Working budget of $ 2 billion Methods research - Coursework Example

? Working budget of $ 2 billion Methods research-- finance paper Affiliation with more information about affiliation, research grants, conflict of interest and how to contact Topic:  Working budget of $ 2 billion Methods research-- finance paper 1. Using the three electronic resources, compile the required data for the 48 countries in an Excel spreadsheet (each row should represent a country and each column should contain the data for one variable). Gross Domestic Product (GDP) is very important in the calculation of the national income of any country. The GDP is calculated by adding the market value of all the final goods or services produced within a country in a given financial year. to be more specific no intermediate goods but only the final products or services because if intermediate goods are also taken into consideration then there would be the error of double calculation in the national income of the country. The GDP of a country is arrived at by adding the sum involved in the consumption activities, the investment activities, the spending by the government of the country and also the net exports (which is derived by deducting the gross imports from the gross exports). GDP = Cn + It + Gs + E(e-i) Where Cn = consumption, It = investment, Gs= Government spending, E= net exports, i= imports, e= exports. The exogenous model is also called as the most suitable model which is needed to understand and frame the long term economic growth of a country. Excel sheet attached. 2. Read the compiled data into Stata, and estimate the empirical model. Test the following null and alternative hypotheses: gen Lypc 2005 =log( ypc2005) gen Lypc1990 =log( ypc1990) gen diferrence lypc=log(ypc2005)-log(ypc1990) gen lseced = log(seced) gen infl= log( cpi1990)-log( cpi1985) inflation regress dlypc Lypc1990 lseced govgdp open infl credit (i) H0:?2=?3=?4=?5=?6=?7=0 against H1:?j?0 for at least one j?(2...7), using a significance level of 0.05. = = = 1.81 The Decision rule is that we can : Accept H0 if ??F0.05 Reject H0 if ?>F0.05 where F0.05 is the 5% critical value from F(k–1, n–k): in this case F(7–1,48–7), or F(6,41). F0.05 = 2.34 Decision is accept H0: F plays a significant role as F is the determining factor of arriving at conclusions. The use of the independent variables has not assisted in predicting the dependent variable (dlypc). (ii) H0:?2=0 against H0:?2?0 using a significance level of 0.05. ii) H0:?2=0 against H1:?2?0 at a significance level of 0.05 ? = = = -2.68 Decision rule: Accept H0 if -t0.025 ? ? ? t0.025 Reject H0 if ? < -t0.025 or ? > t0.025 ?t0.025 from t(41) is ?2.04 Decision is reject H0.: it means the variable (lypc90) has a significance impact in the depended variable (dlypc). We can see that there is a contradiction between the test in (i) and (ii). In (i) we accept that: ?2=?3=?4=?5=?6=?7=0 where in (ii) we reject that :?2=0 . Also, we can check by compare the p-value of the coefficient (0.011) t0.005 ?t0.005 from t(41) is ?2. 7 Decision is accept H0. it means the variable (lypc90) has no significance impact in the depended variable (dlypc) when we used significance level of 0.01. (iv) H0:?3=0 against H0:?3>0 using a significance level of 0.05. To test H0:?3=0 against H1:?3>0 at significance level 0.05 ? = = = 2.61 Decision rule: Accept H0 if ? ? t0.05 Reject H0 if ? >t0.05 t0.05 from t(41) is 1.7 Decision is reject H0, which means the independent variable (lseced) has a significance effect in the dependent variable dlypc. Also, we can check by compare the p-value of the coefficient (0.013) 0 using a significance level of 0.05. To test H0:?7=0 against H1:?7>0 at significance level 0.05 ? = = = 1.69 Decision rule: Accept H0 if ? ? t0.05 Reject H0 if ? >t0.05 t0.05 from t(41) is 1.7 Decision is accept H0. Which means the independent variable (Credit) has no significance effect in the dependent variable dlypc. Also, we can check by compare the p-value of the coefficient (0.099) >significance level (0.05). Apparent contradiction between the test results in (i) and (ii). The test results in i and ii are contradictory as one explains the significance of F while another explains the significance of secd which means the percentage of secondary school going students and its effect on the national economy of all the fourty eight countries. 3. On the basis of the model you have fitted and tested in Q2, formulate your advice to the Finance Minister on the question as to whether US$ 2 billion would be spent more effectively on secondary education, or on bailing out the banks, assuming that the policy objective is to increase growth in GDP per capita over the next 15 years. On the basis of the models tested in the question 2 the best decision which can be arrived is to spend more effectively on the secondary education than bailing out banks in the countries. Since the main aim is to increase the GDP rate over the next 15 years therefore the mian focus is on long term growth. Bailing out banks will be a short term process and will show only a short term increase in the GDP rate while spending more on the secondary system of education will generate more national income in the form of efficient human resource who can increase the per capita income of the country and in turn increase the GDP. The effect of on credit GPD per capital = 2.98 The effect of lseced on GPD per capital= 17.25 We can see that spending the 2 billion on improving the secondary education would be a better idea than bailing out banks with respect to the effect of credit and secondary education on the GDP of a country. Because The effect of on credit GPD per capital is around 3% only while the effect of lseced on GPD per capital isw around 17%. This is a type of investment activity and thus the government should focus on long term goals and so it is advisable to spend the amount of $ 2 million dollars on financing the secondary education of students rather than bailing out banks which is a short term deal. “Using a short-term investment product for a long-term investment horizon can increase the opportunity cost of your decision. On the other side, using a long-term instrument for a short-term need can increase your liquidity risk and cause you to lose funds or opportunities.” (Victor, 2011). Answer to Question 4 Diagnostic Tests for ascertaining validity of statistical assumptions: (i) Testing the linearity assumption by using RESET test: RESET test: H0: the Model is correctly specified as linear. H1: the model is not linear RESET test: Decision rule: Accept H0 if ? ? the model is correctly specified in linear form Reject H0 if ? > the model is incorrectly specified in linear form ? = nR2 (from the auxiliary regression) = 48?0.0206 = 0.99 from ?2(1) = 3.84 In this case of linearity assumption, Ho would be accepted if value of t is less than or equal to In this case t = 0.99 while = 3.84 Thus this hypothesis is validated and the model is correctly specified as linear. (ii) Testing the homoscedasticity assumption by using RESET test: LM test: H0: the Model is homoscedasticity H1: the model is not homoscedasticity ML test: Decision rule: Accept H0 if ? ? the model is homoscedasticity Reject H0 if ? > the model is not homoscedasticity ? = nR2 (from the auxiliary regression) = 48?0.0052=0.249 from ?2(1) = 3.84 In this case of homoscedasticity assumption, Ho would be accepted if value of t is less than or equal to In this case t = 0.249 while = 3.84 Thus this hypothesis is validated The decision is to accept the null hypothesis of homoscedasticity (iii) Testing the normality assumption: Bera and Jarque’s (1982) skewness-kurtosis test: Decision rule: Accept H0 if ? ? ? the ui’s are Normal Reject H0 if ? > ? the ui’s are non-Normal H0:ui ~ N is true, ? = = 31.599894 [ from ?2(2) = 5.99] In this case of normality assumption, Ho would be accepted if value of t is less than or equal to or rejected if it is more. In this case t = 31.599894 while = 5.99 Thus this hypothesis is invalidated since t values are higher than assumed. Decision is reject the null hypothesis of normality Answer to Question 5. To solve the non-normality problem, we have to create dummy variables 0 to 1 to remove the outliers observation with residual larger than three times the standard error (3*0.2808=0.8424) of the regression. We found that Zimbabwe has the extreme value. After we exclude the outliers we re-estimate d the model using the new specification (dc) and we repeat the diagnostic test. (i) Testing the linearity assumption by using RESET test: RESET test: H0: the Model is correctly specified as linear. H1: the model is not linear RESET test: Decision rule: Accept H0 if ? ? the model is correctly specified in linear form Reject H0 if ? > the model is incorrectly specified in linear form ? = nR2 (from the auxiliary regression) = 48?0.0206 = 0.625 from ?2(1) = 3.84 In this case of linearity assumption, Ho would be accepted if value of t is less than or equal to In this case t = 0.625 while = 3.84 Thus this hypothesis is validated The Decision is to accept the null hypothesis of linearity (ii) Testing the homoscedasticity assumption: LM test: H0: the Model is homoscedasticity H1: the model is not homoscedasticity ML test: Decision rule: Accept H0 if ? ? the model is homoscedasticity Reject H0 if ? > the model is not homoscedasticity ? = nR2 (from the auxiliary regression) = 50? 0.0188=0.94 from ?2(1) = 3.84 In this case of homoscedasticity assumption, Ho would be accepted if value of t is less than or equal to In this case t = 0.940 while = 3.84 Thus this hypothesis is validated The Decision is to accept the null hypothesis of homoscedasticity (iii) Testing the normality assumption: Decision rule: Accept H0 if ? ? ? the ui’s are Normal Reject H0 if ? > ? the ui’s are non-Normal ? = = .735898 [ From ?2(2) = 5.99] In this case of normality assumption, Ho would be accepted if value of t is less than or equal to In this case t = 0.735898 while = 5.99 Thus the decision is to accept the null hypothesis of normality Answer to Question 6: After we have re-specified and re-estimated the model, we have found out that we choose the wrong decision in making budget allocations for spending $2 billion on bailing out of the distressed banks. As a matter of fact, according to the new evidence made available for the purpose of this budget analysis of how best to invest the $ 2 billion, it is evidenced that it might be better to spend the budgeted allocation of $2 billion in the secondary education and try and increase the per capita GDP by 2.76% rather than trying to bail out the distressed banks by putting in the money as bail money for their bailment. Because effect of lseced on GPD per capital =0.2667371*In(61)%- In(55%) = 2.76% But the effect of credit on GPD per capital= 0.1970321* (56%-44%) =2.3% Conclusion: Thus, the better option considering the above data, would be in terms of using the allocated budgetary funds of $2 billion in policy measures that will increase the country’s rate of enrolment in secondary education and trying to boost the secondary school enrolment rate by about 6%, from the current figure of 55% to an estimated 61% in near future. Reference List Victor, D. (2011).How to choose the right investment options for your financial portfolio. Helium. Retrieved January 29, 2011, from http://www.helium.com/items/1574342-how-to-choose-a-good-investment Read More