TAYLOR

Quantitative Techniques

E-Portfolio

HOR CHUN KIT

 

          For Part A question 1, it wants us to identify and state clearly the appropriate independent and the dependent variable by referring the lecture notes. We have identified that the independent for this question is arrival while the dependent are the receipts (RM). Question 2, it asked us to use Excel to draw a scatterplot with all necessary information provided in the previous question. My group members and I had make up a scatterplot graphs with Excel and had given the graphs on the answer slides. Next, question 3, it asked us that is it appropriate to fit a regression line in this case based on our own scatter diagram and explain it. The answer is yes, because when the arrivals increase, the receipts increase and this shows a positive linear regression between the arrivals and the receipts. For question 4, use Excel to generate a summary output for regression analysis. For this question, my group members and I had generated a summary output for the regression output and it can be found in our answers slides. Question 5 asked us to form a regression line from our summary output and interpret the value of y-intercept and slope. The formula for the regression line is Y=a+bX. When a=22.3161, b=3.2833, then Y will be Y=22.3161+3.2833X. The interpretation for the Y-intercept is when there is no arrivals, the receipts will be 22.3161 billion, slope of the equation increases 3.2833 unit in receipts when arrivals increasing in every unit. Question 6 asked us to explain reasons and how we think about the dependent variable is explained by the independent variable based on our analysis. My group members and I discussed and came out with the final answer which is yes, because the dependent variable is explained by the independent variable because the coefficient of correlation, r 0.98897 which shows a very strong relation between them and also the determination of correlation also shown that 97.95% of the variation in the arrivals of tourism, Y is explained by the variation of the receipts, only remain 2.05% of it is explained by the other factors. Question 7 ask us would we recommend using the regression equation to predict the dependent variable and explains with our reasons and how reliable is it. The answer from us is yes we will recommend on using this regression equation to predict the dependent variable because the coefficient of determination, r2is 97.95% which is considered a good prediction. The standard error is 1.78 which is quite high. It may be because of the variable X and Y consist of decimal places and also the scatter diagram shows it has a strong positive correlation between the variable because all the point is close fit to the line. Therefore, the regression equation Y=22.3161+3.2833X is a good predictor for the dependent variable, receipt.

                As for Part B question 1, it ask us to use the similar data above and construct two descriptive tables, select and interpret on the most appropriate two central location values and one dispersion value for each set of data. My group members and I had constructed two descriptive tables and selected on interpreting the most appropriate two central location values and dispersion value for each set of data given on our answer slides. Question 2 asked us to construct two suitable frequency tables for our data set, one for the dependent variable and one for the independent variable and show all appropriate calculations while constructing the tables. We have constructed suitable frequency tables in the answer slides. Both of the k value for both tables are k=4 while the class interval or width for both are different, where one of it is 2.32 and the other is 8.36. As for question 3, it asked us to use Excel again to draw an appropriate graphs to elaborate the answer found in the previous question from Part B. We have drawn both of the graphs for both of the frequency data mentioned in the 2nd question in Part B in the answer slides for this question. Question 4, the last question, asked us to describe the features for the graphs that we have drawn. We described that the arrivals of tourist histogram show that highest frequency of 5 arrivals to Malaysia is between 23.42 – 25.74 and 2 frequency lie in 16.43 – 18.75. There is 1 frequency in 18.76 – 21.08 and 21.09 – 23.41 respectively. For the receipts from tourism histogram, the highest frequency is 3 which lie in 48.74 – 57.10 and 57.11 – 65.47 respectively. The lowest frequency 1 lies in 40.37 – 48.73. The 32.00 –40.36 has two frequency.