Data Analysis for Managers - Report Example

Data analysis for managers Data analysis is part of a wider scoped statistical research that plays an important role in managerial decision-making processes. It forms a basis for understanding property of data and trend in time series data for forecasting. This paper explores the scope and applicability of data analysis for managerial application within Tsuneishi Holdings Corporation. Introduction This paper seeks to determine and report on existence of a significant relationship between demand for the corporation’s tanker order vessels, tanker fleet vessels and tanker demolition vessels, and a number of identified independent variables. The independent variables are Brent crude oil price, global oil productivity, and percentage industrial production by identified countries, growth rate in industrial production by regions, and the Libor interest rates. Hypothesis Based on a time series set of data for the random variables, the analysis seeks to test the general null hypothesis that there is no significant relationship between demand for each of the tanker vessels and the independent variables as expressed bellow. βi= 0, for all the independent variables in relation to each of the tanker vessel types. This means that there is no significant relationship. The general expression for the alternative hypotheses is expressed bellow. βi≠0. βi are the coefficients of the independent variable in a given expression for a vessel. This indicates existence of significant relationship between the dependent variable and at least one of the independent variables. Analytical techniques The report applies inferential statistics to explore the data. It explores correlation and regression analysis to test the sets of hypotheses for each of the vessel type. Identification of a significant relationship is identified in a model of best fit leads to further analysis to determine the independent variables that significantly affect demand (Mann, 2010). Data analysis Correlation The following table offers an excel output for correlation coefficients 1 0.14411 1 -0.0161 0.17854 1 0.38705 0.81949 0.0389 1 0.47017 0.83054 0.081 0.8487 1 0.45704 0.29976 0.2402 0.4764 0.4721 1 0.31835 0.29916 0.2004 0.3499 0.3313 0.5742 1 0.22494 -0.4787 -0.152 -0.164 -0.2006 0.2136 0.3343 1 0.25123 -0.462 -0.101 -0.137 -0.2104 0.1908 0.307 0.935 1 0.25905 -0.0644 0.2195 0.1661 0.0701 0.5993 0.662 0.7227 0.738 1 0.02837 -0.4921 -0.479 -0.282 -0.4351 -0.2747 -0.042 0.5313 0.513 0.08875 1 The coefficients correspond to the variables in their corresponding order: tanker order vessels, tanker fleet vessels, tanker demolition vessels, Brent crude oil price, global oil productivity, and percentage industrial production by identified countries, growth rate in industrial production by regions, and the Libor interest rates Regression analysis In order to complete a regression analysis for the entire set of data, missing values were fixed through estimation from neighboring data sets. The following is a summary of regression analysis output for the relationship between the demand for tanker orders vehicles and the other factors. Test was done at 0.05 % level of significance. SUMMARY OUTPUT Regression Statistics Multiple R 0.717313 R Square 0.514538 Adjusted R Square 0.484937 Standard Error 18.39523 Observations 175 ANOVA   df SS MS F Significance F Regression 10 58818.9 5881.89 17.38226 2.87E-21 Residual 164 55495.08 338.3846 Total 174 114314         Coefficients Standard Error t Stat P-value Intercept -282.493 50.51021 -5.59279 9.17E-08 X Variable 1 -0.03089 0.005886 -5.24718 4.72E-07 X Variable 2 0.341644 0.286063 1.194297 0.234086 X Variable 3 0.122769 0.125334 0.979533 0.328759 X Variable 4 5.025838 0.780561 6.43875 1.28E-09 X Variable 5 1.351591 0.516873 2.614939 0.009756 X Variable 6 1.205266 0.569503 2.116348 0.035825 X Variable 7 -2.73541 1.103409 -2.47905 0.014185 X Variable 8 0.026582 0.009517 2.793206 0.00584 X Variable 9 -0.00695 0.005734 -1.2117 0.22737 X Variable 10 3.024191 1.211288 2.496673 0.013524 The following is the significant regression model Y= -282.493-0.03089x1+5.025838x4+1.351591x5+1.205266x6-2.73541x7+0.026582x8+3.024191x10 The following tables summarize the regression analysis results for demand for tanker fleet vessels and the other factors with demand for tanker order vessels and demand for tanker demolition vessels as the first and second independent variables respectively followed by the other variables in their original consecutive order. SUMMARY OUTPUT Regression Statistics Multiple R 0.943315 R Square 0.889844 Adjusted R Square 0.883127 Standard Error 225.802 Observations 175 ANOVA   df SS MS F Significance F Regression 10 67546607 6754661 132.4792 3.73E-73 Residual 164 8361796 50986.56 Total 174 75908403       Regression model   Coefficients Standard Error t Stat P-value Intercept -2719.99 642.3588 -4.23438 3.81E-05 X Variable 1 -4.654 0.886954 -5.24718 4.72E-07 X Variable 2 2.966333 3.519048 0.842936 0.400492 X Variable 3 7.3959 1.430814 5.169017 6.77E-07 X Variable 4 82.46209 8.575956 9.615497 1.23E-17 X Variable 5 -25.878 6.152183 -4.20631 4.26E-05 X Variable 6 23.58251 6.841997 3.44673 0.000721 X Variable 7 -65.5795 12.8102 -5.11932 8.51E-07 X Variable 8 -0.07895 0.119403 -0.66123 0.50939 X Variable 9 0.267504 0.067547 3.960266 0.000111 X Variable 10 21.92639 15.05146 1.456762 0.147094 The following is the significant regression model Y= -2719.99-4.654x1+7.3959x3+82.46209x4-25.878x5+23.58251x6-65.5795x7+0.267504x9 The following tables summarizes the regression analysis results between demand for tanker demolition vessels and the other factors with demand for tanker order vessels, and tanker fleet vessels as the first and second independent variables respectively followed by the other variables in their original consecutive order. SUMMARY OUTPUT Regression Statistics Multiple R 0.717313 R Square 0.514538 Adjusted R Square 0.484937 Standard Error 18.39523 Observations 175 ANOVA   df SS MS F Significance F Regression 10 58818.9 5881.89 17.38226 2.87E-21 Residual 164 55495.08 338.3846 Total 174 114314       Regression model   Coefficients Standard Error t Stat P-value Intercept -282.493 50.51021 -5.59279 9.17E-08 X Variable 1 0.341644 0.286063 1.194297 0.234086 X Variable 2 -0.03089 0.005886 -5.24718 4.72E-07 X Variable 3 0.122769 0.125334 0.979533 0.328759 X Variable 4 5.025838 0.780561 6.43875 1.28E-09 X Variable 5 1.351591 0.516873 2.614939 0.009756 X Variable 6 1.205266 0.569503 2.116348 0.035825 X Variable 7 -2.73541 1.103409 -2.47905 0.014185 X Variable 8 0.026582 0.009517 2.793206 0.00584 X Variable 9 -0.00695 0.005734 -1.2117 0.22737 X Variable 10 3.024191 1.211288 2.496673 0.013524 The following is the significant regression model Y= -282.493-0.03089x2+5.025838x4+1.351591x5+1.205266x6-2.73541x7+0.026582x8+3.024191x10 Interpretation of analyzed data The correlation analysis results identify both direct and inverse proportionality relationship between the variables. This can however be explored further through regression analysis. The model for factors affecting demand for tanker orders fleet identifies a general existence of significant relationship. From a further analysis of each factor, the dependent variable is significantly accounted for by all the factors except demand for tanker demolition vessels, crude oil price, and production growth in pacific. The general model for factors affecting demand for tanker fleet vessels also identifies a general significant relationship that is significantly accounted for by all the independent variables except demand for demolition vessels, production growth rate in Atlantic region and Libor interest rate. Similarly, the general model for the demand for tanker demolition vessels identifies a significant relationship that is accounted for by all factors except demand for tanker orders vessels, Brent crude oil price, industrial production in India, and production growth in Pacific. Decision All the factors affect the shipyard industry. This is identifiable from a review of the three models because each factor is significant in at least one of the models. The demand for tank orders vessels is directly proportional to its significant determinants that have increasing trends. The management should therefore consider increasing production level of the type of ship because of expected increase in demand. The management should consider maintaining the production level of tanker fleet vessels because both of its negative and positive determinants are significantly and therefore cancel out for a constant trend. The major determinants for the demand for tanker demolition vessels are directly proportional to its demand and bear an increasing trend. The management should therefore consider increasing production of the type of ships. Conclusion The factors; Brent crude oil price, global oil productivity, and percentage industrial production by identified countries, growth rate in industrial production by regions, and the Libor interest rates, therefore affect performance of the shipyard industry. This is realized through the three identified models for each type of ship. Based on the null hypothesis that the factors are not significant in the industry, the report recommends that the corporation’s management keenly track the factors in predicting demand for its types of ships. Reference Mann, P. (2010). Introductory statistics. New Jersey, NJ: John Wiley & Sons. Read More