This chapter gives a detailed presentation of linear regression, one of the most widely studied and applied statistical and econometric techniques in transportation data analysis. The chapter discusses linear regression’s suitability for modeling a wide variety of relationships between variables and the ease of which its results can be interpreted and communicated. However, focus is also directed toward misuse, which includes violations of basic assumptions used in derivations. The chapter presents detailed discussions on underlying model assumptions, least squares and maximum likelihood estimation, variable transformations, data outliers, goodness-of-fit measures, multicollinearity of explanatory variables, and estimating elasticities. Models dealing with censored dependent variables (Tobit regressions) and Box-Cox regression are also presented. The chapter shows the great potential of these approaches for addressing a variety of transportation data analyses.