While using standard tests of weak form market efficiency along with the more recent DELAY test, this report examines if the returns of six selected stocks and two decile indices follow a random walk which would evidence the non-predictability of future stock returns by historical prices which is a necessary condition for the weakest form of market efficiency. The evidence of four different measurement tests suggests that except of one stock all stocks and indices drift away from the weak form market efficiency hypothesis.
Table of Contents
I. Companies overview
II. Data and Methodology
A. Data
B. Methods
B.1. Autocorrelation Tests
B.2. Variance Ratio Tests
B.3. Runs Tests
B.4. Griffin-Kelly-Nardari DELAY Tests
III. Descriptive Statistics
A. Daily Data
B. Monthly Data
IV. Results
A. Autocorrelation Tests
A.1. Tests for Log-Returns
A.2. Tests for Squared Log-Returns
A.3. Tests for the Absolute Value of Log-Returns
A.4. Correlation Matrix of Stocks and Indices
B. Variance Ratio Tests
C. Runs Tests
D. Griffin-Kelly-Nardari DELAY Tests
V. Conclusions and Discussions
Research Objective and Scope
The primary objective of this report is to empirically test the Weak Form Efficient Market Hypothesis (EMH) to determine whether historical price data can be used to predict future stock returns, thereby establishing whether selected financial assets follow a random walk.
- Empirical analysis of six selected NYSE/NASDAQ stocks and two decile indices.
- Application of autocorrelation tests to check for serial correlation in returns.
- Execution of variance ratio and runs tests to validate the random walk hypothesis.
- Implementation of Griffin-Kelly-Nardari DELAY tests to measure market response speed.
- Evaluation of distribution characteristics through descriptive statistics and normality tests.
Excerpt from the Book
B.1. Autocorrelation Tests
In order to test if an individual time series follows a random walk the data is checked for serial correlation which describes the correlation between two observations of the same series at different dates. The weakest version of a random walk, RW3, supposes that the increments or first-differences of the level of the random walk are uncorrelated at all leads and lags. RW3 can be tested by testing the null hypothesis stating that the autocorrelation coefficients of the first-differences are all zero at various lags.
where ρ_k is the autocorrelation at lag k; r_(i,t) is the log-return on stock i at time t; and r_(i,t-k) is the log-return on stock i at time t - k. The serial correlation is positive if ρ_k is also positive. The serial correlation is negative if ρ_k is also negative. Equation (3) assumes covariance-stationarity of returns (i.e. their mean and variance are constant, while the covariance between lags should depend only on distance between lags, and not on shifts throughout the time). To reject the null hypothesis of no serial correlation in return series ρ_k needs to be significantly different from zero.
The output of the autocorrelation test contains the coefficients for up to 12 lags for all six selected stocks as well as the two decile indices. Not only the statistical significance of each individual autocorrelation coefficient is tested but also the Ljung-Box test (cp. Campbell, Lo and Mackinlay (1997, p. 47)) is employed which tests the joint hypothesis stating that all the values of the autocorrelation coefficients up to the tested lag are simultaneously equal to zero. The test statistics for 3 and 12 lags are computed.
Summary of Chapters
I. Companies overview: This chapter provides fundamental business profiles and market data for the six selected companies under investigation.
II. Data and Methodology: This section details the data selection criteria and outlines the specific statistical tests employed to examine the market efficiency hypothesis.
III. Descriptive Statistics: This chapter presents a statistical overview of daily and monthly returns, including skewness and kurtosis, to assess the normality of the return distributions.
IV. Results: This chapter reports the empirical findings from autocorrelation, variance ratio, runs, and delay tests to evaluate the random walk behavior of the assets.
V. Conclusions and Discussions: This chapter synthesizes the results, concluding that most assets deviate from the weak-form EMH, with Energen Corporation being the only exception providing consistent random walk evidence.
Keywords
Weak Form Efficiency, Market Hypothesis, Random Walk, Autocorrelation, Variance Ratio, Runs Test, DELAY Test, Stock Returns, Serial Correlation, Volatility Clustering, Log-Returns, Financial Markets, Statistical Significance, Efficient Market Hypothesis, Investment Analysis.
Frequently Asked Questions
What is the fundamental focus of this research?
The research focuses on testing the Weak Form Efficient Market Hypothesis (EMH) to determine if stock prices reflect all available historical information.
Which specific areas are covered in the investigation?
The study examines six individual stocks (AMD, BDK, EGN, CLHB, COBZ, COKE) and two decile indices using various statistical models to check for market efficiency.
What is the primary research goal?
The primary goal is to determine if the selected assets follow a random walk, which would imply that past price movements cannot predict future performance.
What scientific methods were applied in this paper?
The author uses a variety of econometric tools including autocorrelation tests (Ljung-Box), variance ratio tests, runs tests, and the Griffin-Kelly-Nardari DELAY model.
What topics are analyzed in the main body?
The main body covers descriptive statistics of returns, testing for serial correlation in log-returns and squared/absolute returns, and assessing the impact of lagged market information.
Which keywords best characterize this work?
Key terms include Efficient Market Hypothesis, Random Walk, Autocorrelation, Variance Ratio, and Volatility Clustering.
Does the data support the random walk hypothesis for all assets?
No, the findings are inconsistent across different tests and assets, with Energen Corporation (EGN) being the only asset providing consistent evidence of following a random walk.
How is market response speed addressed?
The report employs the Griffin-Kelly-Nardari DELAY test to evaluate how quickly stock prices adjust to market-wide information compared to a restricted model.
Why are both daily and monthly data analyzed?
The study uses both frequencies to check for robustness and to see if conclusions regarding market efficiency hold true across different observation intervals.
- Quote paper
- Björn Schubert (Author), 2009, Weak Form Efficiency Tests, Munich, GRIN Verlag, https://www.grin.com/document/131805
