Band 15, Heft 1

The 2020 Decennial Census garnered unprecedented attention due to the proposed reintroduction of the citizenship question by the Trump Administration. The legal imperative to respond to the Census and the sensitive nature of the citizenship question led to tensions and public outrage. This paper discusses the controversy surrounding the addition of the citizenship question and its implications on vulnerable communities, particularly undocumented immigrants and communities of color. Although the citizenship question was ultimately not added to the 2020 Decennial Census, it continued to be asked on the American Community Survey (ACS). We examine how negative public sentiment during this time, in tandem with historical mistrust of government data collection, may have manifested as item non-response within the ACS, specifically on questions relating to citizenship status and, more broadly, the Origin and Language subgroup of questions. The analyses in this paper explore trends in non-response rates from the American Community Survey from 2014 to 2022. Item allocation rates are used as a proxy for non-response to questions relating to citizenship. A variety of data visualization tools, supported by statistical methods, are employed to weave connections between allocation trends and the proposed addition of the citizenship question to the Decennial Census. We aim to bring transparency to this issue to educate and encourage response within vulnerable communities by emphasizing the importance of accurate data collection and positive perceptions of government-issued surveys, which are used to make key legislative decisions and create a more democratic nation.

Local statistics are in high demand in almost all countries due to their relevance for public policy monitoring and evaluation, decision-making, and strategic planning. However, traditional sources of local statistics, such as general censuses, administrative statistics, and national and local surveys, have limitations. This has led to the development of several techniques for estimating parameters over small areas. In this article, we use both spatial and non-spatial estimators for small domains to estimate the local employment rate of women in Algeria. We find that the empirical spatial estimator is the most appropriate and efficient estimator as more spatial correlations are considered. We also find that an approach based on the combination of spatial and non-spatial small area estimators is very beneficial because it allows for obtaining efficient estimates with lower Root Mean Squared Errors (RMSEs). This finding is significant for Algeria and similar countries, where traditional sources of local statistics are limited. The combination of spatial and non-spatial estimators can provide more accurate and reliable estimates of local statistics, which can be used to inform public policy and decision-making.

Information Communication Technology (ICT) literacy is essential in the digital age, and an important channel to acquire essential ICT skills is science education. Gender gap in ICT literacy and the associated reasons remain under-explored, especially at macro level. Using country level data from the database of Sustainable Development Goals (SDGs), this article explores the association between infrastructure and gender disparity in ICT literacy, both have direct relationship with science education. SDG Indicator 4.5.1 monitors the female/male ratio of acquiring the ability to use basic arithmetic formula in a spreadsheet (ARSP) at country level, which is selected into this article to measure gender disparity in ICT literacy. SDG Indicator 9.c.1 (the population coverage of 4G mobile network) is used to measure infrastructure development. SDG Indicator 4.4.1, monitors the percentage of population with ARSP skills, which also demonstrates the level of science education, is controlled as an independent variable. Linear regressions and correlations were conducted to explore the relationship between infrastructure and gender gap in ICT literacy in 30 countries, and Mann-Whitney U test was performed to conduce comparisons between high income and middle/low income countries. Infrastructure contributes to reduce gender gap in ICT literacy, because infrastructure can improve a country’s science education which can benefit both men and women’s ICT skills. However such influence may vary across countries. Reasons of the results were discussed with implications for policies.

This study investigated four trend analysis models namely; linear, quadratic, semi log linear and semi log quadratic to study the pattern of live births registration in the Northern Region of Ghana. The study revealed that Semi log linear trend model is the best trend model for studying the pattern of live births registration in the Northern Region of Ghana based on AIC and BIC criteria. The study further fitted four existing fuzzy time series (FTS) models for forecasting live births registration in the Northern Region of Ghana. The Chen, Singh, Heuristic and Chen-Hsu models are the four models used to analyze the data.

Normality, in the colloquial sense, has historically been considered an aspirational trait, synonymous with ideality. The arithmetic average and, by extension, statistics including linear regression coefficients, have often been used to characterize normality, and are often used as a way to summarize samples and identify outliers. We provide intuition behind the behavior of such statistics in high dimensions, and demonstrate that even for datasets with a relatively low number of dimensions, data start to exhibit a number of peculiarities which become severe as the number of dimensions increases. Whilst our main goal is to familiarize researchers with these peculiarities, we also show that normality can be better characterized with ‘typicality’, an information theoretic concept relating to entropy. An application of typicality to both synthetic and real-world data concerning political values reveals that in multi-dimensional space, to be ‘normal’ is actually to be atypical. We briefly explore the ramifications for outlier detection, demonstrating how typicality, in contrast with the popular Mahalanobis distance, represents a viable method for outlier detection.