 |
 |
Subject: CCSR Short Course Training in Social Research Methods and Statistics 2013/14 CCSR Short Course Training in Social Research Methods and Statistics at the University of Manchester 2013/14 There are still a small number of places left on the upcoming courses on research skills, social statistics and data analysis at the Centre for Census and Survey Research. See www.ccsr.ac.uk/courses/list/<http://www.ccsr.ac.uk/courses/list/> You can also download the course brochure http://www.ccsr.ac.uk/documents/2013-2014ShortCourseLeaflet.pdf Foundation Skills for Data Analysts - 11th September 2013. This is a foundation course for participants with no previous experience in statistics or statistical analysis software. It will introduce key concepts such as: cases, variables, values and levels of measurement. By the end of the day, participants will be able to open a data file, to do basic manipulations to the data, to produce descriptive statistics, one and two way tables and simple graphs. This course will provide participants with the appropriate background to progress to other CCSR courses, particularly Introduction to Data Analysis 1 and Introduction to Data Analysis 2. Introduction to Data Analysis 1 - 12th September 2013. This course provides an introduction to the theory and methods of quantitative data analysis, focussing on the social survey, with a focus on the use of crosstabulation to explore the relationship between categorical variables. It includes a series of practical sessions including using the statistical software package SPSS to explore a government dataset. Introduction to Data Analysis 2 - 13th September 2013. This course provides an introduction to the theory and methods of quantitative data analysis for interval variables, focussing on the techniques of correlation and linear regression. It includes a series of practical sessions including using the statistical software package SPSS to explore a government dataset. Introduction to STATA - 2nd October 2013. The course provides an introductory training in STATA, a statistical package increasingly used for social research data analysis which has powerful data manipulation procedures and extensive and powerful statistical capabilities. Multiple Linear Regression - 16th October 2013. This course provides a thorough grounding in the theory and methods of multiple linear regression including: model selection, non linear relationships, dummy variables, interaction terms and assumption testing. The course comprises taught and practical components in about equal proportions. Logistic Regression - 17th October 2013. This course examines the fitting of models to predict a binary response variable from a mixture of binary and interval explanatory variables. The approach is illustrated using examples from a social science perspective, including cases where logistic regression models are used as a means of analysing tabular data where one of the dimensions of the table is a two-category outcome variable. The participant will also learn how to fit a logistic regression model, and how to interpret the results. Introduction to Mathematical Concepts for Social Statistics - 23rd October 2013. The course covers the following essential topics in mathematics: back to basics (percentages, proportions, averages), data and tables, describing and visualizing data, measures of spread, transforming data, concepts in algebra and common symbols, geometry of a straight line, limits and continuity, derivatives and more, maximization in statistics, correlations, vectors and matrices, solving a multivariate regression problem. There will be exercises and examples of the use of these concepts in mathematics for statistical applications. This course introduces social scientists to the essential mathematics that are utilized in social statistics. Statistical Disclosure Control - Balancing Data Confidentiality and Data Quality - 6th- 7th November 2013. The need for data products that combine information across databases and organizations is increasing. Overwhelmingly, the data from which these data products are built is reported at the individual entity level and is confidential. Ethical survey practice and often law or regulation demands that confidential data pertaining to individual entities not be revealed through data products. Confidentiality concerns have been addressed by researchers over decades, resulting in a suite of methods for statistical disclosure limitation (SDL) used by national statistical offices. Until recently, however, the effects of disclosure limitation methods on data quality, completeness and usability have been largely ignored. The interplay between data confidentiality methods and data quality and usability is the unifying subject of this course. Constructing Measures Using The Rasch Model - 14th - 15th November 2013. This short course covers the basic theory behind measurement, from an Item Response Theory perspective, focusing on the assumptions of the Rasch models in particular. The Rasch model provides the means to create measures (or score scales) from a combination of items in tests or surveys. The principles governing the application of such models are shown through examples from educational measurement but are easily applicable to other areas in social and health sciences. The course will be of interest to researchers and practitioners involved, among others with educational measurement, measurement of satisfaction for evaluation, tests of skills, knowledge and other cognitive outcomes, attitudinal scales and measures of dispositions. Participants should have some basic knowledge of introductory statistics. Questionnaire Design - 18th November 2013. Rubbish in, rubbish out - have you ever discovered too late that your survey questions did not deliver useful or useable data? Through looking at a wide range of pitfalls, this course explores ways to assess the effectiveness of existing questionnaires as well as how to write successful new ones. It combines suggestions from the research literature on questionnaire design with a very practical approach. Common errors in the wording of individual questions are examined as well as how to combine individual questions into a meaningful questionnaire. Standardised Multi-Item Scale Development for Surveys - 19th November 2013. Standardised multi-item scales are very common in psychology, education, and health, but much less so in sociology, political science, and survey research. This one day course is designed to inspire participants from all disciplines that it is possible to develop your own high quality multi-item scales. This course offers an introduction on how to do this: looking at psychometric principles, exploring the special questionnaire design concerns, introducing some basic statistical tools for assessing the reliability and dimensionality of multi-item scales, and practice evaluating some existing scales in a lab session at the end of the day. An Introduction to Computational Social Science Using Big Data - 20th November 2013. Every day we interact with countless technological systems, which support our communication, our transport, our shopping activities, and much more. Through these interactions, we are generating increasing volumes of "big data" and there is scope for measuring human behaviour, captured in a natural setting at an unprecedented speed and scale. Such data constitute a new opportunity for social science research. To make maximum use of these datasets, researchers must possess a combination of programming skills and statistical analysis skills, alongside subject specific knowledge. In this course, participants will be given an overview of recent developments in the field of computational social science, to illustrate the possibilities the new data offers. Participants will be guided through a case study exercise, demonstrating how data on worldwide usage of online resources such as Google and Wikipedia can be linked to collective behaviour in the real world. The case study exercise will focus on basic programming skills for acquiring, processing, and analysing data, and will provide participants with a framework for further self study following the course. Linking Data 1 Background to Techniques - 27th November 2013. The one day course will introduce basic concepts of data linkage, provide background information on data linkage applications and different data sources as well as aspects of preparing datasets for data linkage. By the end of the day, participants should have an understanding of what is involved when merging datasets. Linking Data 2 Theory to Practice - 28th - 29th November 2013. The course will cover probabilistic approaches to data linkage including pre-matching processes, string comparators, determining field weights, types of errors and decision theory, the evaluation of the quality of linkage procedures and the analysis of linked datasets. The course will have a strong practical emphasis to enable course participants to put the taught methods into practice and will include a tutorial and computer workshop. Introduction to Statistical Testing in Research - 4th December 2013. The course aims to cover many of the commonly used parametric and non-parametric statistical tests, along with basic concepts of a randomized clinical trial and the analysis of survival data, with data examples from a health environment but for use in social research more widely. Social Media Data Analysis - Researching YouTube and Twitter - 10th December 2013. The course will use the free Webometric Analyst software for the following purposes: gathering tweets matching a geographic or keyword query; gathering comments on one or more YouTube videos; constructing network diagrams from users or comments. The analysis methods discussed will include: simple quantitative methods, such as social network analysis, to describe the results and content analysis to provide insights into the YouTube or Twitter data. Statistical Analysis With Missing Data Using Multiple Imputation 11th - 12th December 2013. In this course we begin by discussing the issues and problems raised by missing data, and introduce the key concepts required for classifying missing data mechanisms into one of three types. We then consider some of the frequently adopted 'ad-hoc' approaches for handling missing data, and discuss their limitations. Next we introduce the method of multiple imputation, a practical and principled approach for handling missing data. Through computer practicals using STATA, participants will learn how to investigate missingness in their data and how to apply the statistical methods introduced in the course to realistic datasets, such as the National Child Development Study. For more information and to book a place please go to www.ccsr.ac.uk/courses/<http://www.ccsr.ac.uk/courses/> Dr. K. Purdam [log in to unmask]<mailto:[log in to unmask]> PGT and Short Course Director CCSR and Social Statistics University of Manchester M13 9PL UK www.ccsr.ac.uk<http://www.ccsr.ac.uk/> 01612754719 twitter.com/SocialStatsMan<http://twitter.com/SocialStatsMan> You may leave the list at any time by sending the command SIGNOFF allstat to [log in to unmask], leaving the subject line blank.