See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/344504543

The Existence of Random Walk in the Philippine Stock Market: Evidence from
Unit Root and Variance-Ratio Tests

Article  in  Journal of Asian Finance Economics and Business · October 2020

DOI: 10.13106/jafeb.2020.vol7.no10.523

CITATIONS READS

0 98

2 authors:

Aileen Camba Abraham Camba Jr.

Polytechnic University of the Philippines Polytechnic University of the Philippines
5 PUBLICATIONS   2 CITATIONS    5 PUBLICATIONS   2 CITATIONS   

SEE PROFILE SEE PROFILE

All content following this page was uploaded by Abraham Camba Jr. on 07 October 2020.

The user has requested enhancement of the downloaded file.

 Abraham C. CAMBA Jr., Aileen L. CAMBA / Journal of Asian Finance, Economics and Business Vol 7 No 10 (2020) 523–530 523

Print ISSN: 2288-4637 / Online ISSN 2288-4645
doi:10.13106/jafeb.2020.vol7.no10.523

The Existence of Random Walk in the Philippine Stock Market:

Evidence from Unit Root and Variance-Ratio Tests

Abraham C. CAMBA Jr.1, Aileen L. CAMBA2

Received: July 03, 2020  Revised: August 23, 2020  Accepted: September 10, 2020

Abstract
The efficient market hypothesis explains the random walk hypothesis suggesting that stock prices are independent of each other, hence,
it is impossible to earn abnormal profits. The positive effect of a well-functioning and highly efficient stock market on the performance
of an economy motivated the Philippine Stock Exchange to pursue massive modernization initiatives. This research provides evidence of
the existence of random walk in the Philippine stock market employing the Augmented Dickey-Fuller (1981) and Phillips-Perron (1988)
unit root tests, the Lo-MacKinlay’s (1988) conventional variance ratio test, and Chow-Denning’s (1993) simple multiple variance ratio
test. Results of the ADF and PP unit root tests confirm the necessary condition for a random walk. The Chow-Denning (1993) maximum
/z/ statistic and the Wald test statistic as in Richardson and Smith (1991) for the joint hypotheses and the Lo and MacKinlay (1988)
individual statistics variance ratio test generally accepted the null hypothesis of a random walk. That is, the unit root and variance ratio tests
consistently indicate that the null hypothesis of random walk cannot be rejected. The existence of a random walk in weak-form efficiency
can be attributed to market liquidity as a result of continuous development and modernization of the Philippine equity market.

Keywords: Chow-Denning Maximum Statistics, Random Walk, Unit Root, Variance Ratio Test, Wald Test Statistic

JEL Classification Code: C32, G10, G12, G14

1. Introduction efficient and traders have full information of all listed

companies as reflected by the corresponding share prices,
The stock market serves as a channel for economic growth then the investment will be allocated to the most efficient
(Camba & Camba, 2020). The most efficient allocation of opportunity and trading activities for both domestic and
capital is achieved with development of financial markets foreign investors can take place without much risk (Lean,
and letting the market allocate the capital. The development Mishra, & Smyth, 2015).
of stock markets, for instance, is necessary to efficiently The efficient market hypothesis seeks to explain the
allocate resources in an economic system by channeling random walk theory by positing that only new information
savings into valuable investments. If a stock market is will move stock prices significantly, and since new
information is presently unknown and occurs at random,
future movements in stock prices are also unknown and,
thus, move randomly. Simply, random walk theory suggests
First Author and Corresponding Author. Assistant Professor II,
1
that stock price changes are independent of one another,
Department of Economics, College of Social Sciences and therefore the past movement of a stock price cannot be
Development, Polytechnic University of the Philippines, Manila,
Philippines [Postal Address: P. Tuazon Ave., Bgry. Kaunlaran, employed to forecast its future movement (Lean & Smyth,
Quezon City, Metro Manila, 1111, Philippines] 2007; Rehman, Kashif, Chhapra, & Rehan, 2018). Hence, it
Email: accamba@pup.edu.ph is not possible to earn abnormal profits.
Associate Professor IV, Department of Economics, College of
2

Social Sciences and Development, Polytechnic University of the

The belief that a well-functioning and highly efficient
Philippines, Manila, Philippines. Email: alcamba@pup.edu.ph stock market positively affects the performance of an
economy motivated the extensive modernization initiatives
© Copyright: The Author(s)
This is an Open Access article distributed under the terms of the Creative Commons Attribution of Philippine Stock Exchange that started in 2005 when
Non-Commercial License (https://creativecommons.org/licenses/by-nc/4.0/) which permits
unrestricted non-commercial use, distribution, and reproduction in any medium, provided the
it adopted the Online Disclosure System (Rufino, 2013).
original work is properly cited. This paper adds to the existing literature in understanding
524 Abraham C. CAMBA Jr., Aileen L. CAMBA / Journal of Asian Finance, Economics and Business Vol 7 No 10 (2020) 523–530

the stock market efficiency (i.e., the weak form efficiency). and Taiwan) were observed for random walks. The unit root
Thus, providing evidence of the existence of random walk in tests concluded that all markets are weak-form efficient
the Philippine stock market is the object of this study. except the markets of Australia and Taiwan. Lean and Smyth
(2007) apply univariate and panel Lagrange Multiplier (LM)
2.  Theoretical Foundation unit root tests with one and two structural breaks to examine
the random walk hypothesis for stock prices in eight Asian
The random walk hypothesis, championed by Louis countries. The results from the univariate LM unit root
Bachelier (1900), states that stock prices are random, like tests and panel LM unit root test with one structural break
the steps taken by a drunk, and therefore are unpredictable. suggest that stock prices in each country is characterized by
The random walk is explained by the efficient market a random walk, but the findings from the panel LM unit root
hypothesis. The efficient market hypothesis states that test with two structural breaks suggest that stock prices in the
financial markets are efficient and that prices already reflect eight countries are mean reverting. Mehmood et al. (2012)
all known information concerning stock prices. There are describe the movement of share prices of companies listed
three forms of the efficient market hypothesis that differ in at Karachi Stock Exchange (KSE) from January 2, 2001 to
what information is considered (Dupernex, 2007; Mehmood, November 15, 2011 with 2672 observations. Simple unit root
Mehmood, & Mujtaba, 2012). Firstly, weak-form efficiency, – Augmented Dickey-Fuller (ADF) and Phillips-Perron (PP)
where past market trading information, such as stock prices, tests – and Johansen Co-integration test findings suggest
trading volume, and short interest are considered. Secondly, that KSE-100 Index follows the Random Walk Hypothesis
semi-strong form efficiency, which extends the information (RWH) and Efficient Market Hypothesis (EMH). Thus, KSE
to public information other than market data, such as news, is an efficient financial market that can adjust to any new
accounting reports, company management, patents, products information efficiently and share prices of listed companies
of the company, and analysts’ recommendations. Thirdly, cannot be predicted. Hence, KSE cannot be beaten to gain
strong form efficiency which extends the information further any abnormal return.
to include not only public information, but also private There are also studies that do not follow the random
information, typically held by corporate insiders, such as walk hypothesis. Hamid, Suleman, Shah, and Akash (2010)
officers and executives of the corporation. conducted a study to check the random walk behavior and
The random walk hypothesis provides a mean to test the weak form efficiency in Asia-pacific region, which includes
weak-form efficiency, hence, non-predictability of financial stock markets of Australia, China, Hong-Kong, India,
markets (Charles & Darné, 2009; Brealey, Myers, & Allen, Indonesia, Japan, Korea, Malaysia, Pakistan, Philippine, Sri
2005; Cuthbertson & Nitzsche, 2004). Given a time series Lanka, Singapore, Thailand and Taiwan. The data uses for
{SPRICEt }Tt =1 , the random walk hypothesis corresponds to the study consists of monthly prices beginning from January
φ = 1 in the first-order autoregressive model: 2004 and ends on December 2009. Autocorrelation, run test,
unit root test, Ljung- box Q-statistic test and variance ratio
SPRICEt = µ + φSPRICEt−1 + εt(1) were used to test the random walk behavior. The results of
the tests show that the monthly return of the Asia-Pacific
where SPRICEt are stock market price, µ is an unknown region stock markets don’t follow the random walk behavior
drift parameter and the error terms εt are, in general, neither and no market is weak-form efficient so investors can predict
independent nor identically distributed (i.i.d.). the prices to earn profits. Omar, Hussain, Bhatti, and Altaf
(2013) investigates the weak form efficiency in Karachi
3.  Literature Review stock exchange consists of daily, weekly and monthly
returns for the period January 01, 1998 to February 29, 2012
3.1.  Using as Basis of the Unit Root Tests to test random walk behavior. They used unit root tests (ADF
and PP tests) and Runs test. The outcome of tests shows that
The following studies confirm the random walk existence KSE does not follow random walk and there are chances
and a weak form market efficiency after applying different for the technical investors that they can earn the abnormal
unit root statistical techniques. Worthington and Higgs profit by identifying the trends in KSE. Rehman et al. (2018)
(2006) investigate the market efficiency in weak-form in research applies multiple unit root tests, Runs Test and State
Asian-pacific stock markets. Daily returns of five developed Space Model. The findings provided sufficient evidence that
markets (Hong-Kong, Japan, New-Zealand, Australia, and the stock prices of KSE 100 Index, S & P BSE 500 Index,
Singapore) and ten emerging (China, Indonesia, India, and CSE All Share Index are not a random walk process and
Korea, Malaysia, Philippines, Pakistan, Sri-Lanka, Thailand weak form inefficient.
 Abraham C. CAMBA Jr., Aileen L. CAMBA / Journal of Asian Finance, Economics and Business Vol 7 No 10 (2020) 523–530 525

3.2.  Using as Basis of the Variance Ratio Statistics framework conducive of transparent corporate governance.
Camba and Camba (2020) study noted the necessity of
Studies using variance ratio have mixed results. Lima and supporting policies that continuously promote a well-
Tabak (2004) tests the random walk hypothesis for China, developed financial infrastructure in order to establish depth
Hong Kong and Singapore. They found that Class A shares in financial services and improve stock market liquidity.
for Chinese stock exchanges and the Hong Kong equity Furthermore, the findings of Al-Homaidi, Tabash, Al-Ahdal,
markets are weak form efficient. However, Singapore and Farman, and Khan (2019) reveal that leverage, return on
Class B shares for Chinese stock exchanges do not follow assets, and firm age are the essential internal determinants
the random walk hypothesis. They explained that liquidity that impact the liquidity of listed firms. Moreover, political
and market capitalization may play a role in explaining stability is also a key factor. Chavali, Alam, and Rosario
results of weak form efficiency tests. In the study of Go and (2020) examine the influence of elections on the stock
Lau (2014), which examines the dynamics of price changes market employing market model event study methodology
and trading volume of Kuala Lumpur Options and Financial for the sample period 2014 to 2019. The findings of the study
Futures Exchange (KLOFFE) from 2000 to 2008, findings reveal that the impact on the market is not the same between
support the Liquidity-Driven Trade hypothesis. In terms any two elections even when the same party comes to power
of investors’ behavior in response to the news, they found for the second time. Thus, a semi-strong form of efficient
that investors are more risk taking in bull market and more market hypothesis holds true in the context of emerging
risk reverse in bear market. Also, uninformed investors with markets like India.
information asymmetry should expect non-informational
trading from informed investors to establish their desired 4.  Research Methodology
positions for better liquid position. Hoque, Kim, and Pyun
(2006) re-examines the random walk hypothesis for eight 4.1.  Unit Root Tests
emerging equity markets in Asia: Hong Kong, Indonesia,
Korea, Malaysia, the Philippines, Singapore, Taiwan, and It is a well-known stylized fact that stock prices are non-
Thailand. The hypothesis is tested with two new variance ratio stationary and are integrated of order 1, (i.e., has a single unit
tests – Wright’s rank and sign and Whang-Kim subsampling root). The first difference of such series is supposed to be a
tests – as well as the conventional Lo-MacKinlay and white noise. The presence of the unit root component can be
Chow-Denning tests. They found that (i) the stock prices of seen as a white noise series (Rufino, 2013; Wang, Chen, &
the eight Asian countries do not follow random walk with Wang, 2018). In this study, we investigated the existence of
the possible exceptions of Taiwan and Korea, and (ii) the random walks by employing the Augmented Dickey-Fuller
accelerated opening of the eight stock markets to foreign (ADF) (Dickey & Fuller, 1981) and Phillips-Perron (PP)
investors following the Asian financial crisis in 1997 has (Phillips & Perron, 1988). The general form of ADF and PP
not significantly altered the mean-reversion patterns of stock tests are as follows (Rehman et al. 2018):
price vis-à-vis relative market efficiency. Likewise, Kim and
Shamsuddin (2008) test for the martingale hypothesis in a q

group of Asian markets using the new multiple variance ratio SPRICEt     SPRICEt 1   j SPRICEt 1   t (2)
tests based on the wild bootstrap and signs. They found that j 1

the Hong Kong, Japanese, Korean and Taiwanese markets

q
have been efficient in the weak-form. The markets of ∆SPRICEt =α + β t + δ SPRICEt −1 + ∑δ j ∆SPRICEt −1 + ε t
Indonesia, Malaysia and Philippines have shown no sign of j =1
market efficiency, despite financial liberalization measures (3)
implemented since the eighties. Also, the Singaporean and
Thai markets have become efficient after the Asian crisis. In ∆SPRICEt =αSPRICEt −1 + xtn δ + ε t (4)
the Middle East markets, Smith (2007) investigates five stock
markets, Israel, Jordan, Kuwait, Lebanon and Oman, using where SPRICEt are stock market price, εt is white noise
the multiple variance ratio test. The hypothesis is rejected in and α = p − 1.
two of the markets, those for Kuwaiti domestic companies
and Oman. For the Israeli, Jordanian, and Lebanese markets, 4.2.  Variance Ratio Test
composite stock price indices follow a random walk or are
weak-from efficient. The variance ratio tests are considered powerful random
In general, the above results point toward the notion walk hypothesis test methodologies. Lo and MacKinlay
that the pricing efficiency of a market depends on the level (1988) initiates the conventional variance ratio test. Later,
of equity market development as well as the regulatory Chow and Denning (1993) modify Lo-MacKinlay’s test
526 Abraham C. CAMBA Jr., Aileen L. CAMBA / Journal of Asian Finance, Economics and Business Vol 7 No 10 (2020) 523–530

to form a simple multiple variance ratio test. Lo and Chow and Denning (1993) extends Lo and MacKinlay’s
MacKinlay (1988) proposed the asymptotic distribution of (1988) conventional variance ratio test methodology and
VR(x; k) by assuming that k is fixed when T → ∞ (Chang form a simple multiple variance ratio test, which uses Lo-
& Ting, 2000; Lock, 2007; Charles & Darné, 2009). If xt is MacKinlay test statistics as the studentized maximum
i.i.d., i.e. under the assumption of homoscedasticity, then modulus (SMM) statistics (Chen, 2008).
under the null hypothesis that V(k) = 1, the test statistic A second approach is available for variance ratio tests of
M1(k) is given by the i.i.d. null. Under this set of assumptions, we may form the
joint covariance matrix of the variance ratio test statistics as
VR ( x; k ) − 1 in Richardson and Smith (1991), and compute the standard
M1 (k ) = 1
(5)
ϕ (k ) 2 Wald statistic for the joint hypothesis that all m variance
ratio statistics equal 1. Under the null, the Wald statistic is
which follows the standard normal distribution asymptotic Chi-square with m degrees-of-freedom (Fong,
asymptotically. The asymptotic variance, φ(k), is given by Koh, & Ouliaris, 1997).
The data of this study consists of the daily closing price
2 ( 2k −1)( k − 1) of the Philippine stock market, over the period January 2015
ϕ (k ) = (6)
3kT to December 2019.
To accommodate xt’s exhibiting conditional
heteroscedasticity, Lo and MacKinlay (1988) proposed the 5.  Results and Discussion
heteroscedasticity robust test statistic M2(k)
5.1.  Descriptive Statistics
VR ( x; k ) − 1
M2 (k ) = (7) Figure 1 describes that for the period covered the
ö* ( k ) 1/ 2
daily closing stock market price ranges from P6,084.28 to
which follows the standard normal distribution P9,058.62 with mean and median of P7,644.65 and P7,721.02,
asymptotically under null hypothesis that V(k) = 1. Chow respectively. Moreover, the Jarque-Bera normality test
and Denning (1993) points out that failing to control the value of 3.3308 with probability = 0.1891 suggests the null
test size for variance ratio estimates result in large Type I hypothesis that residuals are normally distributed cannot be
errors. To control the test size and reduce the Type I errors, rejected.

Figure 1: Histogram and Descriptive Statistics

 Abraham C. CAMBA Jr., Aileen L. CAMBA / Journal of Asian Finance, Economics and Business Vol 7 No 10 (2020) 523–530 527

Table 1: Unit Root Tests

Level First Difference

Test Decision Decision
Intercept Intercept, Linear Trend Intercept Intercept, Linear Trend
ADF -2.7346 -2.9094 Accept -34.8548*** -34.8410*** Reject
PP -2.5493 -2.7355 Accept -35.1123*** -35.0968*** Reject
Note: ADF test was performed using Schwarz information criterion and the automatic lag selection set at 14. PP test was performed with
Bartlett Kernel and Newey-West Bandwidth. Statistical significance: ***(1%), **(5%) and *(10%).

Figure 2: Level and First Difference Plots

5.2.  Unit Root Tests 5.3.  Variance Ratio Tests

Table 1 presents the Augmented Dickey-Fuller (ADF) Assuming that the daily closing stock market price data
and Phillips-Perron (PP) unit root tests results of the daily follow a random walk, so that variances are computed for
closing stock price in constant and linear trend components. differences and assume that the data follow an exponential
At level the results of the ADF and PP indicates non- random walk so that the innovations are obtained by taking
stationarity but at the first difference the daily closing price log differences Table 2 presents the variance ratio test results.
becomes stationary. Thus, with a significance level of 1 Here, the Chow-Denning maximum /z/ statistic of 1.7723
percent, one unit root of the time series cannot be rejected and 1.7762 are associated with the period 16 individual
while the first difference of the series under consideration is test. The approximate p-values of 0.2722 and 0.2701 cannot
stationary, which confirms that the series is likely to be I(1) reject the null of a random walk.
and, thus, meets the necessary condition for a random walk. The results are quite similar for the Wald test statistic
Simply, the daily closing stock price follows a random walk
for the joint hypotheses. The individual statistics generally
during the January 2015-December 2019 period and the
accept the null hypothesis, though the period 16 variance
Philippine stock market is an efficient market (i.e., regarded
ratio statistic p-value of 0.0763 and 0.0757 are significant
as weak-form efficient). These findings are consistent with
the results of Mehmood et al. (2012), Lean and Smyth (2007), at 10% level. Results of the above variance ratio tests
and Worthington and Higgs (2006) that there exists a sense consistently fail to reject the random walk hypothesis.
of randomness among the stock prices. The explanation of That is, empirically establishing the validity of the
the existence of a random walk in weak-form efficiency can efficient market hypothesis in the Philippine stock market.
be attributed to market liquidity (Lima & Tabak, 2004; Go Therefore, the daily stock price follows a random walk
& Lau, 2014; Camba & Camba, 2020) because of policies during the January 2015-December 2019 period and is
that promote continuous development and modernization of considered weak-form efficient. Figure 3 displays the
an equity market (Kim & Shamsuddin, 2008; Rufino, 2013). graph of the variance ratio statistics and plus or minus two
Figure 2 shows that stock price is non-stationary at level and asymptotic standard error bands, along with a horizontal
stationary in its first difference form. reference line at 1 representing the null hypothesis.
528 Abraham C. CAMBA Jr., Aileen L. CAMBA / Journal of Asian Finance, Economics and Business Vol 7 No 10 (2020) 523–530

Table 2: Variance Ratio Test Results

Null Hypothesis: SPRICE is a random walk

Joint Tests Value df Probability
Max |z| (at period 16)* 1.7723 1216 0.2722
Wald (Chi-Square) 4.3131 4 0.3653
Individual Tests
Period Var. Ratio Std. Error z-Statistic Probability
2 0.9991 0.0287 -0.0307 0.9755
4 0.9440 0.0537 -1.0432 0.2969
8 0.8634 0.0848 -1.6108 0.1072
16 0.7763 0.1262 -1.7723 0.0763
Null Hypothesis: Log SPRICE is a random walk
Joint Tests Value df Probability
Max |z| (at period 16)* 1.7762 1216 0.2701
Wald (Chi-Square) 4.6302 4 0.3274
Individual Tests
Period Var. Ratio Std. Error z-Statistic Probability
2 1.0061 0.0287 0.2120 0.8321
4 0.9568 0.0537 -0.8054 0.4206
8 0.8719 0.0848 -1.5100 0.1310
16 0.7758 0.1262 -1.7762 0.0757
*Probability approximation using studentized maximum modulus with parameter value 4 and infinite degrees of freedom.

Figure 3: Graph of the Variance Ratio Statistics

 Abraham C. CAMBA Jr., Aileen L. CAMBA / Journal of Asian Finance, Economics and Business Vol 7 No 10 (2020) 523–530 529

6. Conclusions Chow, K. V., & Denning, K. C. (1993). A Simple Multiple Variance

Ratio Test. Journal of Econometrics, 58, 385-401. https://doi.
This research provides evidence of the existence of org/10.1016/0304-4076(93)90051-6
random walk in the Philippine stock market employing Cuthbertson, K., & Nitzche, D. (2004). Quantitative Financial
the Augmented Dickey-Fuller (1981) and Phillips- Economics (2nd Ed.). Chichester, UK: John Wiley and Sons.
Perron (1988) unit root tests, the Lo-MacKinlay’s (1988) Dickey, D. A., & Fuller, W. A. (1981). Likelihood ratio statistics
conventional variance ratio test and Chow-Denning’s for autoregressive time series with a unit root. Econometrica,
(1993) simple multiple variance ratio test. Results of the 49(1), 1057-1072.
unit root and variance ratio tests consistently indicate that Dupernex, S. (2007). Why Might Share Prices Follow A Random
the null hypothesis of random walk cannot be rejected. Walk? Student Economic Review, 21, 167-179.
Thus, the Philippine stock market is regarded as weak-
Fong, W. M., Koh, B., & Ouliaris, S. (1997). Joint Variance Ratio
form efficient fully reflecting all information contained in Tests of the Martingale Hypothesis for Exchange Rates. Journal
its past prices, which means that studying the behaviors of of Business and Economic Statistics, 1(1), 51-59.
historical prices cannot earn abnormal returns or profits.
Go, Y., & Lau, W. (2014). Asymmetric Information Spillovers
Random walk has been held as a sufficient condition for
between Trading Volume and Price Changes in Malaysian
describing the stock market as efficient, which implies Futures Market. Journal of Asian Finance, Economics and
that investors cannot predict the market returns or Business, 1(3), 5-16. https://doi.org/10.13106/jafeb.2014.vol1.
equivalently, abnormal profits cannot be obtained just by no3.5
knowing the past prices. The implication of weak-form
Hamid, K., Suleman, T. M., Shah, A. Z. S., & Akash, I. S. R.
efficiency is the random walk hypothesis, which indicates (2010). Testing the Weak form of Efficient Market Hypothesis:
that successive price changes are random and serially Empirical Evidence from Asia-Pacific Markets. International
independent. Research Journal of Finance and Economics, 58, 121-133.
http://dx.doi.org/10.2139/ssrn.2912908
References Hoque, H., Kim, J., & Pyun, C. (2006). A comparison of variance
ratio tests of random walk: A case of Asian emerging stock
Al-Homaidi, E., Tabash, M., Al-Ahdal, W., Farman, N., & Khan, markets. International Review of Economics & Finance, 16(4),
S. (2019). The Liquidity of Indian Firms: Empirical Evidence 488-502. https://doi.org/10.1016/j.iref.2006.01.001
of 2154 Firms. Journal of Asian Finance, Economics and
Business, 7(1), 19-27.  https://doi.org/10.13106/jafeb.2020. Kim, J., & Shamsuddin, A. (2008). Are Asian stock markets
vol7.no1.19 efficient? Evidence from new multiple variance ratio tests.
Journal of Empirical Finance, 15, 518-532.  https://doi.
Brealey, R. A., Myers, S. C., & Allen, F. (2005). Corporate Finance org/10.1016/j.jempfin.2007.07.001
(8th Ed.). New York, NY: McGraw-Hill Irwin.
Kwiatkowski, D., Phillips, P. C. B., Schmidt, P., & Shin, Y.
Camba, Jr. A. C., & Camba, A. L. (2020). The Dynamic Relationship (1992). Testing the null hypothesis of stationarity against the
of Domestic Credit and Stock Market Liquidity on the alternative of a unit root. Journal of Econometrics,  54(1-3),
Economic Growth of the Philippines. Journal of Asian Finance, 159-178. https://doi.10.1016/0304-4076(92)90104
Economics and Business, 7(1), 37-46. https://doi:10.13106/
jafeb.2020.vol7.no1.37 Lean, H. H., & Smyth, R. (2007). Do Asian Stock Markets Follow
a Random Walk? Evidence from LM Unit Root Tests with One
Chang, K., & Ting, K. (2000). A Variance Ratio Test of the and Two Structural Breaks. Review of Pacific Basin Financial
Random Walk Hypothesis for Taiwan’s Stock Market. Markets and Policies, 10(1), 15-31. https://doi.org/10.1142/
Applied Financial Economics, 10, 525-32. https://doi. S0219091507000933
org/10.1080/096031000416406
Lean, H. H., Mishra, V., & Smyth, R. (2015). The Relevance of
Charles, A., & Darné, O. (2009). Variance ratio tests of random Heteroskedasticity and Structural Breaks When Testing for a
walk: An overview. Journal of Economic Surveys, 23(3), 503- Random Walk With High-Frequency Financial Data: Evidence
527. from ASEAN Stock Markets. In: Gregorious, G (eds). The
Chavali, K., Alam, M., & Rosario, S. (2020). Stock Market Handbook of High Frequency Trading. Singapore: Elsevier.
Response to Elections: An Event Study Method. Journal of https://doi.org/10.1016/B978-0-12-802205-4.00004-X
Asian Finance, Economics and Business, 7(5), 009-018. https:// Lima, E., & Tabak, B. (2004). Tests of the random walk hypothesis
doi.org/10.13106/jafeb.2020.vol7.no5.009 for equity markets: evidence from China, Hong Kong and
Chen, J. (2008). Variance Ratio Tests of Random Walk Hypothesis of Singapore. Applied Economics Letters, 11(4), 255-258. https://
the Euro Exchange Rate. International Business & Economics doi.org/10.1080/13504850410001674911
Research Journal, 7(12), 97-106. https://doi.org/10.19030/iber. Lo, A. W., & MacKinlay, A. C. (1988). Stock market prices do not
v7i12.3318 follow random walk: Evidence from a simple specification
 530 Abraham C. CAMBA Jr., Aileen L. CAMBA / Journal of Asian Finance, Economics and Business Vol 7 No 10 (2020) 523–530

test. The Review of Financial Studies, 1, 41-66. https://doi. Richardson, M., & Smith, T. (1991). Tests of Financial Models
org/10.1093/rfs/1.1.41 in the Presence of Overlapping Observations. The Review of
Lock, D. B. (2007). The Taiwan stock market does follow a random Financial Studies, 4(2), 227-254.
walk. Economics Bulletin, 7(3), 1-8. Retrieved February 11,
Rufino, C. (2013). Random walks in the different sub-markets of
2020, from https://core.ac.uk/download/pdf/6310232.pdf
the Philippine Stock Exchange amid modernization. Philippine
Mehmood, M. S., Mehmood, A., & Mujtaba, B. G. (2012). Stock Review of Economics, 19(1), 57-82.
Market Prices Follow the Random Walks: Evidence from the
Efficiency of Karachi Stock Exchange. European Journal of Smith, G. (2007). Random walks in Middle Eastern stock markets.
Economics, Finance and Administrative Sciences, 51, 71-80. Applied Financial Economics, 17(7), 587-596.  https://doi.
Omar, M. M., Hussain, H., Bhatti, G. A., & Altaf, M. (2013). org/10.1080/09603100600911200
Testing of random walks in Karachi stock exchange. Finance Wang, N., Chen, Y. B., & Wang, B. (2018). Normality of the Stock
Management, 54, 12293-12299.
Index Futures of China. Journal of Mathematical Finance, 8,
Phillips, P. C., & Perron, P. (1988). Testing for a unit root in time 86-101. https://doi.org/10.4236/jmf.2018.81007
series regression. Biometrica, 75(1), 335-346.
Worthington, A. C., & Higgs, H. (2006). Weak-form market
Rehman, S., Kashif, M., Chhapra, I. U., & Rehan, R. (2018). Are
Stock Prices a Random Walk? An Empirical Evidence of Asian efficiency in Asian emerging and developed equity markets:
Stock Market. Etikonomi: Jurnal Ekonomi, 17(2), 237–252. Comparative tests of random walk behavior. Accounting
http://dx.doi.org/10.15408/etk.v17i2.7102 Research Journal, 19(1), 54-63.

View publication stats