Prague Economic Papers 1999, 8(1) | DOI: 10.18267/j.pep.38

Prague stock exchange: sectorial indices development in 1997

Jiří Trešl

Statistical analysis of sectorial and global indexes at Prague Stock Exchange in 1997 was performed. The relative variability of sectorial indexes ranged from 5 % (Mining) to 29 % (Agriculture). The normal distribution was appropriate roughly for one half of index returns. Daily (resp. weekly) correlation coefficients between different sectorial daily and weekly returns were statistically significant particularly between Finance and Banking, Investment Funds and Heavy Industry sectors with typical values from 0.2 to 0.5 (daily) and from 0.4 to 0.6 (weekly). Quasi-periodic time course of indexes enables the trend modelling through harmonic components superposition. The first four harmonic terms were capable to explain 80-90 % of values observed.
Time behaviour of index returns was modelled using Box-Jenkins method. As a rule, simple models up to the second order proved to be satisfactory. Further, two thirds of index returns were explained by the first order moving average model. Prevailing part of sectorial index returns exhibited random behaviour with respect to number of positive and negative events, but the opposite is true from the point of view of runs number expected. The weekend effect has been found with Monday returns systematically lower. The dependence of PX - GLOB returns variance on the PX - GLOB values may give rise to an idea about different generating mechanism at different levels.

Klíčová slova: capital market analysis, financial time series, return modelling, stock behaviour

Zveřejněno: 1. leden 1999  Zobrazit citaci