Asymptotic Theory of Outlier Detection Algorithms for Linear Time Series Regression Models

Outlier detection algorithms are intimately connected with robust statistics that down‐weight some observations to zero. We define a number of outlier detection algorithms related to the Huber‐skip and least trimmed squares estimators, including the one‐step Huber‐skip estimator and the forward search. Next, we review a recently developed asymptotic theory of these. Finally, we analyse the gauge, the fraction of wrongly detected outliers, for a number of outlier detection algorithms and establish an asymptotic normal and a Poisson theory for the gauge.     

Oppositional Girlhoods and the Challenge of Relational Politics

Over the last five years, scholars from a wide variety of disciplines have problematized the discourse of “adolescent female exceptionalism” (Switzer in Fem Theory 14(3):345–360, 2013, p. 4) popularized by the NIKE Foundation’s Girl Effect. Arriving at similar conclusions, scholars point to the artificial neocolonial divisions between ‘the West’ and ‘the rest’ of the world animated by an ‘invest in girls’ logic. This paper endeavors to move beyond the “oppositional girlhoods” (Bent in Sociol Stud Child Youth 16(1):3–20, 2013a, p. 7) bind of girl effects discourse to propose that differentially positioned and experienced girlhoods might be better understood as transnational, relational cultural formations. Drawing from our empirical research with girls in North America and Sub-Saharan Africa, we consider the implications of girls’ increasing global visibility as the ‘saviors of humanity’ from different geopolitical contexts. We then go further to suggest the oppositional girlhoods frame assumes reductive, apolitical, and ahistorical claims of divergence between girlhoods in the Global North and Global South “with highly unequal effects” (Gonick et al. in Girlhood Stud 2(3):1–9, 2009, p. 3). By countering the normative construction of global girlhoods as mutually exclusive forms of personhood and historical experience, our project authorizes a new understanding of girlhoods as mutually constituted and relationally contingent. It is from within this relational framework that we propose new directions for thinking about girlhoods transnationally.     

Your position in society matters for how happy you are

This article shows that people's perception of their position in society is strongly correlated with their level of happiness, and thus that differences in happiness levels among countries in different welfare state clusters are influenced by people's perceptions of their relative position in society (subjective position). The study drew on data from the European Social Survey. Two important findings emerged from the analysis. First, an individual's subjective position in society is a more important predictor of happiness than objective measures such as income, education and labour market position. Second, the link between individuals’ perceived position in society and their level of happiness is moderated by the welfare state. In the Nordic countries, people's perceptions of their position in society have less influence on happiness whereas in Eastern European countries we found a strong connection between subjective position and happiness.     

Simulating Properties of the Likelihood Ratio Test for a Unit Root in an Explosive Second-Order Autoregression

This paper provides a means of accurately simulating explosive autoregressive processes and uses this method to analyze the distribution of the likelihood ratio test statistic for an explosive second-order autoregressive process of a unit root. While the standard Dickey-Fuller distribution is known to apply in this case, simulations of statistics in the explosive region are beset by the magnitude of the numbers involved, which cause numerical inaccuracies. This has previously constituted a bar on supporting asymptotic results by means of simulation, and analyzing the finite sample properties of tests in the explosive region.     

Mexican Immigrants,Labour Market Assimilation and the Current Population: The Sensitivity of Results Across Seemingly Equivalent Surveys

In this paper we compare estimates of immigrants’ labour supply assimilation profiles using the Current Population Survey Annual Demographic Files (March ADS) and the Current Population Survey Outgoing Rotation Groups (ORGs). We use a measure that is seemingly consistent across both surveys: usual weekly hours of work in the main job. This measure is not only important as it measures the intensive margin of labour supply, but it is also used to estimate hourly earnings in both surveys. Our results indicate that the two surveys produce dramatically different estimates of the change in average hours of work as immigrants’ years in the United States increase: estimates from the March ADS predict much steeper hour's assimilation profiles than do estimates obtained from the ORGs. These differences persist if we include controls for demographic characteristics, and only disappear once we control for occupation heterogeneity. We argue that these differences stem from two separate factors that differentiate the data. First, the ADS and ORG frame the usual “hours worked” question differently. Also, differences in the timing of the surveys may produce seasonality effects that differentially affect the composition of recent and earlier migrants, thereby changing assimilation profiles.     

Newcomb's problem: Recalculations for the one-boxer

Theory and Decision -     

Asymptotic Inference on Cointegrating Rank in Partial Systems

The likelihood ratio test for cointegrating rank is analyzed for partial (or conditional) systems in the vector autoregressive error-correction model. Under the assumption of weak exogeneity for the cointegrating parameters, the asymptotic distributions are given and tables of critical values are provided. A discussion is given of some of the assumptions of the model, why they are needed, and how they are tested.     

On the Distribution of Likelihood Ratio Test Statistics for Cointegration Rank

This paper analyses the likelihood ratio test for the hypothesis of reduced cointegration rank in a Gaussian vector autoregressive model. The usual asymptotic distribution typically gives rather large size distortions. This is explained by the fact that the asymptotic distribution of the likelihood ratio test statistic varies across the parameter space. A much improved distribution approximation can be obtained using local asymptotic theory. The idea is discussed for some low dimensional examples.