ANALISIS FRAKTAL TERHADAP PERILAKU RETURN HARIAN INDEKS HARGA SAHAM SEKTORAL PADA BURSA EFEK JAKARTA
<b>Abstract</b><p align="justify"> <br /> Theories of Capital Market grow so fast; that new theories appear and last theories are not suitable. As an example Fractal Market Hypothesis (FMH) concept denies the EMH concept. Therefore, it is important to do researches...
Saved in:
Main Author: | |
---|---|
Format: | Theses |
Language: | Indonesia |
Online Access: | https://digilib.itb.ac.id/gdl/view/4589 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Institut Teknologi Bandung |
Language: | Indonesia |
Summary: | <b>Abstract</b><p align="justify"> <br />
Theories of Capital Market grow so fast; that new theories appear and last theories are not suitable. As an example Fractal Market Hypothesis (FMH) concept denies the EMH concept. Therefore, it is important to do researches on the behavior of The Jakarta Stock Exchange Industrial Classifications on Jakarta Stock Exchange (JSX) have fractal characters and obey FMH concept.<p align="justify"> <br />
<br />
In the EMH concept, investors are assumed to have rational character, efficient market and random walk. From the result of skewness, kurtosis, chi square test and the time structure of volatility proved that the EMH concept failed. <br />
Meanwhile, FMH assumes that 1)The market is stable when it consists of investors covering a large number of investment horizons. 2)The information set is more related to market sentiment and technical factors in the short term in the longer term. 3)Prices reflect a combination of short term technical trading and long term fundamental valuation.<p align="justify"> <br />
<br />
The FMH test uses Rescaled Range (R/S) analysis and produces H value (Hurst). Higher value of H indicates lower degree of risk because it points out system that have little noise, more persistent and clearer trend. The highest value of H is Miscellaneous Industry (11=0.648), that mean it has the lowest risk degree (a=1.543) and the highest correlation measure (C=28.8%). Furthermore, it is followed by Finance, Trade, Property, Basic Industry, Mining, Consumer Goods, Manufacture and Agriculture. The lowest H value is Infrastructure with H=0.546, a=1.832, and C=6.6%.<p align="justify"> <br />
<br />
Validations of R/S analysis test are randomly scrambling test and R/S analysis of time sensitivity test. The results of the scrambling test for all sectors show that H value closer to 0.50. Analyses of the time sensitivity test prove that although different periode of time, characteristic of market constantly show fractal, just different in value of sensitivity. The lowest value of sensitivity is shown by Finance sector, with a different percentage of H value of 0.456%. Industry of Property has the highest value of sensitivity as big as 14.115%. <br />
To see the failure of the assumption of the EMH and based on the RIS analysis test result, the FMH assumptions are more realistic and do happen on the Indonesian Capital Market, especially on the JSX with the IHSS focus. It uses the `bias random walk' concept, investors consist of various investment horizons and correlation of price changes from time to time. |
---|