INTRO. TO ATLAS.ti and CAT
for QUALITATIVE DATA ANALYSIS
November 6, 2009 (Friday; 10 a.m. - 4 p.m.)
University of Massachusetts Amherst
Instructor: Dr. Stuart Shulman, Assistant Professor of Political Science, University of Massachusetts Amherst. He directs the Qualitative Data Analysis Program (QDAP-UMass) and is the associate director of the National Center for Digital Government.
The Workshop:
10 a.m. - 12 noon: The morning colloquium on “Measuring Validity and Reliability in Coding” will demonstrate the ways in which CAT is used in a variety of multi-disciplinary research projects to measure, improve and report reliability and validity in coding. It will also show how these tools can be used to focus attention on difficult to code concepts.
Tools for reviewing, coding, and retrieving text found in qualitative data analysis packages carry with them no particular attributes for ensuring the reliability or validity of the recorded observations. It is preferable to speak of the reliability or validity of the results from a particular set of observations, rather than of the tool itself, the coding system, or its developers. The Qualitative Data Analysis Program (QDAP) uses the Coding Analysis Toolkit (CAT), a suite of custom built, web-based tools, that enables the Project Manager to measure coder reliability on the fly during pioneer pre-tests. CAT’s core functionality allows for the adjudication of coded items by an “expert” user (or users). The system keeps track of which instances of a particular code are scored valid and which coders assigned those codes. This information provides a track record of coders for assessing coder validity over time. It also allows the account holder to see a rank order list of the coders most likely to produce valid observations, report the overall validity scores by code, coder, or entire project, and end up with a ‘clean’ dataset consisting of only valid observations.
1:00-4:00 p.m.: After the lunch break, Dr. Shulman will lead a hands-on, computer lab-based training introducing techniques for using ATLAS.ti and the Coding Analysis Toolkit (CAT) effectively on multi-coder projects. ATLAS.ti is a software program for the qualitative analysis of large bodies of textual, graphical, audio and video data; CAT is a suite of custom-built web-based tools that work with ATLAS.ti to measure coder reliability.
An ongoing ' user group' will be convening to provide follow up to this workshop.
This workshop is offered in collaboration with the Science, Technology and Society Initiative at the University of Massachusetts Amherst.
/ return to top
HIERARCHICAL LINEAR MODELS I
June 1-5, 2009 (Monday-Friday)
University of Massachusetts Amherst
Instructor: Dr. Aline Sayer, associate professor of psychology and CRF's Methodology Program Director at UMass Amherst.
Hierarchical linear models (HLMs) provide a conceptual framework and a flexible set of analytical tools to study a variety of social, political, and developmental processes. One major HLM application focuses on the modeling of longitudinal data or the analysis of individual change over time. Another set of applications focuses on data in which persons are clustered within social context such as schools, neighborhoods, or organizations. Participants will be exposed to a wide variety of examples, with emphasis on the interpretation and reporting of results.
/ return to top
MODELING DIARY AND DYADIC DATA
June 8-11 (Monday-Thursday)
University of Massachusetts Amherst
Instructors:
Dr. Jean-Philippe Laurenceau, Psychology, University of Delaware
Dr. Niall Bolger, Psychology, Columbia University
This workshop is for social psychologists, family and medical sociologists, gerontologists, social workers, communication researchers, and researchers of marketing and organizational behavior.
Diary methods allow researchers to examine dyadic processes in daily life in a way that is not possible using traditional methods. Using diaries, researchers typically obtain many repeated observations on dyad members over days and weeks. Dyadic diary data, however, present several data analytic challenges stemming from the various sources of interdependence in these data. Not only is there non-independence between members of the dyad, there is also non-independence of observations within each dyad member. The multilevel or hierarchical linear model (HLM) provides a flexible set of analytic tools that can take account of these complexities. This workshop will begin by considering models for diary data on individuals. It will then cover models for the analysis of dyads, where individual responses are clustered within couples, sibships, caregiving dyads, or other matched pairs. Finally, it will cover models for dyadic diary data.
The course will devote equal time to lectures/demonstrations by the presenters and computer lab work by the participants. The main software used will be HLM6 with some advanced applications using SAS PROC MIXED and Mplus. Participants should have strong backgrounds in multiple regression analysis. A list of likely topics includes:
* Introduction to multilevel models for diary data
* Allowing for auto-correlated error terms
* Testing mediation in diary data
* Dyadic consensus and discrepancy
* Partners as multivariate outcomes
* Power in multilevel models
* Actor-partner interdependence model
* Multilevel modeling for dyadic diary data
* Exchangeable vs. distinguishable dyads
* Extending multilevel modeling to dyadic diary data
* Separating state and trait effects with centering
* Dichotomous outcomes
* Psychometrics of diary measures
/ return to top
ANALYZING DEVELOPMENTAL TRAJECTORIES
June 15-18, 2009 (Monday-Thursday)
University of Massachusetts Amherst
Instructor: Dr. Daniel Nagin, professor of Public Policy and Statistics at Carnegie-Mellon University.
A developmental trajectory describes the course of a behavior over age or time. This three-day workshop aims to provide participants with the training to apply a group-based method for analyzing developmental trajectories. This methodology has four significant capabilities: (1) the capability to identify rather than assume distinctive groups of trajectories, (2) the capability to estimate the proportion of the population following each such trajectory group, (3) the capability to relate group membership probability to individual characteristics and circumstances, and (4) the capability to use the group membership probabilities for various other purposes such as creating profiles of group members. In addition, workshop participants will be trained in the application of three important extensions of the method: (1) the capability to add time-varying covariates to trajectory models, (2) the capability to estimate joint trajectory models of distinct but related behaviors, and (3) the capability to link trajectories with distal outcomes.
/ return to top
RESEARCHING THE CONNECTED WORLD : An Introduction to Social Network Analysis
Instructor: Dr. Andrew Papachristos
Department of Sociology, University of Massachusetts Amherst
July 13-15, 2009 (Monday-Wednesday)
University of Massachusetts Amherst
Are you interested in learning what constitutes peer pressure? How does marriage affect banking relationships? Global trade patterns and modern art? The answers to nearly all these questions are based in an understanding of social networks and how they are structured. This workshop will introduce the concepts and methods of Social Network Analysis, a burgeoning scientific field that spans disciplines. Researchers studying peer network, criminal networks, global management and business networks will benefit from this workshop.
The workshop will introduce a variety of network concepts and methods, with particular attention paid to properties such as: centrality, social cohesion, social contagion, formal characteristics of global and local network structures, and a brief introduction to statistical models for social networks. The afternoon session will guide the participant through a hands-on network tutorial using freely available software and data including PAJEK and UCInet (freeware).
/ return to top
