TAYLOR

Quantitative Techniques

E-Portfolio

LEONG YEW YONG

 

          We have chosen tourist arrivals and receipts to Malaysia variable for this assignment, arrivals as the independent variable and receipts as the dependent variable. By using this variable, we have made a scatter plot diagram using excel. It shows a positive linear regression between the two variables. Hence, it is appropriate to fit a regression in this case. Then, we used the data analysis to form a summary output. Form the summary output, we have form a regression line Y = 22.3161 + 3.2833Xby using the formula, Y=a+bX. By this, we found out that when there is no arrivals, the receipts will be 22.3161 billion using the y-intercept by substituting X=0. The 3.2833X shows that every unit increase in arrivals, the receipts will increase in 3.2833 units. Based on the analysis, I think that the dependent variable is explained by the independent variable because the coefficient of correlation, r in the summary output is 0.9897 which shows strong relationship between them. The determination of correlation, r2 shows that 97.95% of variation in arrivals of tourist, Y is explained by the variation of receipts. The remaining 2.05% is explained by other factor. As a conclusion, I would recommend to use this regression equation Y = 22.3161 + 3.2833Xto predict the dependent variable. This is because the r2is 97.95% which is considered a good prediction. The standard error is quite hard as the variable consist of decimal place. The scatter diagram also has a strong correlation as the point is close fit to the line and this shows the equation is reliable.

           Next, we used the independent and dependent variable to construct two descriptive tables.Then, we have chosen mean and median as the central location and standard deviation as dispersion value to interpret. For the independent variable (the arrivals), the average arrivals of tourist to Malaysia are 22.2978 which is the mean. The median shows half of the arrivals are below 23.65 and half are above it. The standard deviation shows that it spread 3.3682 around mean. For the dependent variable (receipts), the mean shows that average receipts from arrivals of tourist to Malaysia is 50.8933 and the median shows that half of the receipts are below 53.4 and half are above it. The standard deviation shows that it spread 11.1739 around the mean. Then, we construct two frequency tables using the two variables. First, we used the formula 2k>n to find the number of classes where n is the total number of observation of each variable .Then we used i (H-L)/k to find the class interval or width of the variable. H is the highest value and L is the lowest value in each of the variable, the k is the number of classes that we found previously. Hence, we can group it and construct a frequency data which consist of the variable and frequency. After we grouped it, we can then use it to construct two appropriate graphs which we choose to construct histograms. We used frequency at the vertical axis and the variable at the horizontal axis for both the variables.Lastly, by using the histogram we can easily find out the highest frequency and the lowest.