Substantially all of the chemical and physical evidence concerning the nature of rubber is consistent with the chemical formula (C5H8)x, and this is the generally accepted formula for “rubber hydrocarbon.” An examination of the evidence discloses, however, that the above formula is not the only one which is consistent with this evidence. The difficulty of establishing beyond question the chemical composition of rubber hydrocarbon has been due largely to the lack of efficient physical methods for fractionating the hydrocarbon, of proving that the final fractions are one-component systems, and of chemically identifying these fractions. If, as seems not improbable, rubber hydrocarbon is a mixture of closely related hydrocarbons not all of which can be represented by the formula (C5H8)x, no single method of fractionation can be relied upon to separate this mixture into its constituents. The only methods heretofore available for this purpose have been those based upon extraction with different liquids and fractional precipitation. One of the most powerful methods for fractionating a mixture of hydrocarbons is systematic crystallization, and the purpose of this investigation was to develop a technic for applying this method to rubber.