Forecasting stock market volatility
Posted on
Abstraction
Volatility analysis of Stock markets is an of import country of survey. There have been assorted academic surveies in yesteryear on the effectivity of clip series theoretical accounts in gauging and calculating the volatility of the stock markets of assorted developed and developing states. Some bookmans chose to pattern volatility of stock index by utilizing all ARCH and non ARCH theoretical accounts while some of them merely used one theoretical account. The informations used by these bookmans besides differed in composing. Depending on the aim of the survey, informations from merely one state was analyzed or multiple stock exchanges ‘ information was modeled and compared.
This paper examines the usage of GARCH type theoretical accounts for patterning volatility and explicating fiscal market hazard on the historical information of Nigerian Stock exchange. We have used informations for 9 old ages from DataStream sourced from Nigerian Stock Exchange ( LSE All portion index ) for our analysis. Four clip series are employed viz. GARCH, Threshold GARCH, Exponential GARCH and ARCH8.The analysis on the information gives strong grounds that the four theoretical accounts can be used to qualify the daytoday returns ( to be verified ) ..
Chapter 1
Introduction
In the past few old ages, considerable uncertainness and volatility has been observed in the emerging and mature fiscal markets worldwide. Fiscal analysts and investors are concerned about the fluctuating returns of their investings due to the market hazard and fluctuation in the market monetary value guess every bit good as the instable concern public presentation ( Alexander 1999 ) .
Quantitative theoretical accounts are used in fiscal econometrics to decode the investor ‘s attitude towards the hazards and returns every bit good towards the volatility every bit good. It is of import for any investors or prospective investor to be cognizant of the hazards associated with the market volatility and the techniques to pull off those hazards. The survey of market volatility involves application of theoretical accounts which are capable of managing the volatility of the market and the clip series. Fiscal Analysts theoretical account and explicate the behaviour of stock market and its returns every bit good as volatility by utilizing the clip series econometric theoretical accounts. The grounds for utilizing econometric theoretical accounts are many viz. uncertainnesss in returns and the monetary values, discrepancy in the fiscal markets which is nonconstant and unexpected events in the state or universe which has the potency of act uponing investors for illustration September 11.
One of the most outstanding tools for capturing such altering discrepancy was the Autoregressive Conditional Heteroskedasticity ( ARCH ) and Generalized ARCH ( GARCH ) theoretical accounts developed by Engle ( 1982 ) , and extended by Bollerslev ( 1986 ) and Nelson ( 1991 ) . Two of import features within fiscal clip series, the fat dress suits and volatility bunch ( or volatility pooling ) , can be captured by the GARCH household theoretical accounts. A series with some periods of low volatility and some periods of high volatility is said to exhibit volatility constellating. Volatility constellating can be thought of as bunch of the discrepancy of the error term over clip: if the arrested development mistake has a little discrepancy in one period, its discrepancy tends to be little in the following period, excessively. In other words, volatility constellating implies that the mistake exhibits timevarying heteroskedasticity ( unconditioned criterion divergences are non changeless ) .
In this paper, we capture fiscal clip series features by using GARCH ( P, Q ) theoretical account and its EGARCH, Threshold GARCH ( TGARCH ) , and ARCH8 extensions. These theoretical accounts have the advantage of allowing probe of the potentially asymmetric nature of the response to past dazes.
Several surveies investigate the public presentation of GARCH theoretical accounts on explicating volatility of mature stock markets ( e.g. Sentana and Wadhwani, 1992 ; Kim and Kon, 1994 ; Kearney and Daly, 1998 ; Floros, 2007 ; Floros et al. , 2007 ) , but few have tested GARCH theoretical accounts utilizing daytoday informations from African markets. Frimpong et Al. ( 2006 ) examine the behaviour of stock returns every bit good as the market efficiency and volatility effects in the Ghana stock exchange utilizing GARCH theoretical accounts. They conclude that GARCH ( 1,1 ) theoretical account outperformed the other theoretical accounts under the premise that the inventions follow a normal distribution.
Few surveies have been conducted on the Middle East markets every bit good. Alberg et Al. ( 2006 ) estimation stock market volatility of Tel Aviv Stock Exchange indices, for the period 19922005, utilizing asymmetric GARCH theoretical accounts. They report that the EGARCH theoretical account is the most successful in calculating the TASE indices.
Finally, Meric et Al. ( 2007 ) analyze the comovements of the US, UK and Middle East stock markets ( Egyptian, Israeli and Turkish ) during the period 1996 to 2006, and describe a really low correlativity. They besides present the mean hebdomadal returns and volatility of returns. Harmonizing to Meric et Al. ( 2007 ) , Israeli ‘s mean hebdomadal returns are 0.24 % , while the Egyptian stock market has a high mean hebdomadal return ( 0.45 % ) . Besides, the Egyptian stock market has the highest return per unit of volatility hazard ( 0.1 % ) , while the Israeli stock market has the lowest return per unit of volatility hazard ( 0.06 % ) over the examined period.
The intent of this paper is to calculate the stock market volatility by utilizing the four clip series GARCHfamily theoretical accounts for the last 9 twelvemonth ‘s stock index informations from Nigerian stock market.
The analysis focuses on Nigerian stock index i.e. the LSE All portion index and information for 09 old ages is captured for carry oning the analysis. Four GARCH household theoretical accounts i.e. GARCH, Threshold GARCH, Exponential GARCH and ARCH8, are used to carry on the analysis.
The remainder of this paper is organized as follows. Chapter 2 contains the inside informations on the Nigerian Stock market with focal point on history, cardinal driver and the recent trading activity and the occurrence in the Nigerian Stick exchange. Chapter 3 is devoted to literature reappraisal while Chapter 4 trades with the informations aggregation, analysis and consequences. Chapter 5 is the reasoning chapter in this paper.
Chapter 2
Overview of Nigerian Stock Market
Harmonizing to the latest survey, Nigerian Stock Market ranked 4th in the universe in 2007, on the footing of sheer growing. It is behind China ‘s Shanghai ( Hongyu, P. and Zhichao, Z, 2006 ) Ukraine ‘s PFTS and Slovenia. Its growing was 73 % which is measured by All Share Index as it acts as natural arrow to the growing of economic system. Within Nigeria all its companies are publically quoted and this index contains portions of them. Equity market was little before 2004 in Nigeria because of low value of equity trade as a proportion to both market capitalisation and GDP. Index of NSE has grown with clip from 134.6 in 1986 to 65005.48 in 2008.
NSE has automatic trading system which means that informations for the companies that are listed is presented monthly, hebdomadal, daytoday, quarterly and yearly. Government has abolished Torahs that used to forestall flow of foreign exchange in the Nigeria to increase foreign investing in the state.
History of the Nigeria Stock market
Stock market of Nigeria is called Nigerian Stock Exchange ( NSE ) that was started in 1961 with 19 securities that increased to 264 securities in 1998 ( Olowe, 2008 ) . Today there are 262 securities listed on The Exchange, made up of 11 Government Stocks, 49 Industrial Loan ( Debenture/Preference ) Stocks and 194 Equity / Ordinary Shares of Companies.
The Nigeria Stock Exchange took on its present name in 1977 as by so the Stock Market already had subdivisions in the most of import concern centres of the state. The subdivisions of The Nigeria Stock Exchange are as given below:

Lagos opened in 1961

Kaduna opened in 1978

Port Harcourt opened in 1980 ;

Kano opened in 1989 ;

Onitsha opened in February 1990 ;

Ibadan opened in August 1990 ;

Abuja opened in October 1999 ;

Yola opened in April 2002.
Lagos nevertheless remained the central office of the Nigeria Stock Exchange. The concern of trading in Nigeria stock exchange Market is conducted during the weekdays from 11 O ‘ clock in the forenoon to 1 O ‘ clock in the afternoon local clip. The goods, which are kept as security while trading are, corporate bonds, portions and authorities bonds.
The trading of portions and bonds are done by the stock agents in big halls by shouting out loud or by doing phone calls which each subdivision holding its ain trading hall. The Nigeria Stock Exchange now uses an Automated Trading System which makes trading easier, faster and safer. TheNigeria stock exchangewas started with a little capital and in the twelvemonth 1997 the capital went up to a sum of about $ 3 billion. Nigeria Stock Exchange has been one of the most successful concerns in Nigeria. The AllShare Index ( AMI ) is the stock market index of the Nigeria Stock Exchange which for its computation uses merely common stocks ( ordinary portions ) , was developed in 1984. Its market capitalisation was 5.12 trillion naira at the terminal of 2006 compared to 2.9 trillion the old twelvemonth.
In the pursuit of achieving universe criterion in stock selling,Nigeria stock exchangebecame member of the FIBV or “Federation of International Stock Exchange” . Besides with the current battle for fraud and corruptness, public trust in the Nigeria stock market has grown enormously, with about three million single investors and 100s of institutional investors ( including aliens who own about 47 % of the quoted companies ) utilizing the installations of The Nigeria Stock Exchange. The Nigeria Stock Exchange ‘s 39year history is barren of any fraud, dazes, dirts or insider traffics.
The organic structure that governs the Nigeria Stock Exchange is the Securities and Exchange Commission ( SEC ) . Clearing, Settlement and Delivery of minutess on The Nigeria Stock Exchange are done electronically by theCardinal Securities Clearing System Limited ( CSCS ),a subordinate of The Nigeria Stock Exchange. The CSCS Limited ( “the Clearing House” ) was incorporated in 1992 as portion of the attempt to do the Nigeria stock market more efficient and investorfriendly. Apart from uncluttering, colony and bringing, the CSCS Limited offers custodian services. Charges included in all minutess are a 3 % committee on the traded value of portions and a 1 % Securities and Exchange Commission fee. Withholding revenue enhancement on dividend and involvement remains at 10 % ; corporate income revenue enhancement, 35 % , capital additions revenue enhancement, 10 % .
The Fundamental driver of the Nigeria Stock Market
In 1971 to 1987 authorities and industrial loan stocks dominated the market and there were barely any trading minutess in equity market. But after 1988 value of equity dealing increased and was about 0.0624. It has ever been fluctuating as it was 0.0516 in 1998, 0.1059 in 2004 and 0.878 in 2005.
When Central Bank increased the capitalisation of Nigerian Banks to 25 billion, so Bankss raised around 406.4 billion from capital bank. This affected quoted securities on NSE. Market Capitalization was increased to 81.0104 in 2007 due to recapitalization of banking industry that besides increased value of equity trade. If we take value of equity trade to be relative to GDP, so it was 0.0023 in 1988, 0.00001 in 1989, 0.0033 in 1998, 0.0192 in 2004 and eventually 0.0171 in 2005. The information indicates a fluctuating tendency.
In 2004, Central bank of Nigeria announced new capital demands of 25 billion for Bankss of Nigeria. The new capital demands increased figure of activities in NSE and brightened the assurance of those who invested in Nigerian economic system and stock market. This affected the volatility and increased capital formation.
In 2005, recapitalization of insurance and reinsurance companies was announced by federal authorities of Nigeria. This increased figure of securities in Nigerian stock market that increased public consciousness and assurance for stock market. Since 2008, stock monetary values were worsening of Nigerian stock market.
Trading activities and recent occurrence in the Nigeria stock market
Every major bank in Nigeria is raising financess through Global depositary grosss ; this can assist other universe provinces to put indirectly. Many of the GDR holders settled abroad are playing in a mode that they can impact monetary values of Nigeria. If they exit the market by disposing their portions, this will tag the market down. Capital market or banking industry is non the lone beginning for the growing of Nigerian economic system. More local people are fall ining its stock market twentyfour hours by twentyfour hours. This addition in engagement locally and internationally will make a state of affairs where there will be more commands and less figure of offers. A state of affairs of market rectification can besides happen where there could be sudden market issue of the people taking to the clang. Due to increased engagement of international investors and regulators, planetary market may act in irrational ways and can take to volatility, crowding and contagious disease. This means it may go on that all the planetary markets may draw all the financess from market one twentyfour hours and major stakeholders sell off from market so the little stockholders who were incognizant may lose large sums and incur heavy losingss.
It is believed that there will be non much volatility in coming old ages in Nigeria and its stock market will maturate over clip. A lag is necessary at some point so that bond market can go vivacious. To increase market capitalisation and capital growing, there should be ensured from repositioned Bankss that more companies are acquiring into stock market. Since petroleum oil monetary values are exceling at $ 100, this has developed assurance for planetary investors. Nigeria will be financially stable if it keeps singlefooting up its foreign militias. Government besides needs to guarantee that societal functions are discharged efficaciously.
Noise bargainers had an impact on Nigeria, since rational bargainers were drowned, but it failed to set up derivative market like US ‘s CMA. They bring in more companies for citing and increase in exchanges but the size of the economic system is still excessively little. There is a demand of making strong derivative market.
For the past few old ages, the Nigerian Stock Exchange ( N.S.E ) has been a hive of activity, having enormous backing from both corporate and single investors. But on 24 July 2008 its market capitalisation sank to N10.03 trillion compared with the high of N12.64 trillion on 5 March, somewhat beat uping by 5 August to N10.64 trillion. This made investors to inquire if the Global lag has affected the Nigerian Stock Index every bit good.
Chapter 3
Literature Review
The returns of the African and other emerging markets have been extensively written on and tested for anomalous stock market seasonal or crosssectional behaviour of their stock returns utilizing oneyear returns ( Ayadi, 1998 ) . Even though trials of stock market anomaly focus more on seasonal or crosssectional behaviour of stock returns and these trials differ from clip series trials which look at the predictability of rates of return over clip ( Claessens et. Al, 1995 ) , the presence of anomalousnesss in stock markets by and large indicates predictability of returns. The trials applied on emerging markets ‘ returns to find the presence of anomalousnesss are similar to those applied on developed markets ‘ stock returns. The presence of anomalousnesss in returns of common stocks has intrigued research workers since the last century disputing the rightness of the Capital Asset Pricing theoretical account ( CAPM ) and the whole theory of market efficiency.
In an anomalous turnoftheyear survey of stock return seasonality in lowincome African emerging markets utilizing monthly market indices for the Ghanese stock market ( 19911996 ) , Nigerian stock market ( 19841995 ) , and Zimbabwean stock market ( 19871995 ) , Ayadi, ( 1998 ) found that the consequences of both the KruskalWallis and Friedman tests suggest the absence of seasonality in stock returns on the Nigerian and Zimbabwean stock markets while the Friedman trial confirms the presence of seasonality in stock returns for Ghana. Furthermore, the WilcoxonMannWhitney trial and the dummyvariable arrested development analysis show the presence of the “ January consequence ” for Ghana but non for Nigeria and Zimbabwe.
In a more recent survey, utilizing hebdomadal index returns adjusted for thin trading as a nonlinear autoregressive procedure with conditional heteroscedasticity, AppiahKusi and Menyah ( 2003 ) used the EGARCHM theoretical account to look into the weakform pricing efficiency of 11 African stock markets. Their findings reject grounds in anterior surveies that the Nigerian stock market is weakform efficient. They confirm antique ante consequences that the markets in Egypt, Kenya, and Zimbabwe are efficient while that of South Africa is non weakform efficient. Their findings indicate that stock markets in Mauritius and Morocco may be efficient while the stock markets in Mauritius and Morocco, Botswana, Ghana, Ivory Coast, and Swaziland are non consistent with weakform efficiency. The application of the EGARCH theoretical account enabled them to capture how conditional volatility affects the pricing procedure without enforcing undue limitations on the parametric quantities of the conditional discrepancy equation. It is obvious that the inquiry of efficiency of the African fiscal markets is still unresolved as conflicting research findings prevail.
Harmonizing to Piesse and Hearn ( 2002 ) , analyzing African markets integrating have suggested that the univariate EGARCH theoretical account suggested by Nelson ( 1991 ) are appropriate for the analysis of African market since they can successfully pattern asymmetric impacts of good intelligence ( market progresss ) and bad intelligence ( market retreats ) on volatility transmittal with high degrees of truth. Using hebdomadal market informations from January 1993 to 2000 for Ghana, they found no grounds of dissymmetry ( i.e. Leverage consequence ) .
Importance of ARCH and GARCH methods
Methods of utilizing average and discrepancy to cipher volatility is unconditioned and does non acknowledge forms of plus volatility i.e. clip changing and constellating belongingss. We use ARCH and GARCH theoretical accounts where we consider volatility return to be a cardinal issue. Many Bankss and other fiscal establishments have used the thought of value at hazard as a manner so that they can mensurate hazards that their portfolios are soon confronting. If there is one per centum value at hazard so any losingss for the following twentyfour hours can transcend around 90 nine per centum.
GARCH ( 1, 1 ) theoretical account is used where there is conditional discrepancy.
Its equation is: Second_{T}= B_{O}+ ?_{T}, ?_{T}/?_{t1}~N ( 0, ?_{T}^{2})
GARCH theoretical account ( refer to Engle, 1982 to cognize more about the theoretical account ) can be generalized into a GARCH ( P, Q ) theoretical account holding extra slowdown footings. These sort of higher theoretical accounts are used when we are covering with big informations. Using these extra slowdown we can hold both fast and slow decay of the information. There are certain disadvantages of GARCH theoretical account. We besides have GARCH ( 2, 2 ) theoretical account that is besides called the constituent theoretical account. We besides have another version for GARCH theoretical account that takes in asymmetric position. It estimates negative and positive returns individually. Higher volatilities by and large follow negative returns more than positive returns. Variance calculated is dependent on merely old error term and non on its mark. It does non state anything about dissymmetry. It can non state anything about negative dazes.
Because of these shortcoming household of GARCH theoretical account have been created that can cover with dissymmetry. These are Exponential GARCH and GJR GARCH theoretical accounts. Besides this there are other signifiers of GARCH theoretical account. These are: IGARCH ( Integrated generalized ARCH ) , GARCHM ( GARCH in Mean ) , QGARCH, TGARCH ( Threshold GARCH ) , APARCH, FIGARCH ( Fractionally Integrated GARCH ) , FIEGARCH ( Fractionally integrated EGARCH ) , FIAPARCH, FCKARCH, HYGARCH, NGARCH ( Non Linear GARCH ) , NAGARCH ( Non Linear In Mean Asymmetric GARCH ) and FGARCH ( Family GARCH ) theoretical accounts. These theoretical accounts were proposed by Engle and Bollerslev ( 1986 ) .
Equation for GJRGARCH theoretical account:
?t = ? + + ?_{I}?_{tI}^{2}+ + ?_{J}?_{tj}^{2}+ + ?_{K}?_{tk}^{2}I^{–}_{tk}
To cipher Stock market Volatility we have used EGARCH ( Generalized Autoregressive Conditional Heteroskedasticity ) in average theoretical account. It has been developed from generalisation of ARCH ( Autoregressive Conditional Heteroskedasticity ) theoretical account. ARCH theoretical account relates conditional discrepancy to the additive combination of squared frequences, but after generalisation conditional discrepancy is related to both lagged values and squared values.
There should be a positive relation between volatility and stock return. Harmonizing to Leon ( 2007 ) high premium hazard should be paid for high volatility in stock market. GARCH examines relationship between volatility and stock return so that hazard return tradeoff can be measured. We use non parametric techniques to happen relationship between hazard and return. We can integrate exogenic variables in the equations that are provided for the GARCH theoretical accounts.
We will utilize average and discrepancy equations for full sample, pre stock market clang, stock market clang, pre planetary and planetary crisis.
Mean and discrepancy equations for full sample are:
Roentgen_{T}=b_{0}+ B_{1}Roentgen_{t1}+ B_{2}?_{T}+ B_{3}BR + B_{4}ISR + B_{5}SMC + B_{6}GFC + ?_{T}
?_{T}/?_{t1}~N ( 0, ?_{T}^{2}, V_{T})
Here V_{T}is grade of freedom
Equation for mean for pre stock market:
Roentgen_{T}=b_{0}+ B_{1}Roentgen_{t1}+ B_{2}?_{T}+ B_{3}BR + B_{4}ISR + ?_{T}
?_{T}/?_{t1}~t ( 0, ?_{T}^{2}, V_{T})
Equation for discrepancy for pre stock market:
?_{T}/?_{t1}~N ( 0, ?_{T}^{2}, V_{T})
Average equation for pre planetary fiscal crisis:
Roentgen_{T}= B_{0}+ B_{1}Roentgen_{t1}+ B_{2}?_{T}+ B_{3}BR + B_{4}ISR + B_{5}SMC + ?_{T}
?_{T}/ ?_{t1}~t ( 0, ?_{T}^{2}, V_{T})
Variance equation for pre planetary fiscal crisis:
?_{T}/?_{t1}~N ( 0, ?_{T}^{2}, V_{T})
Average equation for stock market clang:
Roentgen_{T}=b_{0}+ B_{1}Roentgen_{t1}+ B_{2}?_{T}+ B_{6}GFC + ?_{T}
?_{T}/ ?_{t1}~t ( 0, ?_{T}^{2}, V_{T})
Variance equation for stock market clang:
Log ( ?_{T}^{2}) = ? + ?_{I} ( ?_{ti}/?_{ti}) – ( 2/? )^{1/2} + ?_{1}log ( ?_{t1}^{2}) + ?  ?_{ti}/?_{ti}
It has the presence of ARCH in it.
Average equation for planetary fiscal crisis:
Roentgen_{T}=b_{0}+ B_{1}Roentgen_{t1}+ B_{2}?_{T}
?_{T}/ ?_{t1}~t ( 0, ?_{T}^{2}, V_{T})
Variance equation for planetary fiscal crisis:
log ( ?_{T}^{2}) = ? + ? ( ?_{t1}/?_{t1}) – ( 2/? )^{1/2} + ?_{1}log ( ?_{tj}) + ?  ?_{t1}/?_{t1}
It besides has presence of ARCH.
Here ? , ? , ? , and ? are volatility parametric quantities.
Chapter 4
Data and Sample description
The chief stairss for the procedure are:

Collection of Data and Samples.
We collect daytoday consequences of stock markets over 9 old ages from 2000 to 2008 utilizing the DataStream.
To cipher monthly volatility we need to calculate daytoday returns utilizing the undermentioned expression:
Roentgen_{m, T}=ln ( I_{m, T}/I_{m, t1})
Where I_{m, T}is value of stock market index and Roentgen_{m, T}is compound return on month.
Monthly realized volatility is computed as:
µ= ( 1/n ) Roentgen_{m, T}
?_{a, m=}[ ( R_{m, t}µ_{m})^{2}]^{0.5}
Number of trading yearss is given by n. Now if we get n observations so half of them are used for appraisal and other half for prediction.
Stock return can be computed as:
Roentgen_{T}= log [ ( NSI_{T}) / ( NSI_{t1}) ]
Where, R_{T}bases for stock return at clip T
NSI_{T}and NSIt_{1}refers to Nigerian Stock Index at clip T and t1 severally

Use prediction techniques.
Forecasting theoretical accounts are chosen by maintaining in head their complexness and scope of steps. We employ four clip series theoretical accounts to analyse the information. The theoretical accounts are summarized below:

GARCH ( 1, 1 ) Model.It stands for Generalized Autoregressive Conditional Heteroscedastic theoretical account. If we have ARMA ( Auto Regressive Moving Average ) theoretical account for mistake discrepancy so the consequence is GARCH theoretical account. In this exemplary conditional volatility depends on yesterday ‘s conditional volatility and yesterdays squared forecast mistake. While gauging entire figure of slowdown we use LJung Box Test. LJung Statistics follow Ten^{2}distribution, holding n figure of grade of freedom. If we reject void so we have no conditional discrepancy mistake. It is computed as follows:
H_{T}= ?_{O}+ ? ?_{t1}^{2}+ ?_{1}H_{t1}

EGARCH ( 1, 1 ) Model ( Nelson, 1991 ) .It stands for Exponential Autoregressive Conditional Heteroscedastic theoretical account. It is an asymmetric theoretical account. In some instances we can hold value of consequence as negative besides. Its equation is:
Ln ( H_{T}) = ?_{O}+? ( ?_{t1}/ ( H_{t1})^{1/2}) + ? [ ( ?_{t1}/ ( H_{t1})^{1/2}) – ( 2/? )^{0.5}] + ?ln ( H_{t1})

TGARCH theoretical account. It stands for Threshold GARCH theoretical account. It is rather similar to GJRGARCH theoretical account. But here we use conditional criterion divergence alternatively of utilizing conditional discrepancy. This theoretical account takes in asymmetric attack. Its equation is given as: ?_{T}= K + ??_{t1}+ ?_{1}^{+}?_{t1}^{+}+ ?_{1}^{–}?_{t1}^{–}

ARCH8 Model. This is a category of semiparametric ARCH ( ? ) theoretical accounts that includes as a particular instance the partly nonparametric ( PNP ) theoretical account introduced by Engle and Ng ( 1993 ) and which allows for both flexible kineticss and flexible map signifier with respect to the ‘news impact ‘ map.

Comparing Consequences:

Symmetrical Error Statistics ( Brailsford and Faff 1996 ) .
Average Error ( ME ) : Formula for ciphering ME:
1/60 ( ?_{degree Fahrenheit, m}– ?_{a, m )}
Mean Absolute Error ( MAE ) : Formula for ciphering MAE:
1/60 ?_{degree Fahrenheit, m}– ?_{a, m}
Root Mean Squared Error ( RMSE ) : Formula for ciphering RMSE:
1/60 [ ( ?_{degree Fahrenheit, m}– ?_{a, m ) 2}]^{0.5}
Mean Absolute Percentage Error ( MAPE ) : Formula for ciphering MAPE:
1/60 ( ?_{degree Fahrenheit, m}– ?_{a, m )}/ ?_{a, m}
Here ?_{degree Fahrenheit, m}refers to calculate volatility and ?_{a, m}refers to recognize volatility in month

Asymmetric Error Statistics.In pricing of options over anticipation of volatility is unwanted for purchasers and under anticipation of volatility is unwanted for Sellerss hence Mean Mixed Error Statistics ( MME ) is employed as follows:
Here O is the figure of over anticipations and U is figure of under anticipations.

Volatility prognosiss:
Volatility prognosiss can be computed from symmetric and asymmetric theoretical accounts by utilizing four Models: ARCH ( P ) , GARCH ( 1, 1 ) , GJR GARCH ( 1, 1 ) and EGARCH ( 1, 1 ) . Conditional average map is computed as: Roentgen_{T}= degree Celsius + ?_{I}Roentgen_{tI}+ ?_{T}
Following symmetric theoretical accounts are used as:
ARCH ( P ) : H_{T}^{2}= ?_{O}+ ?_{I}?^{2}_{t1}^{2}
GARCH ( 1, 1 ) : H_{T}^{2}= ?_{O}+ ?_{1}?_{t1}^{2}+ ?_{1}H^{2}_{t1}
Following asymmetric theoretical accounts are used:
EGARCH ( 1, 1 ) : ln ( H_{T}) = ?_{O}+? ( ?_{t1}/ ( H_{t1})^{1/2}) + ? [ ( ?_{t1}/ ( H_{t1})^{1/2}) – ( 2/? )^{0.5}] + ?ln ( H_{t1})
This shows asymmetric consequence is exponential and non quadratic.

To prove relationship between return and volatility:
Forecast theoretical account produces a arrested development that gives relationship between return and volatility:
µ_{tungsten}= ? + ?_{degree Fahrenheit}?_{degree Fahrenheit, tungsten}+ vitamin E_{tungsten}
If ?_{degree Fahrenheit}= 0 so µ_{tungsten}( market returns ) And volatility are unrelated
If ? =0 and ?_{degree Fahrenheit}& gt ; 0 so, market returns and volatility are relative
Relationship between market returns and unexpected volatility is given as:
µ_{tungsten}= ? + ?_{degree Fahrenheit}?_{U, tungsten}+ vitamin E_{tungsten}
Using the above process we get generalised consequences as follows:

Exponential Smoothing attack provides superior prognosiss for monthly volatility where there are different market conditions and contexts.

NonARCH theoretical accounts are superior to ARCH theoretical accounts.

If we have sub groups of ARCH type theoretical accounts, so the complex theoretical accounts are by and large more superior.
Chapter 5
Decisions
This subdivision would be written after the information analysis.
Mentions
Alberg, D. , Shalit, H. , and Yosef, R. ( 2006 ) “Estimating stock market volatility utilizing asymmetric GARCH models” , Discussion Paper No. 0610, Monaster Center for Economic Research, BenGurion University of the Negev, Israel.
Alexander, C. ( 1999 ) “Risk Management and Analysis, Volume 1: Measurement and Modeling Financial Risk” , John Wiley and Sons, New York, NY.
AppiahKusi J. and Menyah K. , ( 2003 ) “Return predictability in African stock markets” , Review of Financial Economics, 12 ( 3 ) , pp. 247
Ayadi, O.F. , ( 1994 ) “ The Efficiency of Price Discovery in the Stock Market and Macroeconomic Variables: An Empirical Probe ” , African Review of Money, Finance and Banking, pp. 3355.
Bollerslev, T. , Chou, R. Y. and Kroner, K. F. ( 1992 ) “ARCH patterning in finance” , Journal of Econometrics, Vol 52, pp. 559.
Claessens, S. ( 1995 ) “ The Emergence of Equity Investment in Developing States: Overview ” , The World Bank Economic Review, 9. ( 1 ) , pp. 1117.
Engle, R. F. ( 1982 ) “Autoregressive conditional heteroscedasticity with estimations of the discrepancy of UK inflation” , Econometrica, Vol 50, pp. 9871008.
Floros, C. ( 2007 ) “The usage of GARCH theoretical accounts for the computation of Minimum Capital Hazard Requirements: International Evidence” , International Journal of Managerial Finance, Vol. 3 ( 4 ) , pp. 360371.
Floros, C. , Jaffry, S. and G.V. Lima ( 2007 ) , “Long memory in the Lusitanian Stock Market” , Studies in Economics and Finance, Vol. 24 ( 3 ) , pp. 220232.
Hongyu, P. and Zhichao, Z. , ( 2006 ) , Forecasting Financial Volatility: Evidence from Chinese Stock Market. Working Paper in Economics and Finance, No. 06/02, University if Durham.
Kearney, C. and Daly, K. ( 1998 ) “The causes of stock market volatility in Australia” , Applied Financial Economics, Vol 8, pp. 597605.
Kim, D. and Kon, S. I. ( 1994 ) “Alternative Models for Conditional Heteroscedasticity of Stock Returns” , Journal of Business, Vol 67, pp. 563598.
Meric, G. , Ratner, M. , and Meric, I. ( 2007 ) “Comovements of the U.S. , U.K. , and Middle East Nelson, D. ( 1991 ) “Conditional heteroscedasticity in plus returns: a new approach” , Econometrica, Vol 59, pp. 34770.
Piesse J and Hearn B ( 2002 ) , Equity Market Integration versus Segmentation in Three Dominant Markets of the Southern African Customs Union: Cointegration and Causality Tests, Applied Economics, forthcoming
Sentana, E. and Wadhwani, S. ( 1992 ) “Feedback bargainers and stock return autocorrelations: grounds from a century of daytoday data” , Economic Journal, Vol 102, pp. 415425.
Stock markets” , Middle Eastern Finance and Economics, Issue 1, pp. 6073.