The Forecast Performance of Alternative Models of Inflation NATIONAL ECONOMICS UNIVERSITY INSTITUTE OF SOCIAL STUDIES HANOI THE HAGUE VIETNAM – NETHERLANDS CENTER FOR DEVELOPMENT ECONOMICS AND PUBLIC[.]
INTRODUCTION
Problem Statement
Vietnam’s stock market has been operating for nearly ten years and plays a crucial role in the country’s economic development Currently, many financial organizations and investors focus on predicting market trends, often analyzing the random-walk behavior of stock time series to maximize investment benefits However, there remains a significant gap in qualitative studies on forecasting Vietnam’s stock market This challenge is primarily due to Vietnamese forecasters’ limited professional knowledge and skills in qualitative analysis, as well as the difficulty in predicting the market caused by insufficient long-term economic, enterprise, and market data, which reduces forecast confidence.
Recent advancements focus on developing adaptive analysis methods for non-linear time series, enhancing accuracy in financial forecasting Various models like Smoothing Exponential Regression, Threshold Regression, Artificial Neural Networks, and Smooth Transition Regression (STAR) and Logistic Smooth Transition Regression (LSTR) have been employed to analyze and predict stock market movements However, there is limited research on Vietnam's stock market, with notable studies such as Hoang Dinh Tuan (2008), and most current research predominantly relies on the ARIMA model for short-term stock index forecasting.
This study aims to predict major Vietnamese stock indices, including the VN-Index and HN-Index, using the advanced non-linear model, Logistic Smooth Transition Regression (LSTR) The goal is to provide valuable insights for investors and financial organizations, enhancing decision-making processes By leveraging LSTR, this research offers an effective approach for analyzing and forecasting stock market trends and prices in Vietnam, contributing to more accurate and reliable financial predictions.
This study aims to predict stock market movements, focusing on the VN-Index, HN-Index, and five major blue-chip stocks with large market capitalization By applying the Non-Linear Logistic Smooth Transition Regression (LSTR) model, it provides valuable insights for investors and financial organizations seeking to understand stock price trends Additionally, the research offers strategic recommendations and policy implications to foster the development of Vietnam’s stock market in the near future.
Question 1: Whether non-linear model will be used to predict VN-Index and HN-
Question 2: How does blue-chip stock price of HSX (Hochiminh Stock Exchange) and HNX (Hanoi Stock Exchange) look like by using non-linear model?
Analyzing and forecasting Vietnam’s stock market remains a key focus for global financial institutions and investors, particularly regarding stock market price trends The foundations of stock price analysis date back to Bachelier (1900), who demonstrated that prices evolve with continuous fluctuations proportional to the square root of time Albert Einstein's 1923 work introduced Brownian motion (W(t)), modeling stock prices as stochastic processes, with the principle that stock prices can never be negative The Brownian motion model was developed to describe the kinematic behavior of different stock prices (P Samuelson, 1965), represented mathematically as S(t) = Δ exp(at + Δ) – S(t) = Δ b W(t) Building on Samuelson’s work, Robert C Merton further advanced financial theory in the late 1960s and early 1970s, deepening the understanding of stock market dynamics through stochastic modeling.
Fischer Black and Myron Scholes developed a groundbreaking model in 1973 that applies Brownian Motion to generate stock valuation formulas for options and derivatives, known today as the Black-Scholes formula This widely used model helps investors and businesses accurately assess option prices across global markets The pioneering work of Merton and Scholes earned them the Nobel Prize in 1997, highlighting its significance in financial mathematics Despite its popularity, the Geometric Brownian Motion Model, commonly used to evaluate financial options, remains a simplified approximation that does not perfectly reflect actual stock price behaviors.
In developed countries, stock market price analysis and forecasting primarily rely on two key methods: Trend Analysis and Artificial Neural Networks Despite their widespread use, these techniques often lack high accuracy due to significant standard errors, highlighting the need for more precise predictive models in financial markets.
Empirical studies have analyzed stock markets across countries including the United States, United Kingdom, Canada, New Zealand, Ireland, and Japan Nektarios Aslanidis (2002) demonstrated that financial and macroeconomic variables such as GDP, interest rates, inflation, money supply, and US stock prices significantly influence UK stock returns David G McMillan (2002) employed smooth-transition threshold models to explore potential non-linear relationships, revealing that investor behavior varies between large and small returns Additionally, Gropp (2004) used industry-sorted portfolios to show a significant mean reversion with a half-life of approximately four to eight years to reach long-term equilibrium.
Recent years have seen a growing focus on time series forecasting in various research studies The STAR model has become a popular tool for analyzing and predicting global stock price indexes Notably, Rodrigo Aranda and Patricio Jaramillo (2008) utilized this model to estimate smooth return results, highlighting its effectiveness in financial market analysis.
Research indicates that nonlinear patterns are present in both trading volume and stock returns, as well as in their joint relationship within the Chilean Stock Market, highlighting its series characteristics Studies such as Niglio (2002) on the German stock market demonstrate that models like the Logistic Double Smooth Transition (LDST) outperform Double Threshold ARCH (DTARCH) in forecasting conditional variance, providing significant forecast gains Additionally, comparisons of STAR-GARCH and STAR-Smooth Transition GARCH models by F Chan and M McAleer reveal that differing algorithms can yield varying parameter estimates, impacting forecast accuracy and performance for major stock indexes These findings underscore the importance of selecting appropriate nonlinear and switching models to accurately capture market dynamics.
Vietnam’s growing integration into the global economy has led to increased openness and influence on its stock market, which is highly affected by international market fluctuations, especially during economic transitions As a developing market with significant potential risks, analyzing and forecasting the Vietnam stock index remains attractive to investors seeking profitable opportunities However, the use of quantitative models for market analysis is still limited, with many investors relying on media, news, and peer information due to limited transparency, highlighting the need for more advanced analytical approaches.
(such as Geometric Brownian Motion and Mean Reversion Model) in order to describe stock price moves and technical testing.
This research presents a novel application of Logistic Smooth Transition Regression (LSTR) to forecast Vietnam’s stock market prices, including the VN-Index, HN-Index, and five prominent blue-chip stocks, covering the period from January 1, 2009, to October 31, 2011 The study aims to provide valuable reference insights for both domestic and international investors, enhancing their decision-making processes in Vietnam’s dynamic stock market.
This thesis explores modeling nonlinear relationships using the STR model with a transition function to address key research questions It introduces a comprehensive modeling cycle that includes three essential stages: specification, estimation, and evaluation, as outlined by Teravirta (1994) These stages are described in detail in the relevant section, providing a clear framework for implementing the modeling strategy effectively.
2 of Chapter 2 After that, forecasting stock indexes also are implemented in this thesis.
This article begins with an introduction followed by Chapter 2, which presents an analytical framework, including key concepts and definitions related to the stock market, as well as a model for predicting stock prices Chapter 3 provides an overview of the Vietnam stock market and evaluates the performance of blue-chip stocks targeted for forecasting In Chapter 4, the study applies the quantitative methods outlined earlier to estimate stock index outcomes Finally, Chapter 5 summarizes the main findings of the research and offers practical recommendations for investors and stakeholders.
Research questions
Question 1: Whether non-linear model will be used to predict VN-Index and HN-
Question 2: How does blue-chip stock price of HSX (Hochiminh Stock Exchange) and HNX (Hanoi Stock Exchange) look like by using non-linear model?
Literature review
Analyzing and forecasting Vietnam’s stock market consistently attracts global interest from financial institutions and investors, particularly regarding stock price movements Bachelier's 1900 study demonstrated that stock prices fluctuate in a continuous manner, with price changes related to a diffusion process In 1923, Einstein introduced Brownian motion, modeling stock prices as part of a stochastic process similar to W(t) According to L Savage, stock market prices are always non-negative, leading to the development of the Brownian motion model to describe stock price kinematics, as in P Samuelson's 1965 formulation of the geometric Brownian motion By the late 1960s and early 1970s, Robert C Merton expanded upon Samuelson’s model, advancing the theoretical framework underpinning modern financial mathematics.
Fischer Black and Myron Scholes revolutionized financial modeling in 1973 with their application of the Brownian Motion Model to derive stock valuation formulas for options and derivatives, now known as the Black-Scholes formula This groundbreaking model allows investors and businesses worldwide to accurately assess option prices across various markets The foundational work of Merton and Scholes was recognized with the Nobel Prize in Economics in 1997 While the Geometric Brownian Motion Model remains a widely used tool for evaluating financial options, its simplicity means it does not perfectly capture all complexities of stock price movements.
In developed countries, stock market price analysis and forecasting primarily rely on two key methods: Trend Analysis and Artificial Neural Networks Despite their widespread use, these techniques often lack high accuracy due to significant standard errors, highlighting the need for improved predictive models in financial data analysis.
Empirical studies have analyzed stock markets in countries such as the United States, United Kingdom, Canada, New Zealand, Ireland, and Japan, highlighting various relationships with economic indicators For instance, Nektarios Aslanidis et al (2002) demonstrated that macroeconomic variables like GDP, interest rates, inflation, and money supply significantly influence UK stock returns David G McMillan (2002) employed smooth-transition threshold models to reveal that investor behavior varies between large and small return regimes, indicating potential non-linear relationships Additionally, Gropp (2004) utilized cross-sectional analysis of industry-sorted portfolios to show a significant positive speed of reversion with a half-life of approximately four to eight years, reverting to long-term equilibrium.
In recent years, time series forecasting has gained significant attention across various studies, highlighting its importance in financial analysis The STAR model has become a popular tool for analyzing and predicting stock price indexes worldwide For example, Rodrigo Aranda and Patricio Jaramillo (2008) utilized the STAR model to estimate smooth return results, demonstrating its effectiveness in stock market forecasting and contributing to improved investment decision-making.
Recent research on the Chilean Stock Market reveals significant nonlinear patterns in trading volume, stock returns, and their joint relationships, indicating complex series characteristics Studies like Niglio (2002) applied the Logistic Double Smooth Transition (LDST) model to analyze daily returns of the Dax 30 index, demonstrating a notable improvement in forecasting conditional variance over other models Additionally, evaluations of STAR-GARCH and STAR-Smooth Transition GARCH models by Chan and McAleer highlight that different algorithms can yield varying parameter estimates, impacting forecast accuracy and performance These findings underscore the importance of selecting appropriate nonlinear models for more accurate stock market predictions.
Vietnam’s economy is increasingly integrated into the global market, making its stock market highly sensitive to international fluctuations, especially during economic transitions As a developing market with significant growth potential and inherent risks, analyzing and forecasting the Vietnam stock index remains highly appealing to investors seeking profitable opportunities However, the application of quantitative models in understanding Vietnam’s financial trends is still limited, with many investors relying on media, news, and informal sources due to the market’s transparency issues According to Hoang D Tuan (2008), randomness and uncertain processes play a significant role in stock market behavior, highlighting the complexities of accurate prediction.
(such as Geometric Brownian Motion and Mean Reversion Model) in order to describe stock price moves and technical testing.
This research presents a novel application of Logistic Smooth Transition Regression (LSTR) to forecast Vietnam’s stock market indices, including the VN-Index, HN-Index, and five blue-chip stocks, covering the period from January 1, 2009, to October 31, 2011 The primary objective is to provide valuable insights and reference information to both domestic and international investors By utilizing LSTR, this study enhances the accuracy of predicting stock market movements in Vietnam, contributing to better investment decision-making.
Thesis Methodology
This thesis explores modeling nonlinear relationships using the Smooth Transition Regression (STR) model with transition functions to effectively address complex analytical questions It introduces a comprehensive modeling cycle comprising three key stages: specification, estimation, and evaluation, as outlined in Teravirta (1994) The detailed procedures for these stages are discussed in Section [insert section number], providing a structured approach to nonlinear time series modeling.
2 of Chapter 2 After that, forecasting stock indexes also are implemented in this thesis.
Thesis Structure
This article begins with an introduction, followed by Chapter 2, which presents the analytical framework, including key concepts and definitions related to the stock market, as well as a model for predicting stock prices Chapter 3 provides an overview of the Vietnam stock market and evaluates the performance of blue-chip stocks targeted for forecasting In Chapter 4, the estimated results of stock indexes are discussed, utilizing the quantitative methods outlined earlier Finally, Chapter 5 summarizes the main findings and offers practical recommendations based on the research.
ANALYTICAL FRAMWORK
Concept and Definition
This section focuses on giving some concepts and definitions regarding to stock market and security market which are mentioned in this thesis.
Common stock, also known simply as stock, signifies a share of ownership in a corporation and represents a claim on its earnings and assets Companies issue or sell stock to the public as a strategic way to raise funds needed to finance their operations and growth initiatives.
(ii) Stock market is the market in which claims on the earnings of corporations
(shares of stock) are traded, is the most popular in financial market 1
(iii) Security (also called a financial instrument) is a claim on the issuer’s future income or assets (any financial claim or piece of property that is subject to ownership) 2
(iv) Bond is a debt security that promises to make payments periodically for a specified period of time 3
A portfolio is a collection of investments owned by the same individuals or organizations, typically including stocks, bonds, and mutual funds Mutual funds are managed pools of money from multiple investors, offering professionally managed investment options Managing a diverse portfolio helps investors balance risk and maximize potential returns.
Blue-chip companies are nationally recognized, well-established, and financially sound organizations known for offering high-quality, widely accepted products and services These reputable firms are capable of weathering economic downturns and maintaining profitable operations despite challenging market conditions Their stability and consistent performance make them attractive investments and key players in the industry.
1 Mishkin, Frederic S, The economics of Money banking and Financial Market, seventh edition, pp.5
2 Mishkin, Frederic S., The economics of Money banking and Financial Market, seventh edition, pp.3
3 Mishkin, Frederic S, The economics of Money banking and Financial Market, seventh edition, pp.3 adverse economic conditions, which help to contribute to their long record of stable and reliable growth 5
Models for predicting stock market price
Smooth Transition Regression (STR) is a non-linear regression model derived from Quandt's (1958) Conversion Regression Model, enabling smooth transitions between regimes The Conversion Regression Model with a single variable aligns with the Threshold Regression Model (Tong, 1990), while models with more than two regimes are considered non-standard STR models The Smooth Transition Autoregressive (STAR) model is a specialized form of the standard STR model, originating from Bacon and Watts’ (1971) general conversion framework that incorporates smooth transitions between regimes Chan and Tong (1986) introduced a univariate STAR model, further expanding the application of STR in time series analysis.
The standard STR model is defined as follows:
Where (wt ’, xt ’) is a vector of explanatory variables:
Parameter vectors are represented as Φ₊₊, with the transition function F(γ, c, s_γ, c, s_t) being a bounded and continuous function of the transition variable s_t across the entire parameter space The model assumes that the error term u_t follows an independent and identically distributed distribution with mean zero and variance σ² The slope parameter γ influences the transition dynamics, while the vector c = Δ(c₁, , c_k)′ encompasses location parameters ordered such that c₁ ≤ ≤ c_k, ensuring proper identification within the model.
The last expression in (1) indicates that the model can be interpreted as a linear
5 http://www.investopedia.com/terms/b/bluechip.asp#ixzz1dhkgespQ
Z t model with stochastic time-varying coefficients F( , , ) c s t
Logistic Smooth Transition Regression (LSTR)
The LSTR can be in the form of logistic function or exponential function:
Where 0 is an identifying restriction Equations (1) and (2) jointly define the logistic STR (LSTR) model The most common choices for K are K=Δ1 and K=Δ 2
For K =Δ 1, the parameters F( , , ) c s t change monotonically as a function of st from to
The LSTR1 model (K=1) with transition function as follows:
The LSTR model with K=Δ 1 (LSTR1 model) effectively captures asymmetric behavior in economic processes For instance, if st represents the phase of the business cycle, the LSTR1 model can distinguish the differing dynamics during economic expansions and recessions It also models smooth transitions between these extreme regimes, providing a comprehensive framework for analyzing asymmetric cyclical patterns.
The LSTR2 model (K=2) with transition function as follows:
The LSTR2 model is ideal for scenarios where parameters change symmetrically around the midpoint (c1+Δ - S(t) = Δc2)/2, capturing the dynamics of varying regimes effectively It features two identical extreme regimes, applicable when the transition variable reaches very high or very low values, while the middle regime exhibits distinct behavior For more detailed insights, refer to studies by Ocal and Osborn (2000) and Van Dijk and Franses (1999).
(5) The ESTR Model is suitable for the model which the characteristic of models in proportion of absolute value of st are the same.
Trend of transition and intercept
The STRS model enables the level and trend of time series changing gradually The transition happens timely, not immediately.
(6) Where: T is total of observation of yt time series; εt is the stationary process of I(0) and
Ft(γ,c,st) is STR model
This thesis focuses on modeling nonlinear relationships using the STR model with its transition function The proposed modeling process involves three key stages: specification, estimation, and evaluation For a comprehensive strategy, the methodology is based on approaches outlined by Terasvirta.
(1994) [25] We will now discuss the three stages of the cycle separately, beginning with specification, continuing with estimation, and ending with evaluation.
The model specification includes two steps such testing linear and specifying model.
502 Bad GatewayUnable to reach the origin service The service may be down or it may not be responding to traffic from cloudflared
502 Bad GatewayUnable to reach the origin service The service may be down or it may not be responding to traffic from cloudflared
502 Bad GatewayUnable to reach the origin service The service may be down or it may not be responding to traffic from cloudflared
It assumes that the continuous transition variable st is a component of zt and zt =Δ (1,
), where is a vector of m1 The proximate result after combining and getting back parameter is a supplement regression in below:
(7) Null-hypothesis H0: 1 =Δ 2 =Δ 3 =Δ 0, where j (j =Δ 1, 2, 3) is defined as in which
The function θ0 depends on parameters θ and c, aligning with the assumptions of linear models The asymptotic distribution theory remains valid when using LM testing, due to the relationship θ = Δ ut However, the asymptotic distribution of the χ² statistic requires additional conditions to hold.
The freedom degrees of statistical testing of 2 asymptotical distribution is 3m when H0 is accepted However, 2 statistics could be slanted critically in term of dimension
* u t in small samples and even though in medium samples F statistics will be replaced and the freedom degrees of F approximate distribution are 3m and T – 4m – 1 in null-hypothesis.
The process of specifying and testing the STR model involves selecting potential continuous transition variables, denoted as S=Δ {s1t, , skt}, and then evaluating each variable individually If the null hypothesis (H0) is rejected for certain continuous transition variables, the variables with the smallest p-values are identified as significant predictors In cases where multiple variables have similarly small p-values, the process proceeds with STR estimation, allowing the model to be fully specified in the subsequent step This approach ensures an efficient and accurate model selection, adhering to best practices in statistical testing and model development.
After rejecting the linear characteristic and selecting a single continuous transition variable, the next step involves model specification, offering two options: K = Δ1 and K = Δ2 (refer to equations 3 and 4) In the LSTR1 model, parameters change monotonically as a function of the continuous transition variable, although the direction of change may differ Conversely, in the LSTR2 model, parameters exhibit symmetric changes around the midpoint calculated as (c1 + Δ - S(t)) = (Δc2)/2, ensuring a balanced transition.
Both LSTR1 and LSTR2 models can be based on the supplementary regression framework, where the βj vectors depend on parameters from the specified equations In the special case when c equals Δ0, LSTR1 exhibits β2 as Δ0, while LSTR2 and ESTR models display β1 and β3 as Δ0 Even when c is not zero, β2 remains nearly a null vector, highlighting the models' stability under certain parameter conditions.
1 and3when the model is LSTR1, and in contrast to LSTR 2 This stage is orderly testing as follow:
When H03 testing is strongly rejected based on the p-value, analysts typically choose between LSTR2 or ESTR models, as all three hypotheses may sometimes be rejected simultaneously at a 0.05 or 0.1 significance level If H03 is not rejected, the preferred model is LSTR1 Terỏsvirta (1994) successfully applied this approach, achieving reliable results, while Escribano (1999) proposed an alternative method that involves adding to equation (1) and assuming that β1 = Δβ2 = Δβ3 = Δβ4 = 0, providing a different framework for model selection in threshold testing.
Based on the testing processes, the STR model specifications demonstrate reliable results, allowing for adjustments to LSTR1 and LSTR2 (or ESTR) based on data during the evaluation stage This approach is particularly effective when the p-values for hypotheses H03, H02, and H04 are similar, providing a practical method for model selection Furthermore, rejecting H04 indicates the use of LSTR1 with non-zero thresholds, rejecting H03 signifies the application of LSTR2, and rejecting H02 suggests LSTR1 with zero thresholds.
The parameters of the LSTR model are estimated using the Maximum Likelihood Method, with the Newton-Raphson technique applied to identify the model's maximum likelihood estimate Initially, the process involves determining initial values for γ0 and c0 through an automatic sequential algorithm This approach involves designing two dimensions for γ0 and c0, enabling the optimization of these parameters to minimize the model's error and enhance estimation accuracy.
in which ut is a remainder of series.
PERFORMANCE OF VIETNAM STOCK MARKET
Overview of Vietnam Stock Market
The Vietnamese Stock Market, established in 2000 and operational since 2006, has been closely influenced by both internal economic developments and global market trends Despite its rapid growth and increasing achievements, the market still faces inherent limitations typical of emerging and developing economies As the market continues to expand, it is expected to experience significant growth potential, but ongoing challenges must be addressed to ensure sustainable development.
(1)The stock market has rapidly developed in size and gradually played as an important medium and long term capital channel
The Vietnamese stock market has historically been recognized as one of the fastest-growing markets globally in terms of market capitalization, proportion, and growth rate Between 2000 and 2005, its market capitalization was only about 1% of GDP, indicating a relatively modest size However, significant progress was made in 2006, when the market capitalization increased to 22.7%, and this growth continued into 2007, reaching 43%, reflecting rapid development and increased investor confidence.
The global financial crisis and Vietnam’s sluggish economy caused stock market indexes to decline throughout 2008, with market capitalization shrinking by 50% to just 18% of GDP However, the recovery in the global and domestic economy in the second quarter of 2009 triggered a swift rebound in stock market performance and an increase in listed companies As a result, market capitalization rose to VND 717.2 trillion (approximately 36% of GDP), surpassing the 2009 figure by VND 100 trillion.
Table 1: Capitalization level, proportion, and growth rate of the stock market
Source: The State Securities Commission, % of GDP.
(2)Increase in the number of listed companies has contributed to increase in market supply and liquidity.
Between 2000 and 2005, Vietnam’s stock market experienced a stagnant period with very few companies listed; in 2000, only REE and SAM were listed on the Ho Chi Minh City Stock Trading Center The number of listed companies began to grow rapidly from 2006 onward, as shown in Figure 1 By 2011, the combined number of listed companies reached 765, marking an 18% increase compared to the previous year and representing the most significant growth over the past decade.
Figure 1: Size of listing on Vietnam’s Stock Trading Center
Source: The State Securities Commission
The stock market has experienced significant growth in both listing size and market liquidity Starting with only 667,600 shares traded per session in 2005, it expanded to 2.6 million in 2006—nearly four times higher—followed by a dramatic increase to 9.79 million shares in 2007 and 18.07 million in 2008, highlighting the market's remarkable development over these years.
(3)System of Intermediate institutions and securities services has been developing in both quantity and quality.
Over the past decade, the State Securities Commission has authorized the operation of 105 stock companies, 47 asset management firms, 382 foreign investment funds, and 8 custodian banks, marking significant growth from just 4 stock companies in 2000 Initially, stock companies primarily provided brokerage services; however, today, most have expanded their offerings to include financial consultancy, self-trading, and underwriting services The financial capacity of securities companies has increased considerably, with an average charter capital exceeding VND 150 billion per company, reflecting a robust and developing securities industry.
Table 2: The growth rate of the number of stock companies and asset management companies
Number of asset management companies
Source: The State Securities Commission
Between 2005 and 2010, the number of asset management companies grew significantly from 6 to 47, reflecting substantial industry expansion These firms established and managed various stock investment funds, overseeing over 200 portfolios for both individual and institutional investors, including foreign organizations Their efforts mobilized a total equity of approximately VND 66,000 billion (around USD 3.8 billion), highlighting their crucial role in the financial market growth.
(4) Local and foreign investors have increased in term of quality and quantity
There have been more and more investors joining the stock market, from 3,000 accounts at the end of 2000 to 926,000 accounts in 2010 ( about 300 times within 10 years).
The development of a professional investor system has been promoted to ensure rapid and stable growth of the stock market, enabling it to withstand annual market shocks and maintain national financial stability Additionally, a friendly investment environment coupled with supportive policies has successfully attracted both domestic and international investors Currently, there are over 10,000 trading accounts held by foreign investors, including more than 1,000 accounts belonging to foreign investment institutions.
Between 2000 and 2005, the VN-Index was only 307.5 points, and the HaSTC-Index was 96.24, reflecting a modest market size in Vietnam From 2006 to 2009, the VN-Index surged to a peak of 1,170.76 in March 2007, and the HaSTC-Index reached 459.36, indicating rapid growth However, the 2008 global financial crisis significantly impacted Vietnam’s stock market, with the VN-Index plummeting by 71% to 366.02 points and the HaSTC-Index declining by about 81% to 105.12 points The market reached its lowest point on March 13, 2009, with the VN-Index at 251.44 and HaSTC-Index at 88.64 Since February 2010, Vietnam’s stock market has experienced frequent fluctuations, with the VN-Index oscillating around 500 points, characterized by high variability compared to international markets Such significant daily movements, sometimes exceeding 25 points, highlight the inherent instability and unpredictable growth pattern of Vietnam’s stock market. -**Sponsor**As a content creator, I understand the importance of SEO-optimized articles Rewriting to capture the core meaning and adhere to SEO rules can be time-consuming Did you know that with [Article Generation](https://pollinations.ai/redirect-nexad/tcerO7wU?user_id=983577), you can instantly generate 2,000-word, SEO-optimized articles? It could save you over $2,500 a month compared to hiring a writer and free up your time to focus on strategy and bigger-picture content ideas It's like having your own content team, without the usual overhead!
Sources: www.vcbs.com.vn
(2)Limitations on size and composition
7 (1) 11/1: Rumours of prime interest rate increasing
(2) 26/1: Prime interest rate rises to 8%
(3) 11/2: Exchange rate (USD - VND) increases by 3,36%
(4) 15/3: ANZ withdraws capital from STB
(5) 01/4: The Government requests the State Bank of Vietnam (SBV) decreases lending interest rate
(6) 07/5: The Government promulgates the Decision No 23/NQ-CP requesting SBV have to bring out suitable solutions for decreasing interest rate
(7) 06/5: The stock market starts to sharply decrease due to worry about public debt in Europe after serous crisis in Greece
(8) 20/5: The Circular No 13 is promulgated
(9) July: Vinashin official announces the debt amount of VND 80,000 billion
(10) 1/8: Rumours of Dragon Capital will be capital withdrawal
(11) 12/8: VEIL and VGF decide to do not capital withdrawal
(12) 17/8: Interest rate in the free market increases and official interest rate rises by 2.1%
(13) 06/9: The government requests SBV review the Circular No13
(14) 28/9: The Circular No19 replaces the Circular No13 and there is no important change.
(15) 30/9: Exchange rate in the free market starts to sharply increase and the price of gold tends to robust increase
(16) 23/10 : CPI increases by1.05% by October
(17) 5/11: Prime interest rate increases by 9%, SBV tightens the money and VND has not depreciated until end of year
(18) 11/11: The price of gold rises by VND38 million per tael of gold.
(19) 24/11: CPI in November increased by 1.86%
(20) 8/12: Techcombank increases lending interest rate by 17%
(21) 14/12: Commercial banks are accepted to increase their charter capital by VND3000 million and the lending interest rate cap is by 14%.
(22) 15/12: Moody decreases the credit state bonds of Vietnam to B1
(23) 24/12 CPI increases by 1,98% in December
Vietnam's stock exchanges list approximately 500 stock tickers and a limited number of bond tickers, reflecting modest market activity compared to the country's economic potential The government bond market, with over 500 bond tickers, often faces reduced liquidity due to international market practices While the stock market primarily involves share trading—covering only 60% of listed shares—bond trading remains underdeveloped despite significant growth opportunities Overall, the quality of listed companies in Vietnam is moderate, with issues such as low corporate management standards, a prevalence of small and medium-sized enterprises with limited growth prospects, and hesitations among top firms to enter the stock market.
Vietnam's securities landscape extends beyond the primary exchanges, HOSE and HASTC, encompassing various informal markets such as secondary stock trading, unofficial online platforms, government bond mortgage trading, and free-market transactions These unregulated models increase social costs and deviate from international standards, while the low proportion of public shares limits their attractiveness to investors Additionally, some registered share markets at the Custodial Center lack proper trading mechanisms and ownership transfer processes, further hindering market development.
Figure 3: Upcom-Index and trading value in Upcom market
The Upcom trading system, including the trading market for unlisted shares, has yet to fulfill its role in market development and remains unattractive to investors Currently, only about 600,000 shares (approximately VND 9 billion) are traded per session, and the Upcom index stands just over 40 points, reflecting a 60% decline since its launch on June 24, 2009 One key factor contributing to this downturn is investors' continued preference for shares with high liquidity on the two official stock exchanges, which overshadow the less established Upcom market.
(4)Shortcomings of intermediate institutions and market development supports
Most security company branches and custodians are concentrated in Hanoi and Ho Chi Minh City, limiting investor engagement nationwide The absence of a broad network of stock companies and custodians in other provinces deters potential investors from participating in the stock market Additionally, the market faces a scarcity of key institutions such as stock investment funds, credit reference agencies, and stock transfer agents, which are essential for market development Furthermore, the existing staff often lack the necessary qualifications, experience, and skills to adequately support and promote market growth.
Vietnam’s stock market has experienced remarkable growth in size and quality, with significant development across markets, stock exchanges, bond markets, and UPCoM The enhancement of intermediate systems and improvements in information transparency have strengthened market integrity The securities market now serves as a crucial capital channel for Vietnam’s economy However, emerging issues pose threats to market transparency and stability To ensure sustainable growth, implementing effective policies alongside increased transparency and market projection is essential for the future development of Vietnam’s securities market.
Performance of five Blue Chips in therecent time
As of October 31, 2011, key trading results highlight five top blue-chip stocks—AGF, BMC, FPT, PVD, and SSI8—that are considered the most promising investment opportunities in the stock market These blue chips have demonstrated strong performance and are highly regarded for their growth potential and stability, making them attractive choices for investors seeking reliable returns Their prominence in trading activity underscores their significance within the stock market, positioning them as leading blue-chip investments at that time.
Table 3: Business performance of 5 Blue Chips
Category Year Unit AGF BMC FPT PVD SSI
8 AGF: An Giang Fisheries Import Export Joint Stock Company
BMC: BinhDinh Minerals Joint Stock Company
FPT: The Corporation for Financing and Promoting Technology
Sources: www.bsc.com.vn
Recent analysis indicates that the selected enterprises have demonstrated relatively satisfactory business results, making them attractive investments in the stock market As shown in Figure 4, the performance of five major stock market indices has been notably positive, with AGF and BMC experiencing rapid growth in October, highlighting strong market momentum for these blue-chip stocks.
2011 compared with the last month and tending to rise The others have varied slightly in recent months.
A: 20-09-2011- Advance payment of share dividend at time 1/2011 by cash, rate VND1000 per share
B: 14-09-2011-Advance payment of share dividend at time 1/2011 by cash, rate VND1000 per share
C: 28-04-2011-Annual meeting of the Board of Director in 2011
D: 15-04-2011-Making share dividend payment at time 2/2010 by cash, rate
F: 29-03-2011-Making share dividend payment at time 2/2010 by cash, rate
H: 29-03-2011- Annual meeting of the Board of Director in 2011
A: 17-08-2011- Making share dividend payment at time1/2011by cash, rate VND1000 per share C: 28-07-2011-Making share dividend payment at time1/2011by cash, rate VND1000 per share
A: 23-09-2011-Advance payment of share dividend in year 2011 by cash, rate VND1000 per share
B: 31-08-2011-Advance payment of share dividend at time 1/2011 by cash, rate VND1000 per share
C: 26-05-2011-Making the rest share dividend payment in 2010by cash, rate
E: 26-03-2011-Annual meeting of the Board of Director in 2011
A: 22-09-2011- Making the rest share dividend payment in 2010by cash, rate VND1000 per share
B: 31-08-2011- Making the rest share dividend payment in 2010by cash, rate VND1000 per share
D: 28-04-2011- Annual meeting of the Board of Director in 2011
Figure 4: Performances of 5 Blue chips on the stock market up to 31 October, 2011
Sources: www.bsc.com.vn
In summary , analyzing the situation of Vietnam’s stock market, particularly VN-
Recent years have seen significant growth in both the size and quality of Vietnam’s stock market, with index and HN-Index data reflecting this progress The rapid increase in stock market indexes and the number of listed companies was driven by the economic recovery in the second quarter of 2009, both domestically and globally The development of intermediate institutions and securities services has contributed to improvements in market infrastructure, attracting more local and foreign investors Despite these advancements, Vietnam’s emerging market faces inherent limitations such as constrained market size, limited composition, and regional variations, leading to unstable growth in stock indexes Additionally, this chapter provides a brief overview of five blue-chip stocks, which will be analyzed and predicted further in this thesis.
MODEL SPECIPICATION AND DATA ANALYSIS
Description of data
This thesis analyzes and forecasts the VN-Index, HN-Index, and five latest blue-chip stocks, including AGF, BMC, FPT, PVD, and SSI, utilizing data collected from Hanoi Stock Trading Center (HASTC) and Ho Chi Minh City Stock Exchange (HOSE) between January 1, 2009, and October 31, 2011 The study aims to provide comprehensive insights into stock market trends and the performance of leading Vietnamese stocks during this period.
Estimated results
Before applying the LSTR model to analyze and predict the VN-Index, the study conducts statistical tests to determine whether the data series are linear or nonlinear The testing results indicate the presence of nonlinear patterns in the data, justifying the use of the LSTR model for accurate time series analysis and forecasting of the VN-Index.
Table 4: Testing linear or non-linear of data series for suggesting model
Trend_HN-Index 4.2855e-14 2.5397e-08 4.9929e-07 1.1102e-14 LSTR1 Trend_AGF 5.3679e-74 3.9183e-03 6.9268e-02 3.1013e-74 LSTR1 Trend_BMC 6.6408e-125 4.5179e-09 3.9968e-14 1.3101e-14 LSTR1
Trend_FPT 3.9513e-129 NaN NaN 3.9524e-14 LSTR1
Trend_PVD 1.8640e-105 1.9207e-14 NaN 4.8352e-11 LSTR1 Trend_SSI 1.1102e-16 2.2867e-06 8.1591e-02 NaN LSTR1
Sources: Estimated results of the model
Note: F statistic of H04; H03; H02Hypothesis are denoted by F4, F3 and F2
The F statistic test regarding linear characteristic of the series data states that H0
Hypothesis is rejected at significance value of 1% Therefore, the suggested model in table
4 will be applied to estimate and forecast stock indexes in next times
To effectively estimate the STR model given its non-linear characteristics, it is essential to first determine the initial parameters Once these starting values are established, the Newton-Raphson algorithm can be employed to estimate the remaining unknown parameters This iterative process aims to maximize the conditional likelihood function, ensuring accurate model fitting and reliable results.
This thesis utilizes the GRID SEARCH method to determine optimal initial values of Gamma (γ) and C1 for seven stock indexes, as outlined in Table 4 The estimated parameter values obtained through this approach are displayed in Figure 5, providing valuable insights for model calibration and performance analysis.
Figure 5: Defining initial values of γ and c by using the method of GRID SEARCH
Based on the results of Gama and C obtained through the GRID SEARCH method and model adjustments, the estimated models for the VN-Index, HN-Index, and five blue-chip stocks are statistically significant, indicating reliable predictive performance and robust financial insights.
The thesis conducts unit root tests on the estimated models to confirm their efficiency and stationarity According to the results in Table 5, the forecasted error term of the model behaves as white noise, indicating model reliability Additionally, Figure 7 illustrates the ADF test for the residual error term, corroborating the stationarity findings presented in Table 5 (Appendix attached).
Table 5: Augmented Dickey-Fuller (ADF) Unit Root and PORTMANTEAU Test results
P-Value (portmanteau test) Value ADF (lag)
Residual of forecasting errors ADF(1)=Δ-14.9965 -2.56 -1.94 -1.62 0.3582
Residual of forecasting errors ADF(1)=Δ-7.5356 -3.96 -3.41 -3.13 0.1331
Residual of forecasting errors ADF(1)=Δ-11.3531 -3.96 -3.41 -3.13 0.1564
Residual of forecasting errors ADF(1)=Δ-11.1740 -3.96 -3.41 -3.13 0.7627
Residual of forecasting errors ADF(1)=Δ -12.1304 -3.96 -3.41 -3.13 0.8900
Residual of forecasting errors ADF(1)=Δ-11.6700 -2.56 -1.94 -1.62 0.3876
Residual of forecasting errors ADF(1)=Δ-10.8424 -2.56 -1.94 -1.62 0.8511
The ADF and Portmanteau tests indicate that the VN-Index, HN-Index, and five blue chip stocks are statistically significant at the 5% level, demonstrating that the models effectively capture the data's underlying patterns These results confirm that the models are both efficient and stationary, ensuring reliable forecasting of residual errors.
Figure 6: ADF Test for residual of error terms with one lag
The estimation results of the LSTR1 model, summarized in Table 6, indicate that these models are statistically significant Both the VN-Index and HN-Index show relatively consistent estimated results; however, notable differences exist between the two models Specifically, the HN-Index model lacks a constant term (α0), whereas the VN-Index model's constant term is positive, suggesting different underlying dynamics Additionally, the positive values of β0 for both indexes imply that they tend to increase prior to the transition period.
Table 6: Estimation results of LSTR1 model 9
The model incorporates key parameters including 9 α 0, the constant term of the linear component, and α 1, which measures the estimated change in the non-linear part The parameter β 0 represents the growth rate of the trend prior to the transition period, while β 1 captures the increasing trend during the transition process The transition timing is indicated by τ, the point at which the model shifts, and γ denotes the rate of this transition, providing a comprehensive understanding of trend dynamics and model behavior over time.
Figure 7: The graph of STR model
Short-term VN-Index predictions are conducted once the model meets the necessary statistical testing conditions, ensuring reliable forecasts The results demonstrate good predictive accuracy, with a relatively small average error across 706 observations, indicating the model's effectiveness As shown in Figure 9, the comparison between predicted and actual VN-Index values from February 1, 2009, to October 31, 2011, reveals that the predicted values closely match the real VN-Index, confirming the model’s strong performance in short-term forecasting.
Figure 8: VN-Index, HN-Index, and five blue chips forecast
CONCLUSIONS
In today's financial landscape, investors and financial organizations are increasingly focused on stock price forecasting to understand market behavior and make informed investment decisions Accurate analysis reports, particularly stock price analysis, are essential for selecting optimal investment opportunities and timing market participation However, predicting stock prices remains challenging due to the complex and unpredictable nature of market fluctuations and the difficulty in anticipating player decisions Despite advancements in forecasting methods since the inception of stock markets, no perfect model exists, making it necessary to accept some degree of error in predictions This thesis proposes a new model designed to assist investors, financial organizations, and newcomers by providing more reliable information for decision-making, with the results demonstrating relatively good accuracy and significance.
This thesis reviews the theoretical frameworks and existing literature on stock index analysis and prediction, proposing an effective model for forecasting the VN-Index, HN-Index, and five key blue-chip stocks The research successfully meets its objectives, providing significant results that demonstrate the applicability of the LSTR model for stock market prediction The findings highlight the potential to develop specialized software tools for real-time stock price forecasting, offering valuable, up-to-date information for investors, financial institutions, and market participants to make informed decisions.
This thesis provides valuable insights for investors, financial organizations, and stock market participants, serving as a useful reference However, it is essential to consider additional factors when applying these methods to ensure optimal investment decisions Due to limited data and market volatility, predicted index values for the near future are not provided in this study Future research will focus on expanding the analysis and improving the accuracy of forecasts in a more stable and comprehensive manner.
[1] A Lendasse, E De Bodt, V Wertz, and M Verleysen (2000), “Non-linear financial time series forecasting – Application to the Bel 20 stock market index”, European
Journal of Economic and Social Systems 14 N° 1 (2000) 81-91.
[2] Bachelier, Louis (1900) Théorie de la Spéculation, Annales Scientifique de l'École Normale Supérieure, 3 e série, tome 17, 21-86 [English translation in Cootner; original French with a more recent English translation in Davis and Etheridge.]
[3] Bacon D.W and Watts D.G (1971), Estimating the transition between two intersecting straight lines, Biometrika 58: 525-534.
[4] Bali, Turan G., K Ozgur Demirtas, and Haim Levy (2008), “Nonlinear mean reversion in stock prices”, Journal of Banking & Finance, Vol 32, pp 767-782.
[5] Chan K.S and Tong H (1986), On estimating thresholds in autoregressive models, Journal of Time Series Analysis 7: 178-190
[6] David G McMillan (2002), Non-Linear Predictability of UK Stock Market Returns, Department of Accountancy and Finance, University of Aberdeen.
[7] F Black and M Scholes (1973), ‘The pricing of options and corporate liabilities’, Journal of Political Economy, Vol 81, pp 637-659, 1973.
[8] F Chan and M McAleer, “Evaluating the forecast performance of smooth transition volatility models”, University of Western Australia
[9] Franses P.H and D.van DiJk (2000), “Nonlinear time series models in empirical finance”, Cambridge: Cambridge university press.
[10] Granger C.W.J and T.Terasvirta (1993), “Modeling non-linear economic relationships”, Oxford: Oxford University Press.
[11] Gropp, Jeffrey, (2004), “Mean reversion of industry stock returns in the U.S., 1926-
1998”, Journal of Empirical Finance, Vol 11, pp 537-551.
[12] Gujarati, Damodar N (2004), “Basic Econometrics”, fourth edition
[13] Hamilton J (1989), “A new approach to the economic analysis of non-stationary time series and the business cycle”, Econometrica 57, 357-384
[14] Laopodis, Nikiforos T (2009), “Fiscal policy and stock market efficiency: Evidence for the United States”, The quarterly Review of Economics and Finance, Vol 49, pp 633-
[15] Marcella Niglio (2002), “Nonlinear time series models with switching structure: A comparison of their forecast performances”, Quaderni di Statistica, Vol.4.2002.
[16] McMillan D.G (2001), “Non-linear predictability of stock market returns: evidence from non-parametric and threshold models”, Department of Economics, St.
Salvator’s College, University of St Andrews, Discussion paper series No 0102
[17] Milani, Fabio (2010), “The impact of foreign stock markets on macroeconomic dynamics in open economies: A structural estimation”, Journal of International
[18] Nektarios Aslanidis (2002), “Smooth Transition Regression Models in UK Stock
Returns”, School of Economic Studies, University of Manchester.
[19] Quandt, R E (1958), The estimation of parameters of a linear regression system obeying two separate regimes, Journal of the American Statistical Association 53: 873-880
[20] R.C Merton (1973), ‘Theory of rational option pricing’, Bell Journal of Economics and Management Science, Vol 4, pp 141-183, 1973.
[21] Rodrigo Aranda and Patricio Jaramillo (2008), “Nonlinear dynamic in the Chilean stock market: Evidence from returns and trading volume”, working paper, Central Bank of Chile.
[22] Samuelson, Paul A (1965), “Rational Theory of Warrant Pricing” Indus Management rev 6 (Spring 1965): 13-31.
[23] Sarantis N (2001), “Nonlinearities, cyclical behavior and predictability in stock markets: international evidence”, International Journal of Forecasting 17, 459-482
[24] Terasvirta T and H.M Anderson (1992), “Characterizing nonlinearities in business cycles using smooth transition autoregressive models”, Journal of Applied
[25] Terasvirta, Timo (1994), “Specification, estimation and evaluation of smooth transition autoregressive models”, Journal of the American Statistical Association
[26] Tong H (1990), Non-Linear Time Series, A Dynamical System Approach, Oxford University Press, Oxford.
Hoang Dinh Tuan’s 2008 study investigates the application of random process analysis to stock price movements in Vietnam's stock market Presented at the workshop on financial economics and applied mathematics at the National Economic University, the paper explores how stochastic models can enhance understanding of market dynamics This research highlights the potential of random processes to improve predictions and trading strategies within emerging markets like Vietnam.
[28] Nguyen Khac Minh (2009), “Smooth Transition and GDP growth in Vietnamese industrial sector”, Journal of Economics & Development
[29] Nguyen Viet Hung (2010), “Short term prediction of VN INDEX and HNX-INDEX”,
Journal of Economics & Development, N0 152, pp 36-42
1 VN-Index variables in AR part: CONST trend(t) str_resids(t-
1) restriction theta=Δ0: str_resids(t-1) restriction phi=Δ0: restriction phi=Δ-theta: transition variable: trend(t) sample range: [3, 706], T =Δ 704 transition function: LSTR1 number of iterations: 7 variable start Estimate SD t-stat p-value
R2: 9.9224e-01 adjusted R2: 0.9923 variance of transition variable: 41360.0000
SD of transition variable: 203.3716 variance of residuals: 0.0003
2 HN-Index variables in AR part: CONST HNX_trend(t) str_resids(t-
1) restriction theta=Δ0: restriction phi=Δ0: CONST restriction phi=Δ-theta: transition variable: HNX_trend(t) sample range: [3, 386], T =Δ 384 transition function: LSTR1 number of iterations: 17 variable start estimate SD t-stat p-value
R2: 9.9448e-01 adjusted R2: 0.9945 variance of transition variable: 12320.0000
SD of transition variable: 110.9955 variance of residuals: 0.0005
3 AGF variables in AR part: CONST AGF_Trend(t) str_resids(t-
1) restriction theta=Δ0: restriction phi=Δ0: restriction phi=Δ-theta: transition variable: AGF_Trend(t) sample range: [3, 336], T =Δ 334 transition function: LSTR1 number of iterations: 6 variable start estimate SD t-stat p- value - linear part -
R2: 9.7913e-01 adjusted R2: 0.9792 variance of transition variable: 9324.1667
SD of transition variable: 96.5617 variance of residuals: 0.0007
In the AR component, BMC variables include CONST, BMC_trend(t), and str_resids(t-1), with specific restrictions such as theta=Δ0 for str_resids(t-1) and phi=Δ0, and phi=Δ-theta to ensure model consistency The transition variable is BMC_trend(t), analyzed over a sample range of 3 to 506 with a total sample size of T=504, using the LSTR1 transition function The model was iterated five times for parameter estimation, providing key results such as the start estimate, standard deviation, t-statistic, and p-value, which are essential for evaluating the significance of the AR variables within the model.
R2: 9.9396e-01 adjusted R2: 0.9940 variance of transition variable: 21210.0000 variance of residuals: 0.0009
The AR model incorporates FPT variables, including the constant term and the FPT_trend(t), with state residuals lagged by one period (str_resids(t-1)) Restrictions are applied, such as setting theta to zero (Δ0) to evaluate its impact, along with phi set to zero (Δ0) and the condition phi equals minus theta (Δ - theta) The transition variable FPT_trend(t) is analyzed over a sample range from 3 to 463, with a total of 461 observations, using the LSTR1 transition function The model's linear component was estimated through five iterations, with initial variable estimates and their standard deviations, t-statistics, and p-values indicating the significance of each predictor in explaining the AR process.
R2: 9.8000e-01 adjusted R2: 0.9800 variance of transition variable: 17748.5000
SD of transition variable: 133.2235 variance of residuals: 0.0004
The AR model includes PVD variables such as CONST, PVD_trend(t), and str_resids(t-1), with specific restrictions like theta=Δ0 and phi=Δ0, and the transition variable PVD_trend(t) The sample range spans from 3 to 400, covering T=398 observations The transition function utilized is LSTR1, with four iterations to optimize model fitting Key variables include the linear AR components and PVD-related variables, providing insights into trend and residual dynamics within the specified sample.
CONST 4.03507 4.03920 0.0044 919.9152 0.0000 PVD_trend(t) -0.00318 -0.00326 0.0001 -35.8396 0.0000 str_resids(t-1) 0.88923 0.88953 0.0234 37.9652 0.0000 nonlinear part
R2: 9.7053e-01 adjusted R2: 0.9706 variance of transition variable:
SD of transition variable: 115.0370 variance of residuals: 0.0004
The AR part of the model incorporates SSI variables including CONST, TREND(t), and str_resids(t-1), with specific restrictions such as theta=Δ0 and phi=Δ, indicating parameter constraints The transition variable analyzed is TREND(t), within a sample range of [3, 433], totaling T=431 observations The transition function employed is LSTR1, with the estimation process requiring 2 iterations Key results include the linear component estimates, their standard deviations, t-statistics, and p-values, providing insights into the significance and behavior of the model parameters in capturing structural shifts and trend dynamics over the sampled period.
R2: 9.9328e-01 adjusted R2: 0.9933 variance of transition variable: 15516.0000
SD of transition variable: 124.5632 variance of residuals: 0.0006
II ADF Test for reidual of data series
ADF Test for series: u_resids sample range: [1961 Q2, 2136 Q2], T =Δ 701 lagged differences: 2 no intercept, no time trend asymptotic critical values reference: Davidson, R and MacKinnon, J (1993),
"Estimation and Inference in Econometrics" p 708, table 20.1,
-2.56 -1.94 -1.62 value of test statistic: -14.9965 regression results:
OPTIMAL ENDOGENOUS LAGS FROM INFORMATION CRITERIA sample range: [1963 Q2, 2136 Q2], T =Δ 693 optimal number of lags (searched up to 10 lags of 1 differences):
ADF Test for series: str_resids sample range: [1961 Q2, 2056 Q2], T =Δ 381 lagged differences: 2 intercept, time trend asymptotic critical values reference: Davidson, R and MacKinnon, J (1993),
"Estimation and Inference in Econometrics" p 708, table 20.1,
-3.96 -3.41 -3.13 value of test statistic: -7.5356 regression results:
OPTIMAL ENDOGENOUS LAGS FROM INFORMATION CRITERIA sample range: [1963 Q2, 2056 Q2], T =Δ 373 optimal number of lags (searched up to 10 lags of 1 differences):
ADF Test for series: str_resids sample range: [1961 Q2, 2043 Q4], T =Δ 331 lagged differences: 2 intercept, time trend asymptotic critical values reference: Davidson, R and MacKinnon, J (1993),
"Estimation and Inference in Econometrics" p 708, table 20.1,
-3.96 -3.41 -3.13 value of test statistic: -11.3531 regression results:
OPTIMAL ENDOGENOUS LAGS FROM INFORMATION CRITERIA sample range: [1963 Q2, 2043 Q4], T =Δ 323 optimal number of lags (searched up to 10 lags of 1 differences):
ADF Test for series: str_resids sample range: [1961 Q2, 2086 Q2], T =Δ 501 lagged differences: 2 intercept, time trend asymptotic critical values reference: Davidson, R and MacKinnon, J (1993),
"Estimation and Inference in Econometrics" p 708, table 20.1,
-3.96 -3.41 -3.13 value of test statistic: -11.1740 regression results:
OPTIMAL ENDOGENOUS LAGS FROM INFORMATION CRITERIA sample range: [1963 Q2, 2086 Q2], T =Δ 493 optimal number of lags (searched up to 10 lags of 1 differences):
ADF Test for series: str_resids sample range: [1961 Q2, 2075 Q3], T =Δ 458 lagged differences: 2 intercept, time trend asymptotic critical values reference: Davidson, R and MacKinnon, J (1993),
"Estimation and Inference in Econometrics" p 708, table 20.1,
-3.96 -3.41 -3.13 value of test statistic: -12.1304 regression results:
OPTIMAL ENDOGENOUS LAGS FROM INFORMATION CRITERIA sample range: [1963 Q2, 2075 Q3], T =Δ 450 optimal number of lags (searched up to 10 lags of 1 differences):
ADF Test for series: str_resids sample range: [1961 Q2, 2059 Q4], T =Δ 395 lagged differences: 2 no intercept, no time trend asymptotic critical values reference: Davidson, R and MacKinnon, J (1993),
"Estimation and Inference in Econometrics" p 708, table 20.1,
-2.56 -1.94 -1.62 value of test statistic: -11.6700 regression results:
OPTIMAL ENDOGENOUS LAGS FROM INFORMATION CRITERIA sample range: [1963 Q2, 2059 Q4], T =Δ 387 optimal number of lags (searched up to 10 lags of 1 differences):