Confidence Intervals of Weighted Kappa Coefficient of a Binary Diagnostic Test

Sensitivity and specificity are classic parameters to assess the performance of a binary diagnostic test. Another useful parameter to measure the performance of a binary test is the weighted kappa coefficient, which is a measure of the classificatory agreement between the binary test and the gold standard. Various confidence intervals are proposed for the weighted kappa coefficient when the binary test and the gold standard are applied to all of the patients in a random sample. The results have been applied to the diagnosis of coronary artery disease.     

Longitudinal Patterns of Nonresident Fathers’ Involvement: The Role of Resources and Relations

Using data from the Fragile Families and Child Wellbeing Study, we examined patterns of nonresident father involvement 1 and 3 years after a nonmarital birth (N = 893). Cluster analyses were used to determine patterns of involvement across different father behaviors. About half of fathers displayed low involvement when children were 1 and 3 years old, one fourth of fathers maintained high involvement, and equal remaining proportions increased or decreased involvement over time. Multinomial logistic analyses indicated that better relationships between parents were associated with consistently high versus low involvement. Better relationships with each others’ extended family also predicted remaining highly involved and increasing involvement over time. Parents’ romantic relationship status was closely associated with patterns of involvement.     

Bias correction for time series factor models

In this paper we work with multivariate time series that follow a Factor Model. In particular, we consider the setting where factors are dominated by highly persistent AutoRegressive (AR) processes and samples that are rather small. Therefore, the factors' AR models are estimated using small sample bias correction techniques. A Monte Carlo study reveals that bias-correcting the AR coefficients of the factors allows to obtain better results in terms of prediction interval coverage. As expected, the simulation shows that bias-correction is more successful for smaller samples. We present the results assuming the AR order and number of factors are known as well as unknown. We also study the advantages of this technique for a set of Industrial Production Indexes of several European countries.     

Language in the process of labour market rationalisation: A sociohistorical approach across twentieth-century Spain

This article analyses the role of linguistic skills in the process of defining professional classifications in Spain during 1919–1980. The aim is to determine the social evaluation of the skills involved. To retrace the classifications, a total of 114 official documents were examined, establishing a chronological division into three major stages: 1920–1940, 1940–1960 and 1960–1980. The first period (1920–1940) shows efforts toward the initial objectification of working conditions and salary scales, revealing social prejudices and tacit conventions shaping the employment hierarchy, while the second one (1940–1960) indicates the extent to which office work stood out over manual work. Finally, the third stage (1960–1980) shows processes of language rationalisation, which entailed attempts to standardise positions based on required skill sets.