Robust Designs in Generalized Linear Models: A Quantile Dispersion Graphs Approach

This article studies design selection for generalized linear models (GLMs) using the quantile dispersion graphs (QDGs) approach in the presence of misspecification in the link and/or linear predictor. The uncertainty in the linear predictor is represented by a unknown function and estimated using kriging. For addressing misspecified link functions, a generalized family of link functions is used. Numerical examples are shown to illustrate the proposed methodology.     

Correlated random effects regression analysis for a log-normally distributed variable

In regression analysis, it is assumed that the response (or dependent variable) distribution is Normal, and errors are homoscedastic and uncorrelated. However, in practice, these assumptions are rarely satisfied by a real data set. To stabilize the heteroscedastic response variance, generally, log-transformation is suggested. Consequently, the response variable distribution approaches nearer to the Normal distribution. As a result, the model fit of the data is improved. Practically, a proper (seems to be suitable) transformation may not always stabilize the variance, and the response distribution may not reduce to Normal distribution. The present article assumes that the response distribution is log-normal with compound autocorrelated errors. Under these situations, estimation and testing of hypotheses regarding regression parameters have been derived. From a set of reduced data, we have derived the best linear unbiased estimators of all the regression coefficients, except the intercept which is often unimportant in practice. Unknown correlation parameters have been estimated. In this connection, we have derived a test rule for testing any set of linear hypotheses of the unknown regression coefficients. In addition, we have developed the confidence ellipsoids of a set of estimable functions of regression coefficients. For the fitted regression equation, an index of fit has been proposed. A simulated study illustrates the results derived in this report.     

Sparrows in urban complexity: macro and micro-scale habitat use of sympatric sparrows in Guwahati City,India

In recent decades the House Sparrow and Tree Sparrow have suffered considerable declines. To date, little is known about the fine scale habitat selection of sparrows where they occur together. We investigated how sympatric sparrows used macro and microhabitats in the urban environment of Guwahati city. Survey of sparrows was carried out in 572 locations of different urban settings to find out the city scale distribution. We classified urban habitats and collected micro-habitat variables at 45 point count stations during 2013–2015. Urbanization gradient was found to be influential in limiting the abundance of sparrows. House Sparrow was more common within the urbanized areas compared to low settlement densities located far from the urban core. In contrast, Tree Sparrows were more scattered and seldom found in crowded areas. Spatial overlap was comparatively high in the residential areas adjacent to hillocks. At micro scale, House Sparrow had quadratic response to the degree of urbanization. Both the species avoided areas where urbanization reached the peak; specifically, the areas which were completely devoid of natural vegetation and top soil was paved, and in shopping centers with glass facades. Habitat requirements of both the species at local landscape scale seemed to be similar, although, with some overlaps, they occupied different gradients of the urban environment. Since urban landscapes are highly managed, the fundamental tool for enhancing urban sparrow populations would be the protection of mosaic habitat prioritizing suitable design and management of private gardens and allotments.

     

Optimum covariate designs in partially balanced incomplete block (PBIB) design set-ups

The use of covariates in block designs is necessary when the covariates cannot be controlled like the blocking factor in the experiment. In this paper, we consider the situation where there is some flexibility for selection in the values of the covariates. The choice of values of the covariates for a given block design attaining minimum variance for estimation of each of the parameters has attracted attention in recent times. Optimum covariate designs in simple set-ups such as completely randomised design (CRD), randomised block design (RBD) and some series of balanced incomplete block design (BIBD) have already been considered. In this paper, optimum covariate designs have been considered for the more complex set-ups of different partially balanced incomplete block (PBIB) designs, which are popular among practitioners. The optimum covariate designs depend much on the methods of construction of the basic PBIB designs. Different combinatorial arrangements and tools such as orthogonal arrays, Hadamard matrices and different kinds of products of matrices viz. Khatri–Rao product, Kronecker product have been conveniently used to construct optimum covariate designs with as many covariates as possible.     

A Variable Selection Criterion in the Linear Programming Approaches to Discriminant Analysis*

There are numerous variable selection rules in classical discriminant analysis. These rules enable a researcher to distinguish significant variables from nonsignificant ones and thus provide a parsimonious classification model based solely on significant variables. Prominent among such rules are the forward and backward stepwise variable selection criteria employed in statistical software packages such as Statistical Package for the Social Sciences and BMDP Statistical Software. No such criterion currently exists for linear programming (LP) approaches to discriminant analysis. In this paper, a criterion is developed to distinguish significant from nonsignificant variables for use in LP models. This criterion is based on the “jackknife” methodology. Examples are presented to illustrate implementation of the proposed criterion.     

Enrollment,Educational Expenditures and Work Among One-Parent Children in India

In this study, I examined the effect of single parenthood due to death, separation, divorce, or migration of spouse on educational inputs among school-age children in India. I used the nationally representative India Human Development Survey to study the implications of different types of parenthood on educational expenditure among children ages 6 to 11 and 12 to 18 years and work participation among the older age group. The study finds that the separated or divorced mothers on average spend less on education and older children of widows are more likely to work because of resource constraints associated with single parenthood. The results highlight the need for public policies that would support widows as well as separated or divorced mothers.     

Comparing Social Work Students’ Perceptions of Risk Using Online Discussion Fora: Lessons Learned from a European Pilot Project

Comparisons of international child welfare systems have identified two basic orientations to practice; a ‘child protection’ orientation and a ‘child welfare’ orientation, which are founded upon fundamentally different values and assumptions regarding the family, the origins of childcare problems, and the proper role of the state in relation to the family. This paper describes a project which sought to compare how undergraduate social work students from three European Universities perceive risk in referrals about the welfare of children and to explore the impact of different cultural, ideological and educational contexts on the way in which risk is constructed by students. Students from Northern Ireland, Germany and Poland examined three vignettes via 10 online discussion fora each of which provided a narrative summary of their discussion. The paper presents some findings from the analysis of the qualitative data emerging from the student discussions and draws out the lessons learned in terms of how the project was designed and implemented using online discussion fora.     

Social Support and its Correlation with Loneliness and Subjective Well-being: A Cross-cultural Study of Older Nepalese Adults

Population aging in Nepal is a recent phenomenon, due more to demographic changes than to socio-economic development. The study had three goals: to analyze the social support exchange among elderly men and women; to discover the main sources of support in loneliness and subjective well-being in the elderly; and to study the cross-cultural differences in support among elderly Chhetri ( N  = 137, mean age = 69.1 [7.2] years) and Newar people ( N  = 195, mean age = 68.8 [7.7] years) in one ward in Kathmandu. The data were collected using face-to-face interviews. The dependent variables were loneliness and subjective well-being (SWB). The results for both ethnic Chhetri and Newar respondents show that their major support comes from their children living in the same household and their spouses. I conclude that the sources of social support and social support exchange are similar between the two castes/ethnicities and that there are no cross-cultural differences between them in terms of support for loneliness and SWB-life stability, although there are cross-cultural differences in their SWB-life satisfaction. Providing social support to friends and neighbors appears to be related to less loneliness and increased SWB in both castes/ethnicities.     

An infinite class of PBIB designs

In this paper, an infinite class of partially balanced incomplete block (PBIB) designs of m+1 associate classes is constructed through the use of a series of row-orthogonal matrices known as partially balanced orthogonal designs (PBOD) of m-associate classes. For the purpose, a series of PBOD is obtained through a method described herein. An infinite class of regular GD designs is also reported.