Using Analysis of Variance and Factor Analysis for the Reduction of High Dimensional Variation in Time Series of Energy Consumption

Summary: In this paper the complexity of high dimensional data with cyclical variation is reduced using analysis of variance and factor analysis. It is shown that the prediction of a small number of main cyclical factors is more useful than forecasting all the time-points separately as it is usually done by seasonal time series models. To give an example for this approach we analyze the electricity demand per quarter of an hour of industrial customers in Germany. The necessity of such predictions results from the liberalization of the German electricity market in 1998 due to legal requirements of the EC in 1996.     

The Effects of Ignoring Level Shifts on Systems Cointegration Tests

Summary: In this paper I analyse the effects of ignoring level shifts in the data generating process on systems cointegration tests that do not accommodate level shifts. I consider two groups of Likelihood Ratio tests based on procedures suggested by Johansen (1988) and Saikkonen and Lütkepohl (2000b). The Monte Carlo analysis reveals that ignoring level shifts reduces the tests’ sizes to zero and causes an important drop in the small sample power for increasing shift magnitudes. This suggests that one should apply test procedures, which take account of level shifts. * This paper is a revised and summarized version of Chapter 3 of my PhD thesis (Trenkler, 2002). I would like to thank two anonymous referees for helpful comments on the submitted paper. Furthermore, I am grateful to Christian Müller, Ralf Brüggemann, and Helmut Lütkepohl for many useful suggestions and comments on an earlier version of the paper and the corresponding chapter of my thesis. The research was supported by the Deutsche Forschungsgemeinschaft (DFG) through the SFB 373 “Quantification and Simulation of Economic Processes” and the SFB 649 “Economic Risk”.     

Mapping of population density

The Bureau of the Census listing of geographical coordinates of centroids of all enumeration districts together with population counts from the U. S. 1970 Census of Population was used to contruct via computer five nationwide geographical grids of population density with sector dimensions of 0.01, 0.02, 0.04, 0.1, and 0.25 degrees of latitude and longitude. The entire population of a district was assigned to a grid sector if the coordinates of the district centroid fell within the boundaries of the sector. The sectors were then rank-ordered according to population density, and listings were made of sector population, population density, geographical location, cumulative population, area of sector, and cumulative area. The five sets of data were synthesized into single equations describing population as a function of density in one case and of area in another. From these data it was found, for example, that about 800,000 people live in 19 sectors of 0.01-degree dimensions with a population density of 100,000 people per square mile or greater (nearly all in Manhattan); about 10 million live in 183 sectors of 0.02-degree dimensions with a population density of 23,000 per square mile or greater; and about half of the total U. S. population, that is, about 100 million people, reside within about 0.6 percent of the area of the United States, that is, within 20,000 square miles.Four representative displays of population density are shown for the Northeast Corridor, including isometric views and a contour map.     

Die Gesellschaftliche Akzeptanz der Sozialhilfe

This article examines on which grounds the German population is willing to support a social policy program targeted towards minorities such as social assistance. Using our own survey data and applying linear regression analysis, we test several hypotheses concerning the influence of self-interest, justice- orientations, and victim-blaming attitudes towards welfare recipients on two indicators of support for social assistance. A central finding is that the effects can be interpreted in line with the concept of a “moral economy”, in that the justice orientations of the respondents as well as their attitudes towards welfare recipients correspond with the norms incorporated in the institutional architecture of social assistance.     

Terror as potentiality – the affective rhythms of the political

ABSTRACT

The paper addresses the ways in which the cultural, the affective and the political intersect, counter and/or feed upon one another in the context of contemporary terror. Initially, building upon Machiavelli and Hobbes, we deal with the political significance of terror (and the fear it provokes), emphasizing its potentiality, which inscribes future within the present. Then we turn to an analysis of terror in the prism of securitization. Terror, in this respect, amounts to de-materialization (the enemy as spectre), de-temporalization (the erasure of the temporal difference between the present and the future), and de-territorialisation the breakdown of the distinctions between ‘inside’ and ‘outside’. Following this, we observe how these three processes are dealt with at the subjective and objective (social) levels. Regarding the first, subjective, level we differentiate three attitudes as paranoid, panic and rational. Regarding the latter, we consider terror in terms of accident, risk and catastrophe. Then, discussing the rhythmic relations between these conceptualizations and their spatio-temporal consequences, we focus on the notion of catastrophe. We end with articulating the aporias emerging in this context     

Computing AIC for black-box models using generalized degrees of freedom: A comparison with cross-validation

Generalized degrees of freedom (GDF), as defined by Ye (1998 Ye, J. (1998). On measuring and correcting the effects of data mining and model selection. Journal of the American Statistical Association 93(441):120–131. [Google Scholar] JASA 93:120–131), represent the sensitivity of model fits to perturbations of the data. Such GDF can be computed for any statistical model, making it possible, in principle, to derive the effective number of parameters in machine-learning approaches and thus compute information-theoretical measures of fit. We compare GDF with cross-validation and find that the latter provides a less computer-intensive and more robust alternative. For Bernoulli-distributed data, GDF estimates were unstable and inconsistently sensitive to the number of data points perturbed simultaneously. Cross-validation, in contrast, performs well also for binary data, and for very different machine-learning approaches.     

The forgotten half: analysing the politics of welfare services

Jensen C. The forgotten half: analysing the politics of welfare services Int J Soc Welfare 2011: 20: 404–412 © 2010 The Author(s), International Journal of Social Welfare © 2010 Blackwell Publishing Ltd and the International Journal of Social Welfare. This article discusses the welfare state and argues that the service component has been neglected in the mainstream literature. A main reason for the neglect is the lack of theorising on the distinction between the politics of welfare services and the politics of transfers. An analytical framework that may help overcome this problem is presented.