Narrow your search

Library

KU Leuven (3)


Resource type

book (3)


Language

English (3)


Year
From To Submit

2020 (3)

Listing 1 - 3 of 3
Sort by

Book
Machine learning
Authors: --- --- --- --- --- et al.
ISBN: 1529749212 Year: 2020 Publisher: London : SAGE Publications Ltd.,

Loading...
Export citation

Choose an application

Bookmark

Abstract

Machine learning is a statistical and computational approach to extracting important patterns and trends in data. This entry is an overview of machine learning methods for social science research. It covers supervised learning methods including generalized linear models, support vector machines, naive Bayes, k-nearest neighbor, artificial neural networks and deep learning, decision trees, and ensemble methods. It also notes several important considerations relevant to supervised learning algorithms including the use of training and test data and cross-validation, loss optimization and evaluation metrics, bias-variance trade-off, and overfitting and regularization strategies. The entry also covers unsupervised learning methods, including k-means clustering, hierarchical clustering, network community detection, principal component analysis, and t-distributed stochastic neighbor embedding. A section on text analysis incorporates supervised and unsupervised learning of documents and neural networks. The entry provides an overview of new developments at the intersection of machine learning methods and causal inference. Key limitations and considerations for adopting these methods in empirical social science research conclude the entry.


Book
Gini coefficient
Authors: --- --- --- --- --- et al.
ISBN: 1529749190 Year: 2020 Publisher: London : SAGE Publications Ltd.,

Loading...
Export citation

Choose an application

Bookmark

Abstract

The Gini coefficient (G) is an index for measuring inequality. This entry reviews the use of the G since its appearance in the literature in 1914. It discusses how the Italian statistician Corrado Gini developed it. The entry highlights methodological aspects to explain the various formulas that can be used to calculate the G value and to show the links with the Lorenz curve and the mean difference. It also discusses how some scholars have come to the same results using different formulas of G, depending on the investigated subject. An application to real data is also provided in order to make the use of G simple and immediate. Finally, the extreme topicality of the Gini index is underlined by showing how it is currently used in fields other than economics - such as in archaeology, hydrology, insurance, biomedicine, geosciences, and to evaluate scientific productivity of universities and departments.


Book
Thomas, Dorothy Swaine
Authors: --- --- --- --- --- et al.
ISBN: 1529749158 Year: 2020 Publisher: London : SAGE Publications Ltd.,

Loading...
Export citation

Choose an application

Bookmark

Abstract

Dorothy Swaine Thomas (1899-1977) was a sociologist, demographer, and social statistician. She has been described as "the most successful woman sociologist of her generation" (Bannister, 1998, p. 226). She produced her first publications while still an undergraduate, coauthoring these with William Fielding Ogburn (Ogburn & Thomas, 1922a, 1922b). In one of these, she pioneered the use of time-series data to document the social effects of business cycles, developing this further in studying for her doctorate at the London School of Economics (LSE), for which she was awarded the Hutchinson Silver Medal. Later, she worked with William I. Thomas in producing The Child in America (Thomas & Thomas, 1928), a book renowned today for what was labelled "the Thomas theorem": that people's perceptions of situations, even [...].

Listing 1 - 3 of 3
Sort by