Latent trajectory models for space-time analysis: An application in deciphering spatial panel data Li An 1 , Ming-Hsiang Tsou 1 , Brian H. Spitzberg 2 , Dipak K. Gupta 3 , J. Mark Gawron 4 1 Department of Geography, San Diego State University, San Diego, CA, USA, 2 School of Communication, San Diego State University, San Diego, CA, USA, 3 Department of Political Science, San Diego State University, San Diego, CA, USA, 4 Department of Linguistics, San Diego State University, San Diego, CA, USA This article introduces latent trajectory models (LTMs), an approach often employed in social sciences to handle longitudinal data, to the arena of GIScience, particularly space- time analysis. Using the space-time data collected at county level for the whole United States through webpage search on the keyword “climate change,” we show that LTMs, when combined with eigenvector filtering of spatial dependence in data, are very useful in unveiling temporal trends hidden in such data: the webpage-data derived popularity measure for climate change has been increasing from December 2011 to March 2013, but the increase rate has been slowing down. In addition, LTMs help reveal potential mechanisms behind observed space-time trajectories through linking the webpage-data derived popularity measure about climate change to a set of socio-demographic covari- ates. Our analysis shows that controlling for population density, greater drought expo- sure, higher percent of people who are 16 years old or above, and higher household income are positively predictive of the trajectory slopes. Higher percentages of Republi- cans and number of hot days in summer are negatively related to the trajectory slopes. Implications of these results are examined, concluding with consideration of the potential utility of LTMs in space-time analysis and more generally in GIScience. Introduction Space-time analysis largely refers to detecting, visualizing, or explaining/predicting space-time patterns for certain human or environmental phenomena of interest. As access to large corpora of space-time data has substantially increased, it is evident that space-time analysis has drawn increasing attention. Parallel to this trend, GIScientists face unprecedented challenges and opportunities in “conceptualization, representation, computation, and visualization of space- time data” (Kwan and Neutens 2014, 851). Considerable recent efforts 1 have been devoted to Correspondence: Li An, Department of Geography, San Diego State University, 5500 Campanile Drive, San Diego CA 92182-4493, USA e-mail: lan@mail.sdsu.edu Submitted: June 26, 2015. Revised version accepted: December 04, 2015. doi: 10.1111/gean.12097 314 V C 2016 The Ohio State University Geographical Analysis (2016) 48, 314–336