COURSE OVERVIEW

 

The workshop offers participants an introduction to sequence analysis using the user written sequence analysis package of commands developed for Stata. Sequence analysis, which has its roots in biomedical research, has of recent become increasing used in social sciences to study a wide variety of ordered social phenomena, such as; life course development, career development and labour market or employment histories. Researchers studying social networks, implement sequence analysis to model whole networks evolve over time. Social network epidemiologists use sequence analysis to model social contact in order to increase their understanding of how a disease spreads.

 

Sequence analysis aims to find similarities between sequences, or to detect typical sequences. Similarities between sequences may arise from common causes (common ancestors), or due to causal relationships between the sequences. It does not however, focus on the relationships of the elements within the sequences, rather it is a description of the characteristics of the entire sequences. Although sequences usually refer to phenomena that are ordered temporally (events or states that unfold over a period of time), a sequence may also reflect spatial order, preference order, hierarchical order, logical order, or other types of order.

 

A variety of techniques have been designed to describe, quantify, and predict sequences, this course focuses on both the graphical analysis of sequences and the calculation of both sequence statistics (descriptive measures of various characteristics of sequences) and sequence similarity statistics (measures of similarity or dissimilarity between sequences.  Sequence statistics and similarity statistics  can then  be incorporated into subsequent analyses – such as regression models, cluster analysis or multidimensional scaling.

 

TARGET AUDIENCE

 

Researchers or professionals working in biomedicine, psychology, the political or social sciences and social epidemiology interested in applying sequence analysis in Stata.

 

COURSE REQUISITES

 

Participants should have a computer or laptop with Stata 13 or higher. They should have a connection to the Internet and write access to Stata’s Ado-Directory (by default c:/ado)


PROGRAM

 

The workshop provide a hands on introductory course to techniques to analyze sequences and to Stata’s SQ-Ados, focusing on the following aspects of sequence analysis:

 

Types of sequences
Data Management for sequence data
Descriptive Statistics

 

 

 

 

Visualization
Sequence Similarity
Grouping

 

Throughout the course of the workshop, a broader concept of the term sequences, which includes  both “words” and sequences of job positions, will be analyzed.