7-10-8 Oil ETN Trading= Rule Linear Poly Daily Open Close Regression Forecasts

OIL ETN TRADING RULE LINEAR & POLYNOMIAL DAILY OPEN & CLOSE REGRESSION FORECASTS- AUTOMATED HTML JAVA SCRIPT SOFTWARE DEVELOPMENT

Avi and Sara Rushinek, University of Miami, arush@miami.edu arushine@aol.com

Oil ETN Trading Rule Linear & Polynomial Daily Open & Close Regression Forecasts- Automated HTML Java Script Software Development

Abstract

This study develops O= il ETN Trading Rules using Linear & Polynomial Daily Open & Close Regression models. It forecas= ts using Automated HTML (Hyper Text Markup Language) and Java Script Software Development methods. This way= the software can run on any HTML Java script compatible device. Initially we developed the softwar= e in Microsoft Excel and then we have converted it to HTML and Java script. Exchange Traded Notes (ETNs) Oil funds are traded securities listed by Yahoo.com. The “iPath S&P GSCI™ Crude Oil Total Return Index ETN is a sub index of the S&P GSCI™ Commodity Index. The S&P GSCI™ Crude Oil Total Return Index reflects the returns that are potentially available through an unleve= raged investment in the West Texas Intermediate (WTI) crude oil futures contract = plus the Treasury bill rate of interest that could be earned on funds committed = to the trading of the underlying contracts.” as http://www.ipathetn.com/OIL-overview.jsp describes it. <= /o:p>

We can trade them just like stocks, except that they are not simple stocks, and they represent the Crude Oil industry index. As tradable instruments, traders c= an trade them, and for this purpose the traders may want to forecast their next day values. The purpose of th= is study is to develop a method that facilitates such forecasts and trades, as well as evaluates the risk. T= his study builds several linear and polynomial models regressing Open and Close= Oil ETN values on date, and forecasting the values. These forecasts help measure the e= rrors and develop methodology for automated, continuous quality improvement in the trading rules. It conducts te= sting hypotheses using ANOVA regression and residual analysis and plots, compares= and contrasts various methods and concludes with some recommendations.

INTRODUCTION AND LITRATURE REVIEW

Exchange Traded Notes

As Wikipedia, the free encyclopedia (http://en.wikipedia.org/wiki/Exchange_Traded_Not= es) explains as follows:”Jump to: navigation, search

Exchange Traded Notes (ETNs) are senior, unsecu= red, unsubordinated d= ebt securities issued by an underwriting bank. Similar t= o other debt securities, ETNs have a maturity date and are backed only by the credi= t of the issuer.

ETNs are designed to provide investors access to the r= eturns of various market benchmarks. The returns of ETNs are usually linked to the performance of a market benchmark or strategy, less investor fees. When an investor buys an ETN, the underwriting bank promises to pay the amount reflected in the index, minus fees upon maturity. Thus an ETN has an additi= onal risk compared to an ETF - upon any reduction of credit ratin= gs or if the underwriting bank goes bankrupt, the value of the ETN will be advers= ely eroded.

Though linked to the performance of a market benchmark= , ETNs are not equities or index funds, but they do share several characteris= tics of the latter. Similar to equities, they are traded on an exchange and can = be shorted. Similar to index fun= d, they are linked to the return of a benchmark index. But as debt securities, ETNs don't actually own anything it is tracking.

The first ETN, marketed as the iPath Exchange-Traded N= otes, was issued by Barclays Bank PLC on 12 June= 2006. This was = soon followed by Bear Stearns, Goldman Sachs & Swedish Export Credit Corp. In 2008, additional issuers entered the market with their own offerings; these inclu= de Deutsche Bank, UBS,= Lehman Brothers, Morgan Stanley and Credit Suisse. As of April 2008, there were 56 ETNs from nine issuers tracking different indexes. The popularity of ETNs is mainly due to the advantages t= hat it offers to investors.<= /p>

Structure of ETNs

The returns of ETNs are linked to the performance of a market benchmark or strategy, less investor fees. Currently, there are four types of ETNs, Commodity ETNs, Emerging Market ETNs, Currency ETNs and Strateg= ies ETNs available in the market. (Please refer to Appendix A for a list of available products in each category.)

As discussed previously, ETNs are debt notes. When hel= d to maturity, the investor will receive a cash payment that is linked to the performance of the corresponding index during the period beginning on the t= rade date and ending at maturity, less investor fees. Typically, ETNs do not off= er principal protection.

ETNs could also be liquidated before their maturity by trading them on the exchange or by redeeming a large block of securities directly to the issuing bank. The redemption is typically on a weekly basis= and a redemption charge may apply, subjected to the procedures described in the relevant prospectus.

The investor fee is calculated cumulatively based on t= he yearly fee and the performance of the underlying index and increases each d= ay based on the level of the index or currency exchange rate on that day. Beca= use the investor fee reduces the amount of return at maturity or upon redemptio= n, if the value of the underlying decreases or does not increase significantly, the investor may receive less than the principal amount of investment at maturity or upon redemption.

Since ETNs are unsecured, unsubordinated debts, they are not rated, but are backed by the credit of underwriting banks. Like other debt securities, ETNs do not have voting rights. But unlike other debt securities, interest will not be paid during the term of the most ETNs.

Pros and Cons of ETNs

Advantages

Tax efficiency

ETN offers a tax-efficient way to invest. It is treate= d for tax purposes as prepaid contracts (A prepaid contract is a financial instrument, such as a forward contract. The owner of a prepaid contract pay= s an initial amount in order to receive a future contingent payment based on the value of an index or other underlying benchmark at a specified time).

Very often index m= utual funds and ETFs are required to make yearly income and capital gains distributions to fund holders which are taxable. Meanwhile, for ETF, when a= fund is forced to sell stock to change its composition, for example, when an ind= ex rebalances, the fund holders have to pay tax on whatever the capital gain w= as, when the stock is sold.

In contrast, for ETN, there is no interest payment and dividend distribution, so neither the tax. The timing of the realization of gains or losses on their ETN is based on when investors buy and sell their investmen= ts. Since the entire gain is treated as a capital gain, the investor can defer = any gain until the security is either sold or it matures. Because long-term capital gains are treated more favorably (Holding more than 1 year, all the gai= ns will be taxed as long-term gains at 15%) than short-term capital gains and interest, the tax treatment of ETNs should be more favorable than that of E= TFs. There is no way to avoid capital gains, but delaying it is valuable because= the amount that would have been paid as tax can continue to accumulate wealth. Control over the timing of this capital gain is a big benefit to any invest= or looking to defer the payment of income taxes.

Recent tax rulings have additionally suggested that ET= Ns may be qualified tax shelters for the purpose of changing current interest inco= me into deferred capital gains income.[1]

No tracking error

ETNs give investors a broad-based index without any tr= acking error to the index, doing away with the discrepancies that exist between the returns of many ETFs and their underlying indexes. One reason of the tracki= ng error observed in ETFs might be attributed to the diversification issues th= at stem from the inability of a fund to replicate an index due to an upper lim= it on the maximum asset allocation to a single stock. But for ETN, this constr= aint does not exist, because though ETN is also tracking the index, the return is not based on the underlying securities. The ETN issuer guarantees the holde= r a return that is an exact replica of the underlying index, minus = expense fees. The bank also agrees to pay large shareholders the exact value of the note on a weekly basis through redemption, which helps the ETNs track very closely to the underlying index return.

Liquid struc= tured product

ETN is a significant innovation to improve liquidity o= f structured products. Not like other buy-an= d-hold structured products, ETN can be bought and sold during normal trading hours= on the securities exchange. For institutional size redemption, investors may o= ffer their ETN for repurchase by the issuer on a weekly basis. Investors can eas= ily track the performance of their ETN. In this sense, ETN is structured to resemble ETF. But ETN is different from ETF, as they consist of a debt instrument with cash flows derived from the performance of an underlying as= set – a structured product.

A= ccess to new markets and strategies

ETNs have provided access to hard-to-reach exposures, = such as commodity futures and the Indian stock market. Certain asset classes and strategies are not easily accessible to individual investors. For example, = the “momentum investing” strategy, which is used in SPECTRUM Large = Cap U.S. Sector Momentum Index, is to take advantage of the varied performances= of the 10 sub-indexes of the S&P 500 Total Return IndexSM (SPTR) relative = to each other and to the SPTR. The weights of the 10 sub-indexes are computed = each day based on performance and correlation. This makes SPECTRUM Large Cap U.S. Sector Momentum Index difficult to track through ETF. On the contrary, ETN provides opportunities to gain exposure to these types of investment strate= gies in a cost-efficient way.

Disadvantages

C= redit Risk & Lack of Risk Metrics

ETNs, as debt instruments, are subject to risk of defa= ult by the issuing bank as counter party. Even though the possibility of default turning into a reality is relatively low, it ought to be measured and accou= nted for. ETN investors will require a credit risk metric that facilitates answe= r to questions regarding the magnitude of the risk and its variation with time. = With new players foraying into the ETN space, how will the risk vary by issuer? = Who will take up the risk evaluation process? If and when the ETN sector grows,= in order to partcipate, retail and institutional investors will need a source = for ETN key data which is easy to assimilate.

Illiquidity<= o:p>

Given its relative newness, there is a flurry of ETNs hitting the market. They are, however, yet to engage the market players enthusiastically, several of whom are probably opting for the wait and watch approach. Under such circumstances, the liquidity of the notes in the secon= dary markets may be threatened should they fail to gain sufficient trading momen= tum. The effectiveness of ETNs at tracking indices is contingent on their abilit= y to garner enough support in the market.

Another flipside of ETNs relates to their redemption feature. While ETNs can be sold daily on the secondary markets or held until maturity, institutional investors who wish to redeem blocks of 50,000 units= or more directly with the issuer can only do so once a week. In contrast, other structured products, ETFs for instance, can be redeemed anytime during a trading day.

Tax benefits speculative

The ETN issuers are using tax efficiency as their trump card. As things stand, there is significant tax saving to be gained from investing in ETNs. In reality, however, the Internal Revenue Service is yet= to decide on the proposed tax treatment. So, the tax benefit status is still arguable.

Dependenc= e on credit ratings<= /p>

ETNs have their worth decided by two factors:

• Performance of the index they are set to track=

• Credit ratings of the issuer

Suppose the issuing bank has been impacted negatively,= if only marginally, by a crisis like the recent (2007-2008) subprime mortgage turmoil and the ratings agencies depreciate the overall credit rat= ing of the issuer to reflect the event.

In the aforementioned set-up, even thought the index i= t is tracking is showing growth, a decline in rating of an ETN issuing financial institution could negate the worth of an ETN.

&= nbsp;

Unprofitable trading strategies

The GSCI has lost nearly 20% of its value since January 2006, despite soaring commodity prices, all thanks to Contango. This is one instance where ETN tracked commodity indices like GSCI have ended up doing exactly the opposite of what they had set out to do.

Contango is a scenario where the cost of the next-month futures contract is costlier than the current month contract. In this event, the issuing bank books a loss each time a current month contract is sold and the next month contract is bought. Contango has hit hard the energy futures over the past few years and markedly brought down the returns from energy markets. Indices are taking varied steps to hedge against the condition. Th= eir results remain to be seen though.

The UBS Bloomberg Constant Maturity Commodity Index (C= MCI) addresses the issues of Contango and b= ackwardation by introducing the concept of constant maturity, which provides diversifica= tion across futures contract maturity dates. This is intended to smooth out the volatility often associated with commodity investments.

Prospect and Conclusions

As a new product, ETN has a very short history. Howeve= r, it has been growing very rapidly. The ETN represents a nifty product structure that is gaining respect and funding in the market. By 18 July= 2006, just one = month after the launch of first two ETNs, GSP and DJP, GSP had attracted more than $40 million in assets, and DJP had pulled in more than $130 million for Barclays. Investments in iPath ETNs surpassed $2 billion by late April 2007= . In just over a year Barclays has gathered close to $3 billion in eight funds. Encouraged by the good performance of the ETNs launched by Barclays, other financial institutions have either launched their own products or are drawi= ng plans to partake of the ETN space. We believe more ETNs will be launched to raise more equity for financial institutions. For the customers, the advant= ages such as tax-efficiency and good liquidity of ETNs will attract more investo= rs to this innovative structured product. All of these imply that ETN is becom= ing more and more popular.

However, now the question is whether this trend is goi= ng to last long. Several industry gurus point to factors that may well dampen the initial euphoria surrounding this product of financial engineering. The lac= k of historical record – upon which to base their decision to make ETN a p= art of their portfolio or not – could be keep potential investors at bay. More importantly, the issuing banks advertise tax-efficiency as ETNs USP. If the IRS rules in the issuers’ favor, the implications of which have b= een discussed at length in Chapter 3, ETN sales could explode. But what if the = IRS delivers an unfavorable word-or never rules? A line of thought that is doin= g rounds is that even if the IRS delivers an unfavorable word-or never rules at all-= the ETNs could still be enormously successful. The reason is that ETNs provide efficient access to segments of the market that would otherwise be difficult for retail investors to reach. But how could we expect that the investors w= ould still prefer ETNs to ETFs, or any of the multitudes of other structured products out in the market, if there is no tax-efficiency for ETNs. Drawing= a comparison to ETFs, another structured product, which suffers from only mar= ket risk, ETNs face both counter party risk and market risk. ETNs, bereft of th= eir tax advantage, may lose their shine in the eyes of an entire class of investors.

To conclude, ETNs have performed very well so far as a= new kind of structured product with lower fees, better liquidity and tax-efficiency. However, both financial institutes and investors should kee= p an eye the status of the tax opinion from the IRS on ETNs while seeking ETNs as business or investment possibility.”

Forecasting sales, expenses and stock market values by quarterly financial statement ratio analysis: a microcomputer software development model

“Forecasting sales, expenses and stock market value= s by quarterly financial statement, “ has been done by using ratio analysis and “a microcomputer software development model,” as the Author= (s):

Avi Rushinek, Sara F. Rushinek describe, in “Manage= rial Auditing Journal,” Year:

1995.

The present case study demonstrates a financial statement= ratio analysis (FSRA). This analysis matches company to industry data and builds sales forecasting models. FSRA imputes forecast standards of sales and cost= s, and applies them to a budgeted financial statement variance analysis for th= e EE (electronic and electrical) industry. The present study is similar = in dealing with an industry, except that the current industry is the Oil and G= as industry (Oil). Likewise, this study demonstrates a financial statement ratio that is the daily growth rat= e of the Oil ETN.

That study “Develops the concept of industry base standards, integrating them into the more traditional statistical and accounting concepts of quality control standards. Provides an implementation example, and reviews possible improvements to the current methodology and approach and uses a similar methodology to forecast the stock market value = with some exceptions.” Likew= ise, the current study develops the concept of industry base standards, of the d= aily Oil ETN growth rate, integrating them into the more traditional statistical regression analysis of forecasting the next day value, and accounting conce= pts of quality control standards, to gauge standard deviants and distinguish th= em from abnormal deviants. As lo= ng as the real growth follows the model within the bounds of the standard error, = it is considered to be a normal deviant. As soon as it exceeds the standard, it is considered an abnormal deviant, and a sell order is issued.

That study provides an implementation example, and reviews possible improvements to the current methodology and approach and uses a similar methodology to forecast the stock market value with some exceptions= . Likewise, the current study does t= he same except that it uses new software techniques that were not available before. Instead of forecasting an individual stock market value the current study forecast the entire fund.

The previou= s study described a “Models sales and costs of an individual company and an industry based largely on aggregate industry databases.” The current study is using the ETN= index fund, which resembles the Oil industry.&nb= sp; The previous study “uses a multivariate linear trend regression analysis for the sales forecasting model.” This study is using a Univariate (1 independent variable, the Julian date) instead of a multivariate (more than= 1 independent agruement variables). The previous study used only linear regression; the current study ad= ds non-linear (Polynomial) regression, to the mix.

Like the previous study, this study also “Defines a= nd tests related hypotheses and evaluates their significance and confidence levels.” For an illustr= ation the previous study uses the EE industry and the APM Company, while the current study uses the Oil industry and the ETN fund. The current study also demonstrates= microcomputer-based software similar to the “FSRA software that speeds, facilitates, and helps to accomplish the stated objectives” of forecasting the next day value, and deciding whether to keep or sell the fund. The current study like the “F= SRA software uses industry financial statement databases” from Yahoo. It computes a financial ratio of E= TN daily growth rate and builds forecasting models, to forecast its next day v= alue.

This study applies the th= eories and concepts related to Budg= eting, Financial statements, Models<= /span>, Ratios<= /span>, Sales forecasting, and Sta= tistics, as they apply to the Case study of the OIL ETN. (Article URL: htt= p://www.emeraldinsight.com/10.1108/02686909510079620)

THE OIL AND GAS INDUSTRIES LITRATURE REVEIW

The Oil and Gas industries are a unique industry with = some special characteristics. Rush= inek, A. and Rushinek, S. Explain s= ome of these characteristics in "Oil and Gas Mandated Accounting Changes and = Debt Covenants: Debt to Equity Maturity, Dividend/Retained Earning Reduction &am= p; Refinancing Cost Ratios", 1991, which impact ETNs. Since ETNs are based on debt coven= ants they affect a variety of issues related to the risk of losses.

As we discussed earlier the quality of the ETNs invest= ments “Dependence on credit ratings.”

ETNs have their worth decided by the Credit ratings of= the issuer. If the issuer is a collapsing company like Bear Stearns, then investors may have to settle for= a steep loss, converting their ETN into cash on a short notice. One way to be sensitive to such is= sues is to monitor the growth rate of the funds market values. As soon as the issuer suffers decl= ining credit rating the index may also reflect some of the risk in a slower growth rate. The objective of this s= tudy is to spot just risks and alert the investor to exit the investment before = it becomes worse.

Rushinek, A. and Rushinek, S. show that "Net Income-to-Sales Ratio Grouping For the Crude Petroleum and Natural Gas Indu= stry Sector” is related to “A Company to Peer Comparative Variance Analysis (1995).” In ot= her words companies within an industry influence their peer’s performance; therefore, taking a fund of an entire industry increases diversification, a= nd reduces risk of dealing with individual companies. For example if a company, as Rushi= nek, A. and Rushinek, S. explain experiences "Damage” using “Co= st Calculation Model for Exxon Corporation and the Oil and Gas Industry.”= ; A situation that describes “= Fraud… (March 1996) will have a very devastating impact on a single company. Likewise, as Rushinek, A. and Rush= inek, S. describe a "Tax Fraud…For the Petroleum Refining IndustryR= 30; Shell Oil, (1997)” will also have a terrible decline stock market val= ue effect on such a company. The rating and ranking of a company including their credit rating is likely to = be affected by a discovery of fraud, and its publicity in the press.

As Rushinek, A. and Rushinek, S. describe the negative= and the positive news affect the ”Rating and Ranking Best Practices of the British Petroleum Oil Company” and it extends to the entire “Oil & Gas Industry,” and eventually affects their “ Sales to Cash …Univa= riate Regression Trend Analysis..( 1997).”= Fraud publicity even if it is without merit may lead to an immediate decline in the value of the company, and thus lead to expensive litigations. As Rushinek, A. = and Rushinek, S. describe the”Litigation in Pennzoil and the Petroleum Re= fining Industry” and their impact on “Financial Ratio Automated Peer Review Analysis of Variance Internet Software... ( 1998).” Investors and traders pay attentio= n to the press as Rushinek, A. and Rushinek, S. shows how ”Correlating Investors’ Preferences to Stock Characteristics” may affect the stock markets values and eventually the ETN. Of the...” Crude Oil &am= p; Refining Industry ( 1999).”

Rushinek, A. and Rushinek, S. Show another example of the same pa= ttern in”Oil & Gas Market, Sector & Company Relative Strength Congruity Trading Theory...” in which they use “An Internet Automation Approach Applied to Chevron Corporation’s Stocks (2000).” This approach is similar to the cu= rrent study that is trying to produce a similar internet software model for ETNs.= Such models can be used, as Rushin= ek, A. and Rushinek, S. shows for “Forensic Audits of Stock Market Forecasts= .” In this case they applied the mode= l to “Texaco & the International Oil and Gas Industry.” Using “Financial Models for = Online Broker Litigation (2003),” they may help provide expert witness testi= mony and litigation support.

Rushinek, A. and Rushinek, S. use a similar approach i= n an “Automated Internet Trading Forecast Variance Analysis” for the “Oil and Gas Industry and BP Corporation” in a Case Study (2003= ).” Likewise, Rushinek, A. and Rushine= k S. demonstrated “Internet Web Se= rver Comparative Forecasting Sales Models” using “Reversed Accountin= g of Texaco Corp and The Oil & Gas Industry” and applying “linea= r, Exponential, Power, Polynomial & Logarithmic Univariate Regressions (20= 05).” The current study is using the same method, except that it applies them to ETNs instead of individual companies. The problem that t= hey encountered is violating some regression assumptions. As Rushinek, A. and Rushinek S. de= monstrate in “An Automated Business Intelligent Stock Market Matching Engine for the Oil and Gas Industry,” the normality assumption may be violated.<= span style=3D'mso-spacerun:yes'> We can control the problem of the = “Materiality of Violating the Normality Assumption of Linear Regression… in the OI= L, GAS, & ENERGY industry (2007).”&= nbsp; Rushinek, A. and Rushinek S. show the “Optimal Forecasting Mod= els for the Oil & Gas Industry” will take into consideration some problems and deal with them effectively. “A Study of the Daily Dow Jones U.S. Oil & Gas Index and ConocoPhillips= 221; is similar to the current study in that it deals with an index, which is similar to an ETN. Using the “Aid of the Virtual Internet Office,” they are solving some problems of improving the performance of the investors (2008).”

As Michael Werner and Kumen Jones demonstrate in the m= ost elementary accounting textbook “Introduction to Management Account= ing – A User Perspective”, (Second Edition, Prentice Hall, M-13= 5, 2003), an XY scatter chart is the most basic way to forecast forward and ad= d a trend line. As they describe a “Microsoft Excel Scatter Graph with a trend line,” Exhibit 5-16 and 5-17, they show how to forecast the cost forward into the future. This= study does the same, but in addition to the chart and the mathematical function it also deals with the statistical test of hypothesis.

Data Collection

Appendix A shows the last week of data collected from Yahoo.com. Using Microsoft Ex= cel we have calculated the following models. As we converted the calculations from the excel format, to HTML (Hyp= er Text Markup language) format with java script, we can perform this analysis, without Microsoft Excel being present on either the server or the client computer. Likewise, it = will also run on any device that supports HTML and Java. Such devices may be portable cell telephone, personal digital assistants, etc.

The Linear Regression Analysis and the Least Squares M= ethod Model of Total Cost Calculations

As Michael Werner and Kumen Jones show “The Line= ar Regression Analysis and the Least Squares Method Model of Total Cost Calculations” follows this format:

Y=3D a + bx

Where:

Y =3D the dependant variable in our case the daily val= ue of the ETN fund

a =3D the intercept of the value of Y when X is equal = to zero, which is the Julian date value

b =3D the slope coefficient the change in Y the ETN da= ily value as a result of an increase of 1day, change of X

X =3D the independent variable, the Julian date of the= ETN stock market value

Table 0	Poly Linear Models of Regressions of Open or Adj. Cl= ose on Date of a Year or a Month
Model 1
	1 year 1 Day Lag Adj. Close on Date

	Poly
	y =3D 5E-11x⁶ - 1E-05x⁵ + 1.15= 4x⁴ - 60847x³ + 2E+09x² - 3E+13x + 2E+18
	R² =3D 0.963 Not Forwarded 1 Day

	y =3D 5E-11x⁶ - 1E-05x⁵ + 1.15= 4x⁴ - 60847x³ + 2E+09x² - 3E+13x + 2E+18
	R² =3D 0.963 Forward 1 day

	Linear
	y =3D 0.207x - 8119.
	R² =3D 0.957

	Comparison	Function	R Square
	Line 1	Poly	96.300%
	Line 2	Linear	95.800%
	Line 1-2	Difference	0.500%	=3DP25-P27

Model 2
	1 Year 1 Day Lag Open on Date
	y =3D 0.000x² - 10.01x + 19406
	R² =3D 0.960
	y =3D 0.209x - 8204.
	R² =3D 0.959

	Comparison	Function	R Square
	Line 1	Poly	96.100%
	Line 2	Linear	96.000%
	Line 1-2	Difference	0.100%	=3DP25-P27

Model 3	1 Year 1 Day Lag Open on Date
	y =3D 7E-11x⁶ - 2E-05x⁵ + 1.65= 9x⁴ - 87493x³ + 3E+09x² - 4E+13x + 3E+17
	R² =3D 0.966
	y =3D 0.209x - 8203.	0.967
	R² =3D 0.957	0.958

	Comparison	Function	R Square
	Line 1	Poly	96.700%
	Line 2	Linear	95.800%
	Line 1-2	Difference	0.900%	=3DP25-P27



Model 4	1 Month Open on Date
	y =3D -6E-08x⁶ + 0.013x⁵ - 130= 8.x⁴ + 7E+07x³ - 2E+12x² + 3E+16x - 2E+20
	R² =3D 0.823
	y =3D 0.162x - 6351.	0.824
	R² =3D 0.570	0.571

	Comparison	Function	R Square
	Line 1	Poly	82.400%
	Line 2	Linear	57.100%
	Line 1-2	Difference	25.300%	=3DP25-P27

Table 0 shows t= he “Poly Linear Models of Regressions of Open or Adj. Close on Date of a Year or a Month models. We wa= nt to find out which time period is better, is it better to use a month or a year= , and is it better to use Open, Open Lagged 1 day, or Adj. Close? Is a linear or a Poly model better (having a higher R Square). T= he R Square measures the quality of the regression line the highest possible val= ue is 100%, a perfect predictor, and the lowest possible value is zero, which means no predictive abilities. The tables shows several models, some are linear, some are polynomial (Poly), a= nd some are regressing the Open on Date, while others are regression the Adjus= ted (Adj.) Close on Date, some are lagged and others are not lagged.

Model 1 describes a 1 year 1 Day Lag Adj. Close regres= sed on Date, using both linear and Poly regressions. The Adjusted close is the Cl= ose adjusted for anomalies such as dividend distributions, or other events that= may affect the price in an inconsistent way.&n= bsp; The model is a Polynomial of the 6^{th (x6 raised to the power of=
6)} level as the number of terms in the formula shows: y =3D 5E-11x6 - 1E-05x5 + 1.154x4 - 60847x3 + 2E+09x2 - 3E+13x + 2E+18. One Poly model includes a forward forec= ast of 1 day adjustment and the other contains no such forward forecast. There is no difference between the models. Therefore, we conclud= e that you might as well ignore the option for forward forecast adjustment of 1 day. The Poly Forwarded 1 day, means that we have checked the option of forward forecast and entered the v= alue of 1, in the Microsoft Excel regression add a Trend dialog box, to see whet= her it affects the Poly model R Square. The results show no differences at all.

---Chart 1 --- Insert here

Chart 1 describes the Adj. Close Yearly model (January= -July); it includes both the Polynomial and Linear regression models. We can see clearly that when the d= ependant variable is the Adj. Close, several assumptions are not violated, including= but not limited to the linearity assumption.&n= bsp; The trend is clearly linear, and it is obvious that the Poly functio= n does not have a much better fit. W= e can also see that the forward 1 day adjustment makes no difference in the R Squ= are or the construction of the Poly and Linear model function. Likewise, the difference in the R = Square between the linear and the Poly models is very small. Therefore, if you have to use an A= dj. Close, due to trading at night it will have a similar pattern compared to forecasting Open, without many benefits to the adjustments and the delay th= at the Close imposes.

The next is the linear function of the same model: y =3D 0.207x - 8119. The R² =3D 0.957 resulting fr= om this linear model is slightly lower than the previous Poly model. The Comparison of Function and R Sq= uare shows for Line 1, Poly of 96.300%, and for Line 2, Linear of 95.800%. The difference, Line 1-2, Difference=3D0.500% =3DP25-P27, one half of 1 percent. The Poly model is better than the = linear model by less than 1% or R Square. This is a small difference by comparison with the 1 month model.

Model 2 describes 1 Year 1 Day Lag Open on Date, using= the unadjusted Open instead of the Adjusted Close is the difference between mod= els 1 and 2. The biggest differen= ce between model 1 and 2 are the dependant variables, Open Versus Adj. close.<= span style=3D'mso-spacerun:yes'> The R Squares are almost the same,= the Comparison shows Line 1-2, with a Difference of 0.100% =3DP25-P27, one tenth of 1 perc= ent, which is less than one half of 1 percent, but not that different.

---Chart 2 --- Insert here

Chart 2 shows that for a yearly model of 6 month of mo= re, the Open of Date regression Linear and Poly model produce a similar R Squar= e, and therefore, we should use the linear.&n= bsp; It is much simpler, easier to understand and use, especially for instructional purposes. Forec= asting Open is better than Close since most actions in the markets occurs in the morning. Forecasting the Adj.= Close for the same number of observation produces similar R Square, due to the adjustments, which may have some confounding affects. The 1 day lag has no significant a= ffect when dealing with a period of 6 month or more. However, it may be theoretically m= ore appropriate, and therefore may be worthwhile to pursue.

&nbs= p; &= nbsp; &nbs= p; &= nbsp;

Model 3 shows the 1 Year 1 Day Lag Open on Date, the b= iggest difference here is that we have lagged the Date 1 day, shifted it 1 day, resulting in: y =3D 7E-11x6 - 2E-05x5 + 1.659x4 - 87493x3 + 3E+09x2 - 4E+13= x + 3E+17, and R² =3D 0.966, for the Poly model. For the linear model we get: y =3D= 0.209 x – 8203 and R² =3D 0.957. The Comparison of the Function R Square grows, for Line 1-2, the Dif= ference is 0.900% =3DP25-P27, is almost 1 percent, larger but still insignificant d= ifference of less than 1%.

---Chart 3 --- Insert here

Chart 3 describes the Oil ETN but reverses the directi= on of the X axis. Therefore, graphi= cally speaking the trend appears to be down.&nbs= p; In fact the trend goes up, as the positive slope shows. This may be confusing for the read= ers due to the convention that goes in the opposite direction. Avoid such presentations since it = may be confusing, and misleading the readers.&nbs= p; However, it confirms the initial notions about the superiority of the Poly model, and the relatively smaller advantage, as the time period rises, compared to shorter time periods of only 1 month, for example. &= nbsp; &nbs= p;

Model 4 describes the 1 Month Open on Date, with a Pol= y of y =3D -6E-08x6 + 0.013x5 - 1308.x4 + 7E+07x3 - 2E+12x2 + 3E+16x - 2E+20, and = R² =3D 0.823, and a Linear model of y =3D 0.162x – 6351, R² =3D 0.5= 70, which is much more different than prior models. The Comparison Function R Square sh= ow for Line 1, Poly of 82.400%, and for Line 2&nbs= p; Linear only 57.100%. The Line 1-2, D= ifference of 25.300% =3DP25-P27, is huge by comparison and rather significant.

---Chart 4 --- Insert here

Chart 1 describes the Open Monthly model (June-July); = it includes both the Polynomial and Linear regression models. We can see clearly that when the dependant variable is the Open, in the Monthly model several assumptions are violated, including but not limited to the linearity assumption. The trend is clearly not linear, a= nd it is obvious that the Poly function does not have a much better fit. Likewise, the difference in the R = Square between the linear and the Poly models is very large. Therefore, if you have to use mont= h of data only, due to trading with a new company, use the Poly model, at least = to verify and confirm the linear trend, it almost doubles the R Square. Otherwise, use at least 6 month of= data or a full year. The full year= will display the trend in a much more reliable way, if it is linear.

Data Analysis

SUMMARY OUTPUT

Table 1

Regression Statistics

Multiple R

96.40%

R Square

92.94%

Adjusted R Square

92.88%

Standard Error

2.78892967

Observations

130

SUMMARY OUTPUT, in Table 1, shows the Regression Stati= stics, with Multiple R 96.40%, R Square 92.94%, and Adjusted R Square of 92.88%. It concludes that the da= te explains over 90% of the variation in the ETN Oil value. It includes the number of Observat= ions of 130, days since the beginning of year 2008, about 7 month (Jan-July).

HYPOTHESIS TESTING

ANOVA		Table 2
	df	SS	MS	F	Significance F
Regression	1	13103.76	13103.75819	1684.693	1.5553E-75
Residual	128	995.6005	7.778128702
Total	129	14099.36
		Table 3
	Coefficients	Standard Error	t Stat	P-value	Lower 95%	Upper 95%
Intercept	-7245.095698	178.136	-40.6717147	4.61E-75	-7597.5682	-6892.62323
Date	0.184903278	0.004505	41.04501064	1.56E-75	0.17598958	0.19381697

The ANOVA (Analysis of Variance), in Table 2, shows the statistical significance of both the entire linear 1 year model, and its intercept and slope. It inclu= des the column headers of: df, SS= , MS, F, and Significance F. The Regre= ssion line with an F of 1684.692899, and Significance F of 1.55533E-75, is much l= ess than the threshold of 5% to reject the null hypothesis, for the entire model. Thus, we reject the nu= ll hypothesis stating the R Square equal to zero, in favor of the alternative hypothesis that it is greater than zero.

Table 3 shows the rejection of the null hypothesis reg= arding the intercept and the X variable, Date.&nb= sp; It shows the headers of Coefficients, Standard Error, t Stat, and P-= value, as well as Lower 95%, and Upper 95%. The Intercept with P-value of 4.61127E-75 is less than 5%, as well as the Date with 1.55533E-75, respectively is also less than 5%. Therefore, we can reject the null hypothesis stating that they are zero, in favor of the alternative hypothes= is stating that they are different than zero.

RESIDUAL OUTPUT		Table 4		PROBABILITY OUTPUT
Observation	Predicted Open	Residuals	Standard Residuals	Percentile	Open
1	83.91553893	-1.13554	-0.40874677	0.38461538	50.62
2	83.73063565	1.109364	0.399325011	1.15384615	50.72
3	82.99102254	3.528977	1.270285066	1.92307692	51.01
4	82.80611926	1.503881	0.541334499	2.69230769	51.52
5	82.62121598	3.098784	1.115433324	3.46153846	51.78

The RESIDUAL OUTPUT, Table 4, shows the PROBABILITY OU= TPUT, it includes the Observation, Predicted Open Residuals, Standard Residuals, Percentile, and Open ETN values of the last day going backward in time. Accordingly, observation 1 shows t= he day value of 83.91553893 and its stock market value of $50.62, for the last observation, and the last day.

---Chart 5 --- Insert here

Chart 5 (Chart 5b: Date Residual Plot) displays= the extent to which some of the regression assumptions are met. As we can see the residuals are not exactly randomly distributed around the mean of zero. The violation of this regression assumption leads to our recommendation to construct a Poly model just to co= nfirm that the loss or R Square is not too high, due to the distribution of the residuals.

As Rushinek, A. and Rushinek S. suggested “An Automated Business Intelligent Stock Market Matching Engine for the Oil and= Gas Industry” may include the comparison of the Poly and the linear models R-Square difference. The larger the difference the more material is the violation and the departure = from the regression assumptions concerning the residual distribution around the = mean of zero. Likewise, the normal= ity assumption violation may be assessed in a similar way. Look at the “Materiality of Violating the Normality Assumption of Linear Regression Control Analysis”, as the OIL, GAS, & ENERGY QUARTERLY describes (2007).<= /p>

Chart 5 a Normal Probability Plot shows that the distribution approaches half a bell curve as we increase the period to over= 6 month. Keep such violation un= der control by monitoring this plot on a regular basis.

Table 5	Forecasted compared to Actual ETN values using the l= ast day observed
Columns J	K	L	M	N
Line19		Coefficients
Line20	Intercept=3Da		-7245.095698
Line21	Date=3Db	0.184903278
Line22	Today=3DX	Tuesday, July 08, 2008
Line23	Today Julian	39637.00		=3DL22
Line24	Date*Today		7329.01	=3DK26*K28
Line25	Forecasted=3DY		$ &nbs= p; &= nbsp; &nbs= p; 83.92	=3DSUM(L25:L29)
Line26	Actual		$ &nbs= p; &= nbsp; &nbs= p; 82.78	=3Doil= !B3
Line27	Difference		$ &nbs= p; &= nbsp; &nbs= p; (1.14)	=3DL31-L30
Line28	%Difference		-1%	=3DL32/L31

Table 5 shows t= he Forecasted compared to Actual ETN values using the last day observed, in an Excel template including the Columns J, K, L, M, and N, and how we apply the model of Y=3Da+bX to the forecast. Line19 shows the Coefficients. Line20 shows the Intercept=3Da, with a value of -7245.095698 days. Line21 is the Slope variable coeff= icient of Date=3Db with a 0.184903278, which is about $.18 daily growth rate of an= ETN share. Line22, Today=3DX, is = the last Date value of this study, which is Tuesday, July 08, 2008. Line23, Today Julian, converts the Date format to its numerical counter part of 39637.00, about 39,637 days since Christ was born.&n= bsp; In the right most column, the table shows the Excel formula behind t= he number, in this case =3DL22, the source of to-days date. Line24 shows the product of Date coefficient times the value of Date, Date*Today, 7329.01=3DK26*K28, which i= s the formula. Line25 shows the sum= of the intercept plus the coefficient effects on the forecasted value, Forecasted=3DY, $83.92, as well as the Excel formul= a =3DSUM(L25:L29). Line26 shows the Actual ETN value = of the last day of $82.78, carried forwarded by the formula of =3Doil!B3.

A Negative Variance of Forecasted compared to Actual S= tock Market Value Budget Adjustment

Finally, Line27 calculates the Difference, or Error as $(1.14)=3DL31-L30. This is a = negative variance, since the Actual value is lower than forecasted, indicating that = the actual profit, had we purchased the stock, would have been lower than expec= ted, generating a lower profit than forecasted.= Therefore, it is a negative effect on profitability, producing a Deb= it entry of $1.14 to adjust the expected forecasted profit, which was too high= , to the actual lower profit level. Thus the forecasted profit exceeds the actual profit and therefore some regard i= t as negative, since our objective is to maximize profit. Any transaction that reduces the a= ctual profit, compared to forecasted profit, is regarded as negative.

Exit Strategy and Automated Stop Rules

Line28, does the same in %Difference of -1%, and =3DL3= 2/L31. As expected the difference is less= than 10%, as the R Square was its complement of 90%, which together adds, and sh= ould add to 100%. In the next level of analysis, we should try to forecast the n= ext day value. In our case that w= ill be the value of this ETN on the Wednesday following Tuesday. We should calcula= te and reassess the model, and repeat the process automatically every day. If the R Square drops below 90% an= d/or our Error rate exceeds 10%, it shows that the model is too instable to use = it as a decision making tool. Likewise, if the value of the funds daily growth declines below a minimum value of our threshold. At such a point, the program should automatically exit this investment and con= vert the ETN to cash, looking for a better opportunity. This indicates that this ETN is not sufficiently profitable, and another investment may be more profitable.

Table 6	Excess of Monthly Growth over Annual Interest
Columns J	K	L	M	N
Line 38	Open		$ &nbs= p; &= nbsp; 50.62000
Line 39	Date	X-Coefficient	$ &nbs= p; &= nbsp; &nbs= p; 0.18490
Line 40	Daily growth rate(X Coefficient) =3D	0.36528%	=3DB18/G25
Line 41	Annual Interest rate=3D	5.000%
Line 42	Days in Year=3D	360	days
Line 43	Daily Interest rate =3D		0.01389%	=3DK41/K42
Line 44	Daily Growth % Gain =3D		0.35139%	=3DL40-L43
Line 45	Days in a week=3D	6	days
Line 46	Daily Growth % Gain =3D		2.10833%	=3DL44*K45
Line 47	Week in a Month=3D	4	days
Line 48	Monthly Growth % Gain =3D	8.43332%	=3DL46*K47
Line 49	Annual Interest rate=3D	5.000%
Line 50	Excess of Monthly Growth over Annual Interest	3.43332%	=3DL48-L49

Table 6 shows t= he “Excess of Monthly Growth over Annual Interest.” It shows Colum= ns J K L M and N.

Line 38 s= hows the Open stock market value of $50.62000. Line 39 has the Date, X-Coefficient, of $ 0.18490, daily growth date per Ju= lian date. As the table converts t= his gain, and compares it to our typical interest rate, the table concludes that Line 50, shows the Excess of M= onthly Growth over Annual Interest t= o be 3.43332%, calculated by the formula =3DL48-L49. In a month this investment earns m= ore than an entire year’s interest by over 3%, which is more than half the weekly interest earning.

--- Appendix B &n= bsp; --- Insert here &n= bsp; = ; &n= bsp; = ; &n= bsp;

Appendix B shows the automatic update from http://finance.yahoo.com/q/h= p?s=3DOIL of the next day of = &nb= sp;

iPath S&P GSCI Crude Oil Tot Ret Idx ETN (OIL) inc= luding the PRICES, Date, Open, High, Low, Close, Volume, and Adj. Close with a new= day record for Wednesday, July 09, 2008. This date has not been included in the production of the previous forecasting models that have been completed 1 day ago. So this day is a sor= t of a “hold-out” data sample, with the following values of a new op= en $82.02. Using this Open let&#= 8217;s compare the actual and the forecast using the previous date model. We therefore, compare the actual of $82.66 with the forecast for the new day of Wednesday, July 09, 2008.

“HOLDOUT” DATA TO TEST = THE FORECASTING FUNCTION- LEAVE OUT THE TOP 2 OBSERVATIONS

Table 5a	Forecasted compared to Actual ETN values using the d= ay after the last day observed
	Columns J	K	L	M
Line 3		Coefficients
Line 4	Intercept=3Da		-7245.0957
Line 5	Date=3Db	0.184903278
Line 6	Today=3DX	Wednesday, July 09, 2008
Line 7	Today Julian	39638.00		=3DL22
Line 8	Date*Today		7329.1961	=3DK5*K7
Line 9	Forecasted=3DY		$ &nbs= p; 84.10	=3DSUM(L4:L8)
Line 10	Actual		$ &nbs= p; 82.02	=3DB7 =
Line 11	Difference		$ &nbs= p; (2.08)	=3DL10-L9
Line 12	%Difference		-3%	=3DL11/L10


Table 6a	Excess of Monthly Growth over Annual Interest
	Columns J	K	L	L
Line 17	Open		$ 82= .02000	=3DB7
Line 18	Date	X-Coefficient	$ &nbs= p; 0.18490	=3DK5
Line 19	Daily growth rate(X Coef) =3D	0.22544%	=3DL18/L17
Line 20	Annual Interest rate=3D	5.000%
Line 21	Days in Year=3D	360	days
Line 22	Daily Interest rate =3D	0.01389%	=3DK20/K21
Line 23	Daily Growth % Gain =3D	0.21155%	=3DL19-L22
Line 24	Days in a week=3D	6	days
Line 25	Daily Growth % Gain =3D	1.26929%	=3DL23*K24
Line 26	Week in a Month=3D	4	days
Line 27	Monthly Growth % Gain =3D	5.07715%	=3DL25*K26
Line 28	Annual Interest rate=3D	5.00000%
Line 29	Excess of Monthly Growth over Annual Interest	0.07715%	=3DL27-L28

Table 5a shows the Forecasted compared to Actual ETN v= alues using the day after the last day observed.= This is important to note that you should have a “holdout̶= 1; data to test the forecasting function.&nbs= p; Even if the difference is less than 10%, from a methodological standpoint it is best to leave out the top 2 observations for testing purpo= ses.

As we can see, the intercept and the X coefficient rem= ain the same, Line 3 Coefficients, for Line 4 Intercept=3Da and -7245.0957, Lin= e 5 Date=3Db0.184903278, as we saw in the last observation testing the model and calculating the forecast residual. This time = we take it one more day forward, which is in Line 6, Today=3DX, Wednesday, Jul= y 09, 2008, one day after the last day of the last observation in the data used to calculate the forecasting models. Line 7, Today Julian value of 39638.00, =3DL22, leads to the calculation in Line= 8, Date*Today, calculates the next day 7329.1961, =3DK5*K7, and finally Line 9, the next d= ay forecast. Forecasted=3DY, sho= w the $84.10, =3DSUM(L4:L8) of the interc= ept plus the X-value times the Coefficient less Line 10, the Actual $82.02, =3DB7. As expected in line 11, the Difference $(2.08), =3DL10-L9, Line 12, = the %Difference of -3%, =3DL11/L10, is higher in the Hold-Out data compared to the last day= , but not large enough to change our decision.

SUMMARY, CONCLUSIONS AND IMPLICATIONS

Summary

We have compared across multiple models concluding tha= t a year model is much better than a month model. Likewise, a year polynomial model = is superior to a linear model for the ETN Oil fund, but the difference is small. A linear model is good enough, and that may explain, why people tend to use it. We have tested and rejected the nu= ll in favor of the alternative hypothesis.

Conclusion

The Poly model is better than the linear model, but the difference increases as we decrease the period from the entire current year (start of the year to do-day, to 30 a whole month,) is becoming huge>25%= . We conclude that we should u= se the entire year if possible. If w= e have to use only 1 month, than try to use a Poly model, since it will boost the accuracy by over 25%.

Implications

Oil ETN seems like a good and profitable investment strategy, but we have to monitor it continuously. It can turn on a dime, as soon as = a new war in the Middle East breaks out, over night. In such a case investors and trade= rs should be very careful and notice that tensions are building up. Price of oil may rise again increa= sing the profitability of such Oil ETNs. On the other hand, if normality returns to the market place, the oil markets may settle, and the abnormal profit will decline with it. If that is the case, do not wait u= ntil it is too late to cash in and take the profit, because in another day it ma= y be gone. This study presents an automated decision too= ls to exit on time, and to see warning on time.&= nbsp; Using an automatically recalculating regression analysis with daily forecasts and variance error analysis will help spot trend changes early en= ough to maximize the return on investment (ROI) on the Oil ETN.

References

Avi Rushinek, Sara F. Rushinek "Forecasting sales, expenses and stock market values by quarterly financial statement ratio analysis: a microcomputer software development model," Managerial Audi= ting Journal, Year: 1995, Volume: 10, Issue: 2, Page: 7 – 33, DOI: 10.1108/02686909510079620, Publisher: MCB UP Ltd URL: http://www= .emeraldinsight.com/10.1108/02686909510079620

Rushinek, A. and Rushinek, S. "Oil and Gas Mandat= ed Accounting Changes and Debt Covenants: Debt to Equity Maturity, Dividend/Retained Earning Reduction & Refinancing Cost Ratios", OIL & GAS TAX QUARTERLY, Vol. 40, No.2, 1991, 316-329.

Rushinek, A. and Rushinek, S. "Net Income-to-Sales Ratio Grouping For the Crude Petroleum and Natural Gas Industry Sector: A Company to Peer Comparative Variance Analysis", OIL AND GAS TAX QUARTE= RLY, June, 1995, Volume 43, No.4, 713-728.

Rushinek, A. and Rushinek, S. "Damage Cost Calcul= ation Model for Exxon Corporation and the Oil and Gas Industry: A Simulated Fraud Decomposition of Expert System Software Controls", OIL AND GAS TAX QUARTERLY, Vol. 44, No. 3, March 1996, 337-350.

Rushinek, A. and Rushinek, S. "Tax Fraud Forecast= ing For the Petroleum Refining Industry: Financial Ratios & Reversed Accoun= ting Theory Applied to Shell Oil", OIL AND GAS TAX QUARTERLY, March, 1997.<= /p>

Rushinek, A. and Rushinek, S.”Rating and Ranking= Best Practices of the British Petroleum Oil Company and the Oil & Gas Indust= ry: Sales to Cash Forecasting Univariate Regression Trend Analysis and Computer Modeling”, OIL AND ENERGY QUARTERLY, December, 1997.

Rushinek, A. and Rushinek, S.”Litigation in Penn= zoil and the Petroleum Refining Industry: A Financial Ratio Automated Peer Review Analysis of Variance Internet Software Development” OIL, GAS & ENERGY QUARTERLY, V= ol.47, No.1, September, 1998, 17-32.

Rushinek, A. and Rushinek, S.”Correlating Investors’ Preferences to Stock Characteristics: An Algorithm for Internet Software Decision Support System Development in the Crude Oil & Refining Industry” OIL,= GAS & ENERGY QUARTERLY, Vol. 48, No.1, September, 1999, 87-101.

Rushinek, A. and Rushinek, S. ”Oil & Gas Mar= ket, Sector & Company Relative Strength Congruity Trading Theory (MSCRSSCTT)= : An Internet Automation Approach Applied to Chevron Corporation’s Stocks” OIL, GAS & = ENERGY QUARTERLY, Vol. 48, No.4, June, 2000, 671-682.

Rushinek, A. and Rushinek, S. "Forensic Audits of= Stock Market Forecasts For Texaco & The International Oil and Gas Industry &a= mp; Financial Models for Online Broker Litigation", OIL, GAS, & ENERGY QUARTERLY, Vol. 51, No. 4, June, 2003, 659-678.

Rushinek, A. and Rushinek, S. “Automated Internet Trading Forecast Variance Analysis: An Oil and Gas Industry and BP Corporat= ion Case Study”, OIL, GAS, & ENERGY QUARTERLY, Volume 52 Number 1 September 2003, 35-54.

Rushinek, A. and Rushinek S. “Internet Web Server Comparative Forecasting Sales Models: Reversed Accounting of Texaco Corp and The Oil & Gas Industry linear, Exponential, Power, Polynomial & Logarithmic Univariate Regressions”, OIL, GAS, & ENERGY QUARTERLY, Volume 54, No. 2, November 2005, 87-95

Rushinek, A. and Rushinek S. “An Automated Busin= ess Intelligent Stock Market Matching Engine For the Oil and Gas Industry: Materiality of Violating the Normality Assumption of Linear Regression Cont= rol Analysis”, OIL, GAS, & ENERGY QUARTERLY, Volume 56, No. 2, Novemb= er 2007, 435-448.

Rushinek, A. and Rushinek S. “Optimal Forecasting Models For The Oil & Gas Industry:&nbs= p; A Study Of The Daily Dow Jones U.S. Oil & Gas Index And ConocoPhillips With The Aid Of The Virtual Internet Office”, OIL, GAS, & ENERGY QUARTERLY, Volume 57, No. 1, June, 2008.

Michael Werner and Kumen Jones “Introduction = to Management Accounting – A User Perspective”, Second Edition, Prentice = Hall, M-135, 2003.

Appendix A Imported data

iPath S&P GSCI Crude Oil Tot Ret Idx ETN (OIL)	http://finance.yahoo.com/q/hp?s=3DOIL
Date	Open	High	Low	Close	Volume	Adj. Close
Tuesday, July 08, 2008	82.78	82.78	80.96	81.36	1228800	81.36
Monday, July 07, 2008	84.84	85.91	83.6	84.91	898800	84.91
Thursday, July 03, 2008	86.52	86.76	85.78	86.56	1095800	86.56
Wednesday, July 02, 2008	84.31	86.3	84.08	86.26	1121600	86.26
Tuesday, July 01, 2008	85.72	85.78	83.93	84.59	860800	84.59

Appendix B Copy and Paste Data

http://finance.yahoo.com/q/hp?s=3DOIL

iPath S&P GSCI Crude Oil Tot Ret Idx ETN (OIL)

PRICES

Date

Open

High

Low

Volume

Adj. Close*

Wednesday, July 09, 2008

82.02

82.66

81.01

81.18

1,005,600

81.18

Tuesday, July 08, 2008

82.78

80.96

81.36

1,228,800

81.36

Monday, July 07, 2008

84.84

85.91

83.6

84.91

898,800

84.91

Thursday, July 03, 2008

86.52

86.76

85.78

86.56

1,095,800

86.56

Wednesday, July 02, 2008

84.31

86.3

84.08

86.26

1,121,600

86.26

Tuesday, July 01, 2008

85.72

85.78

83.93

84.59

860,800

84.59

Monday, June 30, 2008

85.58

83.35

84.16

837,200

84.16