The development of new conductive polymers nowadays is one of the most important technological areas in materials design. Computational investigation of desired properties in conductive polymers could save financial resources and time, but it is important to choose the methodology that produces good results comparing to experimental results. To verify the prediction of second hyperpolarizability (γ) in oligomers of Trans-Polyacetylene (TPA) by theoretical calculations, a series of semi-empirical, Hartree-Fock (HF), and Density Functional Theory (DFT) calculations were performed and analysed through linear fitting statistical analysis to investigate the accuracy of such theoretical predictions in comparison to the experimental ones. The results showed that HF and DFT methodologies do not describe γ with good accuracy, but the use of diffuse and polarizability functions in HF methodology provided better results than 3-21G and 6-31G functions. It was concluded that RM1 methodology better agrees with γ experimental results for TPA oligomers, and linear fitting statistical analysis is a useful tool to compare experimental and theoretical results.