Using a Box–Cox transformation in the analysis of longitudinal data with incomplete responses

We analyse longitudinal data on CD4 cell counts from patients who participated in clinical trials that compared two therapeutic treatments: zidovudine and didanosine. The investigators were interested in modelling the CD4 cell count as a function of treatment, age at base-line and disease stage at base-line. Serious concerns can be raised about the normality assumption of CD4 cell counts that is implicit in many methods and therefore an analysis may have to start with a transformation. Instead of assuming that we know the transformation (e.g. logarithmic) that makes the outcome normal and linearly related to the covariates, we estimate the transformation, by using maximum likelihood, within the Box–Cox family. There has been considerable work on the Box–Cox transformation for univariate regression models. Here, we discuss the Box–Cox transformation for longitudinal regression models when the outcome can be missing over time, and we also implement a maximization method for the likelihood, assumming that the missing data are missing at random.     

THE DISTRIBUTION SECTOR AND THE DEVELOPMENT PROCESS: ARE THERE PATTERNS? YES

Using an increasing returns specification for distribution, an inverted U pattern between the share of distribution in gross domestic product and the level of development is shown to arise. A cross-section time-series data set is constructed and merged with one used to analyze the service sector. In contrast to the rising pattern found for services, an average time-series relation that exhibits an inverted U pattern is established. The empirical results are robust, for example, to choice of functional form and country and time period coverage. A similar pattern is found in the average cross-section (country) relation between distribution and development.     

Nichts genaues weiss man nicht!?

What do voters really know about party platforms and how do they perceive the contents? Are there any relationships between party election platforms and electoral behavior? Despite of much research on parties, there are hardly any answers to these questions. If political parties devise programmes in order to influence political attitudes or electoral behavior, it will be necessary that these programmes are read by people. But it seems to be unclear if and how people do so. This article shows clearly that voters don’t know much about party manifestoes. Still, programmes are more important for voters than many people believe. Programmes are also an important factor for electoral behavior. But there is still a lack of data to get evident results.     

Time and Postmodernism

In this essay we discuss changes in the cultural meaning and significance of time in postmodernism. We begin by examining the experience of time and space in the Middle Ages and its radical alteration following the Renaissance. After a relatively brief period of optimism during the Enlightenment regarding the scientific control over time and space, a new crisis beginning in the mid‐nineteenth century emphasized the increasing disjuncture between external, objective notions of time and the way time was experienced subjectively. We argue that the current literature on time and post‐modernity is best understood in this context, where earlier disequilibriating effects brought about by modern technologies are exacerbated by new developments in transportation and communications technology. Here we discuss the particular effects on topics of interest to social scientists such as changes in notions of personal identity and the effacement of historical time. We conclude with a call for more empirically grounded work on questions concerning time in postmodernism. We lament the paucity of concrete data as well as the excess of useless polemics and recommend several researchers already conducting work in this field.     

“Something More”: The Meanings of Marriage for Religious Couples in America

This study focused on how couples’ beliefs about marriage and religion shape the meanings they find in their marriage. Interviews about connections between religion and marriage were conducted with 57 Christian, Jewish, and Muslim couples in New England and northern California. Qualitative analyses found the major theme, common across faith traditions, was that marriage is a sacred union that is “something more": more than the self, more than the couple, and more than the family unit. To these couples marriage is divine and institutional and a vital support for their relationship. Our findings raise an interesting counterpoint to the current scholarly discourse about the deinstitutionalization and individualization of contemporary marriage. Institutionalized features of marriage may retain their strength in contemporary society as many religious couples, and perhaps many other couples as well, believe marriage is something more than the deinstitutionalized, private relationship that many scholars now see.     

In-house capability and supply chain decisions

This study considers an internal production option for a contractor and analyzes its effect on the supply chain decisions when the contractor has innovated and the subcontractor has an incentive for opportunistic behavior. In contrast to the single disclosure threshold in the benchmark scenario where the contractor lacks in-house capability, we find two thresholds in the referred scenario. When information misappropriation is possible and the contractor has in-house capability, the contractor will organize a coordinated supply chain only when innovations fall between the two thresholds. Compared to the benchmark scenario, in-house capability has a positive effect on the contractor's incentive to innovate and an ambiguous effect on the subcontractor's incentive to invest in the production process. When the contractor needs to incur an extra cost to build in-house capability, the contractor keeps the same levels of investment compared to the case of no additional in-house capability cost, whereas the subcontractor increases the levels of investment. Furthermore, we find that in the presence of potential misappropriation on the part of the subcontractor, the higher the level of in-house capability, the less likely the contractor will be to outsource innovative products that generate higher profitability. This study can explain why firms strategically outsource low-end products and produce high-end products themselves. This study provides new results on the effects of in-house capability on the strategic interactions of parties in supply chains and, hence, on supply chain efficiency.