RISs in a more complex, dynamic choice experiment. We find that between-subjects randomization reduces risk aversion. While within-subjects randomization delivers unbiased measurements of risk aversion, it does not eliminate carry-over effects from previous tasks. Both types generate an increase in subjects’ error rates. These results suggest that caution is warranted when applying RISs to more complex and dynamic tasks.     

The challenge of using standard contracts in public–private partnerships

A call for an increased use of standard contracts in public–private partnerships (PPPs) for infrastructure development is noticeable in practice. These contracts are expected to simplify and improve procurement by creating opportunities for learning, lower transaction costs, and better competition. This paper delineates standard contracts in PPP as a new venue for research and unfolds their potential impact. Here lies an important challenge since the benefits of standardization are not as straightforward as they look at first sight, particularly when taking into account the tension between the powerful, control-oriented role of contracting authorities and the need for contingent, informal contracting.     

Gaming the future of an urban network

Scenario and gaming techniques have a number of complementary characteristics. In this article, the design and evaluation of a gaming-scenario experiment for the exploration of development planning in an urban network in the Netherlands is presented. Two gaming sessions were held using two long-term scenarios (2030) as varying contexts. The combined gaming-scenario approach made it possible to evaluate the impact of external future developments and trends on the administrative and spatial development. Evaluation results of the gaming experiment indicate that the gaming-scenario approach generated new and critical insights on development planning and the future of the urban network. Through the game, the principal, the game leaders but most of all the stakeholder-participants experienced and realized that the management of development planning in urban networks is a very difficult task and is full of pitfalls.     

Economic valuation of habitat defragmentation: A study of the Veluwe, the Netherlands

This paper offers an economic value assessment of a nature protection programme in the Veluwe, the Netherlands. This programme involves two defragmentation scenarios: the first scenario connects the central part of the Veluwe with river forelands in a north-eastern direction (i.e. the meadows of the IJssel river), while the second scenario is focussed on defragmentation in a south-western direction (i.e. the meadows of the Rhine river). The valuation is based on a questionnaire that was administered during face-to-face interviews in the area and through the Internet. We employ a contingent valuation approach to assess the respondents' willingness to pay for the realisation of the defragmentation scenarios. It appears that the mean willingness to pay (WTP) for the two defragmentation scenarios is € 162.2 (lognormal distribution) per respondent. Because the Veluwe is considered a nature park of national importance, we performed an aggregation of individual WTP estimates over Dutch households. With the resulting aggregate estimates we can compare the total costs and benefits of the two scenarios for habitat defragmentation in the Veluwe. In addition, we test whether respondents value the two scenarios equally. We also check whether the methods of data collection (face-to-face interviews and Internet questionnaires) have distinct influences on the stated WTP responses.