TY - GEN
T1 - Tutorial on latent growth models for longitudinal data analysis
AU - Gu, Binx
AU - Pavlou, Paul A.
PY - 2010/12/1
Y1 - 2010/12/1
N2 - This tutorial introduces Latent Growth Modeling (LGM) as a promising new method for analyzing longitudinal data when interested in understanding the process of change over time. Given the need to go beyond cross-sectional models in IS research, explore complex longitudinal IS phenomena, and test Information Systems (IS) theories over time, LGM is proposed as a complementary method to help IS researchers propose time-dependent hypotheses and make longitudinal inferences about IS theories. The tutorial leader will explain the importance of theorizing patterns of change over time, how to propose longitudinal hypotheses, and how LGM can help test such hypotheses. All three tutorial facilitators will describe the tenets of LGM and offer guidelines for applying LGM in IS research including framing time-dependent hypotheses that can be readily tested with LGM. The three tutorial facilitators will also explain how to use LGM in SAS 9.2 with a hands-on application that will attempt to model the complex longitudinal relationship between IT and firm performance using longitudinal data from Fortune 1000 firms. The tutorial facilitators will also draw comparisons with other existing methods for modeling longitudinal data and they will also discuss the advantages and disadvantages of LGM for identifying longitudinal patterns in data.
AB - This tutorial introduces Latent Growth Modeling (LGM) as a promising new method for analyzing longitudinal data when interested in understanding the process of change over time. Given the need to go beyond cross-sectional models in IS research, explore complex longitudinal IS phenomena, and test Information Systems (IS) theories over time, LGM is proposed as a complementary method to help IS researchers propose time-dependent hypotheses and make longitudinal inferences about IS theories. The tutorial leader will explain the importance of theorizing patterns of change over time, how to propose longitudinal hypotheses, and how LGM can help test such hypotheses. All three tutorial facilitators will describe the tenets of LGM and offer guidelines for applying LGM in IS research including framing time-dependent hypotheses that can be readily tested with LGM. The three tutorial facilitators will also explain how to use LGM in SAS 9.2 with a hands-on application that will attempt to model the complex longitudinal relationship between IT and firm performance using longitudinal data from Fortune 1000 firms. The tutorial facilitators will also draw comparisons with other existing methods for modeling longitudinal data and they will also discuss the advantages and disadvantages of LGM for identifying longitudinal patterns in data.
UR - http://www.scopus.com/inward/record.url?scp=84870385358&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84870385358&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84870385358
SN - 9781617389528
T3 - 16th Americas Conference on Information Systems 2010, AMCIS 2010
SP - 1802
EP - 1806
BT - 16th Americas Conference on Information Systems 2010, AMCIS 2010
T2 - 16th Americas Conference on Information Systems 2010, AMCIS 2010
Y2 - 12 August 2010 through 15 August 2010
ER -