The Relationship Between the Gross Domestic Product and the Balance of Trade - Essay Example

College: Topic: Effects of Recession on International trade of UK Dissertation This paper looks at how recession impacts on international trade, specifically looking at the case of the united kingdom within the years of 2001 and 2013.On its analysis, this paper assumed a non-positive correlation between the gross domestic product and the international trade for the population of analysis. This paper sources its data from arguably most reliable internet sources and uses it to analyze the situation. Since the gross domestic product is a function of the recession, the paper uses it as a representative to interrogate its findings. Recession has been characterized with variables such as unemployment, jobs creation and availability, the incomes of the affected population as well as aspects of housing and demography. This paper even so narrows its scope to take the gross domestic product to represent the aforementioned variables. Recession can be argued by this paper to affect the social life in terms of increase in crime, This, loosely speaking, can be said to result from the cases of lack of jobs, unemployment, and the effect of recession on higher education or education in general. Due to the recent cases of recession, there have been reports of sharp increases in unemployment rates, evident in between the years, 2008 and 2009 (Trading Economics, 2014). This happened concurrently with drastic declines in employment rates in a given span of years. The number of available jobs fell and this impacted negatively on production. This paper notes that, during the recession period, most of the lively hoods in the UK were negatively impacted. This is what prompted the analysis. As much as there exists domestic negative impacts, this paper seeks to find out if the same impact has a relationship with the international trade. This paper developed a model, Y = -73460693 -0.596*balance of trade, to relate and predict the effects of the recession on international trade. Introduction The daily activities in the world derived from quantitative techniques. Practical phenomena and decisions need to be addressed more accurately and effectively. Practically the everyday numerous decisions that must be made are assisted by analyzing datasets quantitatively. The importance of this statistical technique is the fact that unlike in the academia, the real business world is rich in information to base on in making critical decisions correctly. The development of statistics and more specifically quantitative analysis methods is majorly due to the inability to identify the characteristics of interest in most instances of business decision making process Statistics entails the whole process of collecting samples, organizing, analyzing them eventually interpreting the data for useful applications. Statistics can also be a term used to refer to the numerical values which are a representative of the characteristics under consideration. Qualitative methods allow for an insight into the population, for instances when information about population is desired, for one reason or another it is either impossible, time consuming or too expensive to carry out the statistic on every individual of the population, it calls for such methods as qualitative analysis to analyze the dataset. Mostly a representative sample is obtained from the population and analyzed quantitatively to represent the entire population (Manski, 1997). Quantitative data as opposed to qualitative data categorizes elements by attaching numeric measures to them. The data is a set of true numbers which makes it possible to analyze with most quantitative techniques available. This type of data is either interval or ratio data. The interval quantitative data lacks a natural starting point. Alternatively, ratio quantitative data has a zero level or a natural starting point, such data include net expenditure or net income. This paper purposes to use quantitative analysis techniques to analyze a data set and draw conclusions. Since quantitative methods have proved to be a tool for survival in the modern business world.it is of important for this paper to highlight the various quantitative methods used in business analysis. From the many types of quantitative methods of data analysis, some of the most commonly used are linear programming, data mining, factor analysis and the one used by this paper, regression analysis. This paper uses the quantitative analysis to make a research conclusion based on statistics. It gives a summary of the quantitative variables including the measures of central tendency including the mean, mode and median, the measures of scatter including the range and standard deviation and to perform a regression analysis. The paper will focus on the linear regression and draw its conclusions from the observations thereof. (Manski, 1997). Data description This paper analyzes a data set derived from a sample representing the gross domestic product of the United Kingdom and the corresponding international trade representative. Data on balance of trade was taken to represent the situation of international trade, this was from the fact that the two are functions of each other. The analyses seek to find out the relationship of the sets and how they vary in relation to each other. The data obtained represented the trend in the two variables from the year 2001 to 2013 as tabulated in appendix 1 (Trading economics, 2014). Methodology In order to achieve a regression model for analysis, it was necessary to obtain the information or data to be used in the model to make predictions. The information was obtained from a sample available from the internet resources. The relationship between the obtained data is then modelled by regression analysis. The regression model used for observation was linear characterized by the regression equation. A scatter plot of international balance of trade for the united kingdom versus the corresponding gross domestic product for a span of years from 2001 to 2013 was made, this was an analysis of how week or strong the two variables under consideration were. This was followed by descriptive statistical analysis to get the insight of the distributions of the datasets including the measures of central tendency for the purposes of describing the datasets used. Correlation of the bivariate data set was done to further establish the relationship of the data, and finally, regression analysis was carried out basing on a null hypothesis and assuming a non-zero gradient. Method of analysis Since datasets may vary, before finding the best statistical technique to employ in the analysis, any researcher is first supposed to determine the type of data collected. Generally in statistics there exist two kinds of data sets, qualitative data and quantitative data. Not at all time’s do data exist in numerical form; some phenomena demand that data is categorized in a non-numeric form. In the business field, a good fraction of data relates to how the customers or clients feel or taste about a product, this will form qualitative data. This paper applied the use of both numerical as well as graphical approaches of quantitative techniques to summarize and display the information of the data sets under observation. Results Descriptive statistics Chart 1: scatter chart of the gross domestic product and the united UK balance of trade Chart 2: The United Kingdom balance of trade (million GBP) Chart 3: Gross domestic product (GBP).Generated from data in appendix 1. Table 1: Correlations United kingdom balance of Trade(million GBP) Gross domestic product(GBP) United kingdom balance of Trade(million GBP) Pearson Correlation 1 -.385 Sig. (2-tailed) .194 N 13 13 Gross domestic product(GBP) Pearson Correlation -.385 1 Sig. (2-tailed) .194 N 13 13 The two charts above (chart 3 and 4) describe the properties of the dataset under observation expressing the means; both data are seen to assume a normal distribution fit with little Skewness. From the correlation table 1, the coefficient of correlation is seen to be negative. This indicates a negative correlation between the international trade and gross domestic product. Similarly, from the scatter plot as illustrated in the chart 1 above. The points are seen to exhibit a weak relationship. This is evident from the widely dispersed points on a scatter plot. Also, the pattern of the scatter is seen to move from right to left indicating a negative correlation. Regression analysis results data sheets Table 2: Variables Entered/Removed Model Variables Entered Variables Removed Method 1 Gross domestic product(GBP)a . Enter a. All requested variables entered. b. Dependent Variable: United kingdom balance of Trade(million GBP) Table 3: Model Summary of the regression analysis. Model R value R Square Adjusted R Square Std. Error of the Estimate Change Statistics R Square Change F Change Degree of freedom 1 Degree of freedom 2 Sig. F Change 1 .385a .148 .071 1.0743488E3 .148 1.916 1 11 .194 a. Predictors: (Constant), Gross domestic product(GBP) b. Dependent Variable: United kingdom balance of Trade(million GBP) Table 4: The F value and p value Table ANOVA test Model Sum of Squares Degree of freedom. Mean Square F value Sig. 1 Regression 2211212.814 1 2211212.814 1.916 .194a Residual 1.270E7 11 1154225.409 Total 1.491E7 12 a. Predictors: (Constant), Gross domestic product(GBP) b. Dependent Variable: United kingdom balance of Trade(million GBP) Table 5: Coefficients Model 95% Confidence Interval for B Correlations Lower Bound Upper Bound Zero-order Partial Part 1 (Constant) -7349.693 19974.420 Gross domestic product(GBP) -.596 .136 -.385 -.385 -.385 a. Dependent Variable: United kingdom balance of Trade(million GBP) Table 6: Collinearity Diagnostics Model Dimension Eigenvalue Condition Index Variance Proportions (Constant) Gross domestic product(GBP) 1 1 1.999 1.000 .00 .00 2 .001 41.639 1.00 1.00 a. Dependent Variable: United kingdom balance of Trade(million GBP) Table 7: Residuals Statistics Minimum Maximum Mean Std. Deviation N Predicted Value -2.894319E3 -1.438695E3 -2.269231E3 429.2641779 13 Residual -1.4054670E3 2.7165208E3 -1.3861049E-12 1.0286107E3 13 Std. Predicted Value -1.456 1.935 .000 1.000 13 Std. Residual -1.308 2.529 .000 .957 13 a. Dependent Variable: United kingdom balance of Trade(million GBP) Chart 4: Normal P-P plot of regression standard residual. Generated from the data set in appendix 1 Discussion From the table 3 above for the model summery, the value of R squared that result is 0.148.convertng this to a percentage format gives 14.8 percent. From this percentage value, it can be deduced that the predictor variable (The gross domestic product) accounts for only 14.8 percent of the corresponding dependent variable.it can be argued that the remaining percentage (85.2) is accounted for by other factors. This implies that gross domestic product does not really explain a lot. From the Anova table (table: 4), a significance of 0.194 is noted which is 19.4 percent. This value implies that a less significant statistical argument and hence this analysis cannot reject the null hypothesis of no relationship. This further means that gross domestic product does note really affect the balance of trade of the United Kingdom. The table of coefficients (table: 5),a highly negative constant is which means when gross domestic product is equal to zero, the corresponding balance of trade is -7349.693.this is meaning full when attempting to predict the balance of trade from the predictor variable in this analysis. From the model summary table: 3, the correlation coefficient 0.286 as found earlier is noted. The table also gives the value of R squared. Converting this to a percent gives. From the table of correlations, the p-value value obtained found to be 0.194, this value is found to be greater than the F-value in table 4, which was found to be 1.619. Basing on this fact where the p value is greater than the F-value, it indicates that the null hypothesis is valid. Still, important conclusions can be made however small the prediction interval may be. Regression analysis The regression equation: Y =a +b X + e, Where : ‘a’ is a constant denoting the intercept of the curve, ’b’ is the slope or gradient of the curve which is taken as the regression coefficient and the values of ‘Y’ and ‘X’ representing the dependent and independent variables respectively. For the purposes of regression analysis of this paper, the dependent variable (Y) was an international trade value, the balance of trade in GBP while the independent variable was the gross domestic product of the United Kingdom. The values of observation were a sample of progressive data between the years 2001 to 2013.the ‘e’ term represents the error in the statistic. The null hypothesis for the analysis that the variation of international trade balances is unrelated to the gross domestic product. It is still possible to draw some meaning full statistics, given the error value (s) in the summary table 3, an approximate 10% error is estimated. This indicated conclusions can be made from the model with up to 80%. The analysis was a simple regression analysis with the values of slope been taken as a value not equal to zero. From the Regression equation, a regression model is shown below. From the coefficients chart (chart 5), values of ‘a’ and ‘b’ are derived as next. a = -73460693 b = -0.596 The regression equation will be given by Y = -73460693 -0.596*X And since our X is the balance of trade, the regression model for this analysis will be like next. Y = -73460693 -0.596*(balance of trade) The model derived above still remains statistically meaningful despite the low R- squared value encountered in the analysis, the low value served to indicate how hard it is to use the predictor to draw conclusion, however, this analysis finds an eighty percent chance of an accurate prediction from the model. Conclusion This paper has analyzed the relationship between the gross domestic product and the balance of trade. This was an attempt to find out the effect of the recession on the international trade in the United Kingdom. This report has through both descriptive statistics and majorly from regression analysis, shown the patterns of change in relation to each variable. This paper concludes that a regression model is an important instrument for predicting the behavior of one variable based on another. The use of linear transformation in this paper enabled the creation of a model from the parameters such as the least squares; this model was able to simulate future behavior of the variables based on an input predictor variable (X). However, as noted from the percentage error, the predicted values lie within a margin of 10% error. This paper recommends for the use of similar data and quantitative techniques such as regression to create a model for the recovery of the United Kingdom from recession. Such a model could be beneficial in such a way that the stakeholders will be able to foresee the consequences of their choices. This however comes with the short falls of the ability of these models to predict events accurately. Reference list Manski, C. F. (January 01, 1997). Regression. Foundations of Probability, Econometrics and Economic Games / Edited by Omar F. Hamouda and J.c.r. Rowley. Trading Economics. (March 20, 2014).United Kingdom, Economic indicators. http://www.tradingeconomics.com/united-kingdom/indicators Appendix Appendix 1: Regression analysis data set. Year International trade(GBP) Gross domestic product (GBP). 2001 -1200 33698.5696 2002 -1400 34535.2997 2003 -3200 35245.6138 2004 -1600 36442.4944 2005 -2700 37313.3557 2006 -3000 38121.5629 2007 -3200 38873.2059 2008 -3700 40027.0519 2009 -2500 39376.963 2010 -3000 37556.5274 2011 300 37949.7737 2012 -1500 38032.3967 2013 -2800 37849.5715 Source: Trading Economics. http://www.tradingeconomics.com/united-kingdom/ Read More