pls i need urgent help with this presentation i have today i already did it but looks like it i need to add something which i need help with before the next 4 hours.

Guidelines and Examples The team project is a chance for you to develop a research question on your own. Imagine you are a business analytics consultant. A business hires you because they are struggling and hope to use analysis of their data to improve the functioning of the business. Alternatively, you could be working for a nonprofit or government agency to improve their effectiveness. Your research question will utilize regression analysis which looks at the relationship between variables. In regression analysis you look at whether the variation in one variable correlates with variation in one or more other variables. Ultimately you are trying to figure out whether a change in one variable will lead to a predictable change in another. Regression analysis measures how much of an impact independent variables have on the dependent variable. Here are some examples of the types of questions you could ask: Example 1: The examples in chapter 9 examine the effect of the size of houses on their sale price. They are trying to determine whether a bigger house means a higher sales price. They find that one additional square foot of house size is associated with an increase in sale price of $35. This type of analysis would be helpful for both realtors and homeowners. Example 2: Another example you could look at would be the income of your customers. You're trying to figure out whether there is relationship between income and purchases. As consumers have more income, do they buy more or less of your product? Your findings could be useful in deciding which customers to target with your advertising. Example 3: Do interest rates influence growth? You could look at interest rates and economic growth rates for the past 40 years (or different countries) to see if the move in a consistent way. Are lower interest rates correlated with economic growth? Research Question For this project you have to find a data set that is publicly available or that you have access to (for economic data http://research.stlouisfed.org/fred2/ is a good one, www.gapminder.org for socioeconomic). In order to work for regression observation the data has to have a decent number of observations (at least 40 or so) with the relevant variables. For example #1 we have a whole list of individual house sales, each one has information on price and house characteristics. For example #3 we would look at each quarter of the year as an individual observation, so Q1 1995 we would have information on both growth rates and interest rates and we would have 4 quarters for each year from 1960-present. When finding a data set, think about what types of information could be potentially useful to a business. Useful could mean enabling them to better target their customers, identify which products to push, how to lower production costs, etc. Think about what actions could be taken based depending on the results of the analysis. Also, think about an area that interests you. This is your chance to explore a topic of your choosing. (Your question cannot be the same as one of the examples done in the book.) Project write-up: Your project write-up is due on Wednesday of the week 8. The project write-up does not have to be long - you may be able to do it in just a few pages. I will give you an example to look at. The quality of the write-up itself is more important than the actual findings. You may find that there is no statistical significance to the factor you assessed, which is an important finding itself. Your write-up has to include the following elements. 1. Rationale and research question: What question you are trying to answer and why it is important to the business. 2. Descriptive information: Explain to us the variables to be analyzed as well as any important characteristics of data. 3. Limitations: Discuss the assumptions of the procedures, uncertainties involved, or other possible trouble spots of this type of analysis. These have to do with the data set and the relationship between the variables. This you should do before you conduct any actual regressions. 4. Analysis: Lay out the procedure you will be using. Conduct the analysis and give the results of the analysis including, R squared, statistical significance, and the regression coefficients. What do these results mean? Decide the best way to display your results. There should be some visual element which could be data tables, graphs, etc. (utilizing the design principles we talked about). Show us the important results, not just everything excel spits out. 5. Results and conclusion: Given the results of your analysis, what can you conclude? In this section you take into account all of the other parts of the paper and focus on what actions would you suggest based on your analysis. Appendix (optional) includes other data results and tables here. Do not include your data set. Project presentation: Along with your write-up you should submit a narrated presentation (you can use PowerPoint, Prezi, or any other appropriate software). The presentation should be no longer than 7 minutes (it can be shorter). The content will be the same as the write-up, but you should be selective and decide what the most important aspects of your research are. You should use some type of visuals and utilize the principles of good design we talked about. For the presentation imagine helping the audience of your classmates to understand your analysis in a quick timeframe. PLEASE ASK IF YOU HAVE ANY QUESTIONS! Mariama Jammeh Professor Robert Kao MBA 474 Quantitative Analysis October, 6th 2016 Research Paper Introduction: This research paper will try to predict the total auto sales in the US for the month of August 2013. The data used for this project spans over the previous 34 months (July 2013 to October 2010). The dependent variable auto sales, is determined by independent variables unemployment, price of oil, the consumer price index and the price of gold. The most important independent variable in this relationship is unemployment because if people are out of work their purchasing power is greatly diminished and the money they have will be diverted to buying things that are essential to their livelihoods. Dependent Variable Definition: Auto Sales The dependent variable is the number of auto sales per month. Auto sales are defined as \"the number of domestically produced units of cars, SUVs, mini-vans and light trucks that are sold\" (Investopedia). The Bureau of Labor Statistics (BLS) provides both seasonally unadjusted and adjusted sales numbers. The numbers used in this paper are seasonally adjusted where applicable. Independent Variables Definition: Unemployment The primary independent variable is the unemployment number in the US. We get this number by taking \"the number of unemployed persons divided by the number of people in the labor force\" (Investopedia). Unemployment is defined by the BLS as people who \"do not have a job, have actively looked for work in the prior 4 weeks, and are currently available for work. Persons who were not working and were waiting to be recalled to a job from which they had been temporarily laid off are also included as unemployed\" (Bureau of Labor Statistics). The unemployment rate determines auto sales because as the number of unemployed increases we should see a decrease in the number of autos sold and vice versa. Price of Oil The second independent variable is the price of crude oil in dollars per barrel. Crude oil prices \"measure the spot price of various barrels of oil, most commonly either the West Texas Intermediate or the Brent Blend\" (Amadeo). Cars run on gas and gas comes from refining crude oil, so the shift in crude oil prices will have an impact on the sale of automobiles. Consumer Price Index (CPI) The third independent variable is the Consumer Price Index (CPI). The consumer price index is defined by the BLS as \"a measure of the average change over time in the prices paid by urban consumers for a market basket of consumer goods and services\" (Bureau of Labor Statistics). Since the CPI measures the change in the price families pay for their living expenses, the fluctuations in the index should correlate with fluctuations in car sales. Price of Gold The final independent variable is the price of gold in dollars per ounce. The price of gold is defined as \"the price at which gold is being traded on the gold market\" (Cambridge Business English Dictionary). The price of gold is used as one of the indicators of how healthy an economy is. When the price of gold is high that means the economy is not doing well because investors go for gold only when they are trying to protect their investments. Low prices indicate an economy that is doing well and investors feel good about investing in other assets. So, high gold prices should correlate with low auto sales and low prices with high auto sales. The data used in this paper was collected from the YCharts, Bureau of Labor Statistics (BLS), Kitco and the U.S. Energy Information Administration (EIA) web sites. More specifically, for the car sales data I used information available on YCharts.com, and BLS.gov was used for the unemployment numbers and the Consumer Price Index. Gold price data was taken from Kitco.com and crude oil prices from EIA.gov. Data Outliers - There are a few data points that are outside the normal data distribution. I am going to explain those here. There was a sharp drop in car sales in May and June 2011. Sales went from 12.91 million in April to 11.87 and 11.68 million for May and June, respectively. This was due to the March tsunami in Japan that caused supply shortages, which led the manufacturers to cut down on marketing and incentives to conserve supplies. With low incentives on many of the vehicles, a lot of shoppers stayed away from the dealerships. Unemployment was at its highest at 9.8 percent in November 2010. We were still in the midst of the recession, but in November specifically, the retail industry lost 28,000 jobs, factories cut 13,000 jobs and the construction sector lost 5,000 positions (CNNMoney). The price of oil was at its highest in April 2011 at 110.04, and it shot up again in March 2012 to 106.21. The cause for the rise in April was due to the uncertainties in the Arab world at this time. The protests were going on in Egypt and Tunisia and the civil war raged in Libya. Investors were worried that this would interrupt oil supplies. The rise in March was caused by the high tensions between the US and Iran. People feared that a war might erupt between the two, which would have caused a sharp drop in global oil supplies, since Iran is one of the major oil producers in the world. The Consumer Price Index rose from 0 percent in January 2013 to 0.7 percent in February. This was caused by a rise in all the indices that are part of the Consumer Price Index, especially gasoline and food. Scatter Plot Analysis - Auto Sales Compared to Unemployment 16 15 f(x) = - 1.78x + 28.82 R = 0.89 14 Auto Sales (in millions) 13 12 11 10 6 6.5 7 7.5 8 8.5 9 9.5 10 Unemployment The comparison of Auto Sales to Unemployment shows a negative slope of the regression line, and a strong positive correlation with an R value of 0.9445. With an R value of 0.892 or 89.2% we can say that 89.2 percent of the variation in the number of Auto Sales is explained, or accounted for, by the variation in Unemployment. The value of t is 15.21 (Reject). Thus we can conclude that there is a correlation. Auto Sales Compared to Price of Oil 16 15 14 Auto Sales (in millions) f(x) = 0.01x + 13.1 R = 0 13 12 11 10 80 85 90 95 100 105 110 115 Price of Oil ($ per barrel) The comparison of Auto Sales to the Price of Oil shows a positive slope of the regression line, and a weak positive correlation with an R value of 0.0316. With an R value of 0.001 or 0.1% we can say that 0.1 percent of the variation in the number of Auto Sales is explained, or accounted for, by the variation in the Price of Oil. The value of t is 0.167 (Accept). Thus we can conclude that the correlation may be a chance based on the sample. Auto Sales Compared to Consumer Price Index 16 15 14= - 1.48x + 13.92 f(x) R = 0.09 13 Auto Sales (in millions) 12 11 10 -0.4 -0.2 0 0.2 0.4 0.6 0.8 Consumer Price Index The comparison of Auto Sales to the Consumer Price Index shows a negative slope of the regression line, and a weak positive correlation with an R value of 0.2950. With an R value of 0.087 or 8.7%, we can say that 8.7% of the variation in the number of Auto Sales is explained, or accounted for, by the variation in the Consumer Price Index. The value of t is 1.634 (Accept). Thus we can conclude that the correlation may be a chance based on the sample. Auto Sales Compared to Price of Gold 16 15 f(x) = 0x + 5.78 R = 0.34 14 Auto Sales (in millions) 13 12 11 10 1000 1200 1400 1600 1800 2000 Price of Gold ($ per ounce) The comparison of the Auto Sales to the Price of Gold shows a positive slope of the regression line, and a moderate to strong positive correlation with an R value of 0.5848. With an R value of 0.342 or 34.2%, we can say that 34.2 percent of the variation in the number of Auto Sales is explained, or accounted for, by the variation in the Price of Gold. The value of t is 3.815 (Reject). Thus we can conclude that there is a correlation. Apr-13 Regression output variables coefficients Intercept Unemployment Price of Oil ($ per barrel) 31.9448 -1.8757 -0.0179 Consumer Price Index -0.0274 Price of Gold ($ per ounce) -0.00041547 a b x 31.944 8 -1.8757 -0.0179 7.5 92.07 -0.0274 -0.4 1485.0 8 -0.00041547 Sum 31.944 8 -14.067 -1.6437 0.0109 6 -0.617 15.627 7 The estimated number of Auto Sales for April 2013 is 15.6277 or 15.63, and the actual number was 15.14, so the number of sales was below the estimation. May-13 Regression output variables coefficients Intercept Unemployment Price of Oil ($ per barrel) Consumer Price Index Price of Gold ($ per ounce) 31.9448 -1.8757 -0.0179 -0.0274 -0.00041547 a b x Sum 7.6 94.8 0.1 1413.5 31.9448 -14.255 -1.6924 -0.0027 -0.5873 15.4074 31.944 8 -1.8757 -0.0179 -0.0274 -0.00041547 The estimated number of Auto Sales for May 2013 is 15.4074 or 15.41, and the actual number was 15.41, so the number of sales was equal to the estimation. Jun-13 Regression output variables coefficients Intercept Unemployment Price of Oil ($ per barrel) Consumer Price Index Price of Gold ($ per ounce) 31.9448 -1.8757 -0.0179 -0.0274 -0.00041547 a b x -1.8757 -0.0179 -0.0274 -0.00041547 7.6 95.8 0.5 1342.36 31.944 8 Sum 31.944 8 -14.255 -1.7103 -0.0137 -0.5577 15.408 2 The estimated number of Auto Sales for June 2013 is 15.4082 or 15.41, and the actual number was 15.81, so the number of sales was above the estimation. Jul-13 Regression output variables Intercept Unemployment Price of Oil ($ per barrel) Consumer Price Index Price of Gold ($ per ounce) coefficients 31.9448 -1.8757 -0.0179 -0.0274 -0.00041547 a b x 31.944 8 7.4 -1.8757 104.7 -0.0179 0.2 -0.0274 -0.00041547 1286.72 Sum 31.9448 -13.88 -1.8692 -0.0055 -0.5346 15.655 7 The estimated number of Auto Sales for July 2013 is 15.6557 or 15.66, and the actual number was 15.73, so the number of sales was above the estimation. Auto Sales Dataset Primary Independent Test Data Dependent Months Auto Sales (in millions) Unemployment Independent Independent Independent Price of Oil ($ per barrel) Consumer Price Index Price of Gold ($ per ounce) 1 Jul-13 15.73 7.4 104.7 0.2 1286.72 2 Jun-13 15.81 7.6 95.8 0.5 1342.36 3 May-13 15.41 7.6 94.8 0.1 1413.5 4 Apr-13 15.14 7.5 92.07 -0.4 1485.08 Research Data Months Primary Independent Dependent Auto Sales (in millions) Unemployment Independent Independent Independent Price of Oil ($ per barrel) Consumer Price Index Price of Gold ($ per ounce) 1 March-13 15.25 7.6 92.96 -0.2 1592.86 2 February-13 15.29 7.7 95.32 0.7 1627.59 3 January-13 15.17 7.9 94.83 0 1670.95 4 December-12 15.17 7.8 88.25 0 1688.53 5 November-12 15.25 7.8 86.73 -0.2 1721.14 6 October-12 14.33 7.9 89.57 0.2 1747.01 7 September-12 14.71 7.8 94.56 0.5 1744.45 8 August-12 14.42 8.1 94.16 0.5 1626.03 9 July-12 14.16 8.2 87.93 0 1593.91 10 June-12 14.32 8.2 82.41 0.1 1596.7 11 May-12 14.11 8.2 94.72 -0.1 1585.5 12 April-12 14.3 8.1 103.35 0 1650.07 13 March-12 14.17 8.2 106.21 0.3 1673.77 14 February-12 14.43 8.3 102.26 0.3 1742.62 15 January-12 13.9 8.3 100.32 0.2 1656.12 16 December-11 13.46 8.5 98.58 0 1652.31 17 November-11 13.36 8.6 97.16 0.1 1738.98 18 October-11 13.28 8.9 86.43 0 1665.21 19 September-11 13.01 9 85.61 0.3 1771.88 20 August-11 12.4 9 86.34 0.3 1755.81 21 July-11 12.4 9 97.34 0.2 1572.81 22 June-11 11.68 9.1 96.29 0.1 1528.66 23 May-11 11.87 9 101.36 0.4 1510.44 24 April-11 12.91 9 110.04 0.3 1473.81 25 March-11 12.75 8.9 102.98 0.5 1424.01 26 February-11 12.82 9 89.74 0.4 1372.72 27 January-11 12.51 9.1 89.58 0.3 1356.4 28 December-10 12.51 9.3 89.23 0.5 1390.55 29 November-10 12.19 9.8 84.32 0.2 1369.89 30 October-10 12.2 9.5 81.95 0.3 1342.02 Works Cited Amadeo, Kimberly. "Crude Oil Prices Definition." About.com US Economy. N.p., n.d. Web. 08 Sept. 2013. . "Bureau of Labor Statistics Data." Databases, Tables & Calculators by Subject. N.p., n.d. Web. 8 Sept. 2013. . "Bureau of Labor Statistics Data." Databases, Tables & Calculators by Subject. N.p., n.d. Web. 8 Sept. 2013. . "Consumer Price Index (CPI)." U.S. Bureau of Labor Statistics. N.p., n.d. Web. 8 Sept. 2013. . "Cushing, OK Crude Oil Future Contract 1 (Dollars per Barrel)." U.S. Energy Information Administration (EIA). N.p., n.d. Web. 8 Sept. 2013. . "Gold Price - definition in the Business English Dictionary - Cambridge Dictionaries Online (US)." Cambridge Free English Dictionary and Thesaurus (US). N.p., n.d. Web. 8 Sept. 2013. . "Historical Gold Charts and Data - London Fix." Gold, Silver, Gold Price, Silver Price, Gold Rate, Gold News | Kitco. N.p., n.d. Web. 8 Sept. 2013. . "Labor Force Characteristics (CPS)." U.S. Bureau of Labor Statistics. N.p., n.d. Web. 8 Sept. 2013. . "Motor Vehicle Sales Definition | Investopedia." Investopedia - Educating the world about finance. N.p., n.d. Web. 8 Sept. 2013. . "November Jobs Report: Unemployment Rate up." CNNMoney. Cable News Network, 03 Dec. 2010. Web. 8 Sept. 2013. . "Unemployment Definition | Investopedia." Investopedia - Educating the world about finance. N.p., n.d. Web. 8 Sept. 2013. . "US Auto Sales (Monthly)." YCharts - Stock Charts, Stock Ratings & Economic Indicators. N.p., n.d. Web. 8 Sept. 2013. . EC 315 Quantitative Research Methods Final Project MARIAMA JAMMEH 10-6-2016 Variables Used Auto Sales - the number of domestically produced units of cars, SUVs, mini-vans and light trucks that are sold Unemployment Rate - represents the number of unemployed as a percent of the labor force Price of Crude Oil - the cost of crude oil in dollars per barrel traded on the open market Consumer Price Index (CPI) - a measure of the average change over time in the prices paid by urban consumers for a market basket of consumer goods and services Price of Gold - the cost of gold in dollars per ounce traded on the open market Collection of Data YCharts.com Car Sales Data BLS.gov Unemployment Numbers and the Consumer Price Index Kitco.com Gold Prices EIA.gov Crude Oil Prices Auto Sales and Unemployment Reject H0 if |t| > 2.048 @95% The comparison of Auto Sales to Unemployment shows a negative slope of the regression line, and a strong positive correlation with an R value of 0.9445. With an R value of 0.892 or 89.2% we can say that 89.2 percent of the variation in the number of Auto Sales is explained, or accounted for, by the variation in Unemployment. The value of t is 15.21 (Reject). Thus we can conclude that there is a correlation. Auto Sales and Price of Oil Reject H0 if |t| > 2.048 @95% The comparison of Auto Sales to the Price of Oil shows a positive slope of the regression line, and a weak positive correlation with an R value of 0.0316. With an R value of 0.001 or 0.1% we can say that 0.1 percent of the variation in the number of Auto Sales is explained, or accounted for, by the variation in the Price of Oil. The value of t is 0.167 (Accept). The correlation may be a chance based on the sample. Auto Sales and CPI Reject H0 if |t| > 2.048 @95% The comparison of Auto Sales to the Consumer Price Index shows a negative slope of the regression line, and a weak positive correlation with an R value of 0.2950. With an R value of 0.087 or 8.7%, we can say that 8.7% of the variation in the number of Auto Sales is explained, or accounted for, by the variation in the Consumer Price Index. The value of t is 1.634 (Accept). The correlation may be a chance based on the sample. Auto Sales and Price of Gold Reject H0 if |t| > 2.048 @95% The comparison of the Auto Sales to the Price of Gold shows a positive slope of the regression line, and a moderate to strong positive correlation with an R value of 0.5848. With an R value of 0.342 or 34.2%, we can say that 34.2 percent of the variation in the number of Auto Sales is explained, or accounted for, by the variation in the Price of Gold. The value of t is 3.815 (Reject). Thus we can conclude that there is a correlation. Durbin-Watson Durbin-Watson (cont.) The Durbin-Watson value is 1.37, which means that the test is \"Not Conclusive (Don't Know)\". Therefore, I don't know if autocorrelation exists and whether the regression statistics are biased and unreliable. I also don't know, whether regression can be used to determine the relationship between the variables. Estimation Statement Formula for the Estimation Statement Using the regression analysis produced the following Estimation Statement: = 31.9448 + (-1.8757)X + (-0.0179)X + (-0.0274)X + (-0.00041547)X The X values consist of actual values for Unemployment, Price of Oil, Consumer Price Index, and the Price of Gold for the months of April, May, June and July 2013. Regression Analysis The estimated number of Auto Sales for April 2013 is 15.6277 or 15.63, and the actual number was 15.14, so the number of sales was below the estimation. Regression Analysis (cont.) The estimated number of Auto Sales for May 2013 is 15.4074 or 15.41, and the actual number was 15.41, so the number of sales was equal to the estimation. Regression Analysis (cont.) The estimated number of Auto Sales for June 2013 is 15.4082 or 15.41, and the actual number was 15.81, so the number of sales was above the estimation. Regression Analysis (cont.) The estimated number of Auto Sales for July 2013 is 15.6557 or 15.66, and the actual number was 15.73, so the number of sales was above the estimation. Data Outliers Car Sales - - April 2011 - 12.91 million - May 2011 - 11.87 million - June 2011 - 11.68 million Cause - March earthquake and tsunami in Japan that caused supply shortages, which led the manufacturers to cut down on marketing and incentives to conserve supplies. With low incentives, a lot of shoppers stayed away from the dealerships. Unemployment - - October 2010 - 9.5 percent - November 2010 - 9.8 percent Cause - We were still in the midst of the recession. But in November specifically, the retail industry lost 28,000 jobs, factories cut 13,000 jobs and the construction sector lost 5,000 positions. Data Outliers (cont.) Price of Oil - - March 2011 - 102.98 - April 2011 - 110.04 - February 2012 - 102.26 - March 2012 - 106.21 Cause - In April we had the uncertainties in the Arab world. The protests were going on in Egypt and Tunisia and the civil war raged in Libya. The earthquake and tsunami in Japan were a part of this, as well as a weaker U.S. dollar at this time. Cause for the rise in March was due to growing tensions between the West and Iran, and the possibility that the conflict might escalate and cause a sudden curtailment of supply. Consumer Price Index - - January 2013 - 0 percent - February 2013 - 0.7 percent Cause - There was a sharp rise in all the indices that are part of the Consumer Price Index, especially gasoline and food