Introduction to the theory and application of data envelopment analysis:a foundation text with integrated software

The book aims to introduce the reader to DEA in the most accessible manner possible. It is specifically aimed at those who have had no prior exposure to DEA and wish to learn its essentials, how it works, its key uses, and the mechanics of using it. The latter will include using DEA software. Students on degree or training courses will find the book especially helpful. The same is true of practitioners engaging in comparative efficiency assessments and performance management within their organisation. Examples are used throughout the book to help the reader consolidate the concepts covered. Table of content: List of Tables. List of Figures. Preface. Abbreviations. 1. Introduction to Performance Measurement. 2. Definitions of Efficiency and Related Measures. 3. Data Envelopment Analysis Under Constant Returns to Scale: Basic Principles. 4. Data Envelopment Analysis under Constant Returns to Scale: General Models. 5. Using Data Envelopment Analysis in Practice. 6. Data Envelopment Analysis under Variable Returns to Scale. 7. Assessing Policy Effectiveness and Productivity Change Using DEA. 8. Incorporating Value Judgements in DEA Assessments. 9. Extensions to Basic DEA Models. 10. A Limited User Guide for Warwick DEA Software. Author Index. Topic Index. References.

History and symptom taking in contact lens fitting and aftercare

Aim: To appraise history and symptom taking for contact lens consultations, to determine current practice and to make recommendations for best practice. Method: The peer reviewed academic literature was reviewed and the results informed a survey completed by 256 eye care practitioners (ECPs) on their current practice and influences. Results: The last eye-test date, last contact lens aftercare (for existing wearers) and reason for visit are key questions for most ECPs. Detailed use of contact lens questions are more commonly applied in aftercares than when refitting patients who have previously discontinued wear (87% vs 56% use), whereas questions on ocular and general history, medication and lifestyle were generally more commonly utilised for new patients than in aftercares (72% vs 50%). 75% of ECPs requested patients bring a list of their medication to appointments. Differential diagnosis questioning was thorough in most ECPs (87% of relevant questions asked). Attempts to optimise compliance included oral instruction (95% always) and written patient instructions (95% at least sometimes). Abbreviations were used by 39% of respondents (26% used ones provided by a professional body). Conclusion: There is scope for more consistency in history and symptom taking for contact lens consultations and recommendations are made.

On stopwords, filtering and data sparsity for sentiment analysis of Twitter

Sentiment classification over Twitter is usually affected by the noisy nature (abbreviations, irregular forms) of tweets data. A popular procedure to reduce the noise of textual data is to remove stopwords by using pre-compiled stopword lists or more sophisticated methods for dynamic stopword identification. However, the effectiveness of removing stopwords in the context of Twitter sentiment classification has been debated in the last few years. In this paper we investigate whether removing stopwords helps or hampers the effectiveness of Twitter sentiment classification methods. To this end, we apply six different stopword identification methods to Twitter data from six different datasets and observe how removing stopwords affects two well-known supervised sentiment classification methods. We assess the impact of removing stopwords by observing fluctuations on the level of data sparsity, the size of the classifier's feature space and its classification performance. Our results show that using pre-compiled lists of stopwords negatively impacts the performance of Twitter sentiment classification approaches. On the other hand, the dynamic generation of stopword lists, by removing those infrequent terms appearing only once in the corpus, appears to be the optimal method to maintaining a high classification performance while reducing the data sparsity and substantially shrinking the feature space