Correlations for estimation of thermophysical properties are needed for the design of processes and equipment related to phase equilibria. The normal boiling point (NBP) is a fundamental characteristic of chemical compounds, involved in many correlations used to estimate important properties. Modern simulation packages usually require the NBP and a standard liquid density from which they can estimate all other necessary properties and begin the design of particular processes, installations and flowsheets. The present work contributes a correlation between the molecular structure and the normal boiling point of hydrocarbons. Its main features are the relative simplicity, sound predictions, and applicability to diversified industrially important structures, whose boiling points and numbers of carbon atoms span a wide range. An achievement of particular interest is the opportunity revealed, for reducing the number of the compounds required for the derivation (the learning set), through multivariate analysis and molecular design. The high accuracy achieved by the correlation opens up a possibility for systematic studies of chemical engineering applications in which the effects of small changes are important. This also defines a path towards the more general problem of the influence of uncertainties in calculated thermophysical parameters on the final outcome of computer aided simulation and design.