Suchergebnisse

This article takes a topographical approach to re-reading print books in digital literary spaces through a discussion of a web-based work of digital literature, …and by islands I mean paragraphs (Carpenter 2013). In this work, a reader is cast adrift in a sea of white space extending far beyond the bounds of the browser window, to the north, south, east and west. This sea is dotted with computer-generated paragraphs. These fluid texts call upon variable strings containing words and phrases collected from a vast literary corpus of books about islands. Individually, each of these textual islands represents a topic—from the Greek topos, meaning place. Collectively they constitute a topographical map of a sustained practice of reading and re-reading and writing and re-writing on the topic of islands. This article argues that, called as statement-events into digital processes, fragments of print texts are reconstituted as events occurring in a digital present which is also a break from the present. A new regime of signification emerges, in which authorship is distributed and text is 'eventilized' (Hayles). This regime is situated at the interface between an incoherent aesthetics, one which tends to unravel neat masses, including well-known works of print literature; and an incoherent politics, one which tends to dissolve existing institutional bonds, including bonds of authorship and of place. Galloway terms this regime of signification the 'dirty regime of truth'.DOI: http://dx.doi.org/10.14195/2182-8830_4-1_5 ; Este artigo adota uma abordagem topográfica enquanto forma de releitura de livros impressos em espaços literários digitais através da análise de uma obra de literatura digital em linha, …and by islands I mean paragraphs (Carpenter 2013). Nesta obra, um leitor encontra-se à deriva num mar de espaço em branco que se estende além dos limites da janela do 'browser', para norte, sul, leste e oeste. Este mar é pontilhado por pontos gerados por computador. Estes textos fluidos invocam cadeias de variáveis que contêm palavras e frases recolhidas de um vasto corpus literário de livros sobre ilhas. Individualmente, cada uma destas ilhas textuais representa um tópico – a partir do grego topos, que significa lugar. Coletivamente, constituem um mapa topográfico de uma prática sustentada de leitura e releitura, de escrita e reescrita sobre o tema das ilhas. Este artigo argumenta que fragmentos de textos impressos, designados eventos-afirmativos em processos digitais, são reconstituídos como eventos num presente digital, que é também uma rutura com o presente. Um novo regime de significação emerge em que a autoria é distribuída e o texto é 'eventivizado' (Hayles). Este regime situa-se na interface entre uma estética incoerente, que tende a desmontar conjuntos arrumados, incluindo obras conhecidas da literatura impressa; e uma política incoerente, que tende a dissolver laços institucionais existentes, incluindo ligações de autoria e de lugar. Galloway denomina este regime de significação de 'regime sujo da verdade'. DOI: http://dx.doi.org/10.14195/2182-8830_4-1_5

Abstract
Multiple imputation is now well established as a practical and flexible method for analyzing partially observed data, particularly under the missing at random assumption. However, when the substantive model is a weighted analysis, there is concern about the empirical performance of Rubin's rules and also about how to appropriately incorporate possible interaction between the weights and the distribution of the study variables. One approach that has been suggested is to include the weights in the imputation model, potentially also allowing for interactions with the other variables. We show that the theoretical criterion justifying this approach can be approximately satisfied if we stratify the weights to define level-two units in our data set and include random intercepts in the imputation model. Further, if we let the covariance matrix of the variables have a random distribution across the level-two units, we also allow imputation to reflect any interaction between weight strata and the distribution of the variables. We evaluate our proposal in a number of simulation scenarios, showing it has promising performance both in terms of coverage levels of the model parameters and bias of the associated Rubin's variance estimates. We illustrate its application to a weighted analysis of factors predicting reception-year readiness in children in the UK Millennium Cohort Study.