The dataset entitled “imputedsalt_PanHa” holds data structures to be relayed to statistical modeling of salinity in near-coastal environments of the Northern Gulf of Mexico. The content therein is created by the ‘covardr2formodel.R’ script that represents terminal decisions on variable setup and transformations). The design ideal is that the content of this directory would be copied to some path of “input” within a model building repository. The table in this directory would be especially suitable for both (1) formal data releases supporting as needed interpretive publications and (2) simultaneous long-term storage as copies within a model building repository in some specific terminal decisions (variable transforms or even dropping of whole data classes by switches in ‘covardr2formodel.R) are reflected in these data and they are a step removed as it were from the “raw” data in the ‘covardr/’ directory.