Abstract: There have been numerous different kinds of data such as stock prices and interest rates observed and gathered in the past. The sequential nature of these data require us to account for the dynamic nature using special statistical skill and techniques. Time series analysis provide the appropriate methods necessary in order to analyze sequential data.
It may be problematic to picture the essential, underlying trend of the data if the time series has a lot of noise. To distinguish the signal and the noise from each other, various linear and nonlinear smoothers must be applied.

This paper collected a century’s worth of P/E ratio data and used the static distribution to map out the overall trend of the P/E ratio in terms of its return period. Also, the data was plotted in Matlab, and multiple fitting models were tested out to see which one fit the data the best. The P/E ratio was chosen due to its significance in the evaluation of stocks’ values, and the static distribution due to its ability to incorporate rapidly fluctuating data into statistical analysis.

Keywords – Multiple fitting models, P/E ratio, statistical analysis, lnear and nonlinear smoothers

References

[1] Peres, D. J.; Cancelliere, A. (2016-10-01). "Estimating return period of landslide triggering by Monte Carlo simulation". Journal of Hydrology. Flash floods, hydro-geomorphic response and risk management. 541: 256–271.
[2] Anonymous (2014-11-07). "Flood Estimation Handbook". UK Centre for Ecology & Hydrology. Retrieved 2019-12-21.
[3] https://en.wikipedia.org/wiki/Gumbel_distribution
[4] ASCE, Task Committee on Hydrology Handbook of Management Group D of (1996). Hydrology Handbook | Books. doi:10.1061/9780784401385. ISBN 978-0-7844-0138-5. doi:10.1016/j.jhydrol.2016.03.036.