Why_Do_People_Sue_

Week 5 Final Project Data Set Assignment Darlene Solano BUS 308: Statistics for Managers Instructor Esmaail Nikjeh June 12, 2011 Week 5 Final Project Data Set Assignment There have been several studies to show that oil price fluctuations have a direct effect on the performance of businesses worldwide. According to those studies, increase in oil prices encourages consumers to stay home more, shop less, and shop online more. This results to lesser vehicles on the road and less traffic. It also, presents an opportunity for a delivery service business. Oil price increase not only expands the business through the expansion in delivery opportunities brought by online shoppers, but also reduces expenses due to potential reduction of travel time. These benefits warrant the need for oil price forecasting. Linear regression of the oil prices from 1982 to 2011 was conducted to come up with a regression model that could be used to predict oil price fluctuations. Though some studies question the accuracy of this method, it helps chart the potential behavior of the oil prices in the coming years. This could help the delivery service business come up with strategies that would alleviate the effects of oil price changes. This paper will focus on the delivery service business and the statistical analysis on oil and gasoline prices that was conducted, as well as the results of the analysis. Explanations on how the results were gained and the figures the analysis came to show. This writer’s personal thoughts and conclusions will be added at the end in answer to the following questions: What effects will the gas price predictions have on the delivery service business' Are the predicted gas prices accurate' What could occur in the future that would change your linear regression line and therefore your prediction' Studies have shown that oil price fluctuations have direct effect on the performance of businesses worldwide. “Massive oil price swings could bring instability, economic crash, and unemployment” (Moshiri & Foroutan, 2006, p. 82). According to Yu, Ailawadi, Gauri, and Grewal “gas budgets go up with the oil price hikes resulting to the decrease in disposable income” (2011, p. 18). For example, from 2003 to 2008, an average income family’s gasoline expenditure increased from 4.6% to 11.5% of their income. As a result, people tend to stay home and eat at home rather than in restaurants and reduce number of shopping trips. These results were confirmed by a study conducted by Burger and Kaffine (2009) on the effect of gasoline prices on highway congestion and freeway speeds. The authors found that based on data collected in 12 major routes in Los Angeles from 2001 to 2006, people tend to drive less when gasoline prices increase. Thomaselli (2011) on the other hand noted the increase in online shopping as a consequence of gasoline price increase. He claims that according to data, volume of online shoppers increase with the rise of gasoline prices. As a delivery service company, conducting an oil forecast is crucial in helping our business prepare for its effects. Unlike other businesses, the delivery service business is in a unique position to reap potential benefits from the oil increase. Based on previous studies, increase in oil prices pump up the demand for delivery service as more people will turn to online shopping. Furthermore, the decongestion of freeways due to decrease in number of travelers could also benefit our service by reducing travel time. Thus, knowledge of oil price behavior could help the company come up with strategies to deal with demand changes brought by oil price fluctuations. Average monthly oil price data from 1982 to 2011 was obtained from Consumer Price Index of the Bureau of Labor Statistics of the United States Department of Labor. Annual averages were computed from the monthly data. The results are presented in Table 1. To test the relationship between year and average oil price, a scatter plot was conducted using Excel (Figure 1). Based on the figure, an oil price tends to increase annually. The equation of the regression line was obtained by computing the slope, m and y-intercept, b from the scatter plot figure. Regression analysis using Excel obtained the same result for m and b. The equation of the regression line was found to be: Y = 0.0647 X – 127.61, or Oil Price = 0.647 * year – 127.61 Based on this equation, future increases in oil price can be calculated by substituting the year, X. The predicted prices based on the equation were obtained by substituting the value of X in the formula. Residuals or the deviations of the observed or actual prices from the predicted prices were calculated. Results are shown in Table 2. The residual plot is a horizontal line which shows that there were no outliers. Thus, the regression model was a good fit. To investigate whether the price of gas in Clinton County, New York within the range of the linear regression line model or not, the actual price of $3.99 a gallon was included in the scatter plot of the results. Based on Figure 3, the price $3.99 lies far from the regression line, it changed the slope and y-intercept of the regression model. Based on this, $3.99 is an outlier. The residual plot confirms this observation. Adding the said value tilted the residual plot away from the horizontal line. To test whether this value lies within the 95% confidence interval, upper and lower limits of the interval were calculated. The formula used for the computation is: [pic]*[pic] where [pic]= t value at 95% and [pic]is the standard error of y (obtained from the regression result) and n = number of observations. To get the upper limit of the confidence interval, [pic]was added to the predicted value and to get the lower limit, [pic] was subtracted from the predicted value. Results obtained are shown in Appendix A. A plot of the predicted value and the two limits is shown in Figure 5. Based on the Figure, the price of $3.99 is not within the range of the 95% confidence interval. From the calculations presented, gas prices will continue to increase in the coming years. Despite the reports of fluctuations “massive fluctuations from $2.00 to $4.00” (Yu, et al., 2011, p. 19), the annual average price of gasoline can be represented by a good fitting model. Oil price fluctuations are evident in the scatter plot of the prices. The results suggest that despite the fluctuations, oil prices tend to increase annually. This presents an opportunity for the delivery business. As the oil price continues to increase, more and more people, and businesses might rely on online shopping; which in turn will raise the need and demand for the delivery business. Furthermore, the inclusion of wider range of samples from 1982 to 2011 provides a comprehensive view of the oil industry which adds to the reliability of the result. According to Moshiri and Foroutan (2006), the “movements in oil prices are very complex and, therefore, seem to be unpredictable” (p. 81). Although the regression model obtained from 1982 to the first two months of 2011 seem accurate and present a best fit for the given period, this does not guarantee that future oil prices would fall within the said model. As Moshiri and Foroutan (2006) noted, linear modeling is not the best and most accurate way of forecasting oil prices. A massive fluctuation in oil price in the future could change the model obtained in this study. The result obtained in the analysis of the $3.99 gas price confirms this observation. Inclusion of the single data dramatically changed the behavior of the model. Furthermore, Figure 5 also shows that most of the observations included in the calculation do not fall within the 95% confidence interval which reflects the variability of the result. However, the goal of forecasting for the delivery business is not to accurately predict the amount of gas increase, rather just knowing the potential behavior of the gas price in the coming years would be enough to help the company come up with strategies that would take advantage of such behavior and thereby increase their net profits. The delivery service would be able to know where and when to expand their services and when to maintain or reduce operations based on the direction of gas price fluctuations. Reference Bureau of Labor Statistics (2011). Consumer price index Retrieved June 10, 2011, from http://www.bls.gov/cpi/ Burger, N., & Kaffine, D. (2009). Gas prices, traffic, and freeway speeds in Los Angeles. The Review of economics and statistics, 91(3) pp. 652-657. Moshiri, S., & Foroutan, F. (2006). Forecasting nonlinear crude oil futures prices. Energy journal. 27(4) pp. 81-95. Thomaselli, R. (2011). As gas prices climb, marketers gird for tumult at the tank. Advertising age. 82(11) p. 1. Yu, M., Ailawadi, K., Gauri, D., & Grewal, D. (2011). An Empirical investigation of the impact of gasoline prices on grocery shopping behavior. Journal of marketing. 75, p. 35.