Use Of Statistics: Symbolic Data Analysis

Write about the Use of Statistics for Symbolic Data Analysis.

 

Introduction

Statistics is a mathematical branch that is highly used in the effective presentation of data for easy understanding and interpretation. It is important to choose the best statistical criterion to represent the data to ensure that the intended information is passed on the to the target individuals. In some cases, data might be represented in a manner that communicates different ideas from the set objective (Hahn and Doganaksoy, 2011). Firstly, the data and the associated statistics needs to be understood before deciding the most applicable statistical tools to use. Table and charts are among the most used data representation tools in the field of statistics (Charles Henry, 2016). These tools are used in presenting the data to ease the work of interpretation to the individuals who are not able to classify statistics displayed in an essay format. In addition, tools like graphs and pie chart reduce data ambiguity by directly associating the variables or factors to their equivalent weights.

Body

The first step in dealing with data is data describing which describe the source of the data and how it was obtained. Data can be acquired by use of primary such as the use of questionnaires or another digital collecting criterion. In most cases, secondary data is credible for studies that need to cover larger capacities. In our case, determining the national growth in GDP and retail trade needs a massive data that can be used in generalising the information throughout the country. The second approach is to understand the data type and scales of measurements. A variable can be continuous or categorical, hence determining the analytical method to be used. In the business world, data is in the most case presented in monetary value and can be transformed into percentage forms depending on the reference points such as the base totals (Francis, 2009).

Providing the data summaries is a crucial step in the data analysis and report writing to ensure that the findings are communicated to the targeted individuals. Summaries and presentations improve the levels of understanding of the core aim of the research or evaluation. These summaries can be presented in a tabular form, with relevant statistics being associated with the variables. Some of the statistics that describes the data effectively include the measures of central tendency and dispersion. These include meaning, median, mode, standard deviation, variance, range and standard error. These descriptive statistics can be used in developing confidence intervals that are used in testing hypotheses. Point estimating is also used to compare the existing situation to the observations achieved from the study analysis.

Based on the economic update article, pie charts and table could be used to present the provided statistics in a more ethical manner. For instance, the total spending of 69% for household and 31% for retail could be represented in a pie chart as shown below (Billard and Diday, 2006).

Using these statistics, the probability of having the same scenario being experienced in the next year would be based on the observations. For instance, the chance of having retail spending being 31% percentage in the next year would be high. Also, if the data is collected at minimum biases, the data can be generalised into other areas of the country's economy (Ward, 2010).

The representation of the percentages could have been tabled based on the real values so the ideal change can be visualised. Using percentages might not indicate the true picture of the change that has been experienced. For instance, food sales rose by 0.2% and this might be seen to be a very small change for the sale. Probably, the change was very significant, hence creating a visible change to the market. A statistical technique in testing whether the increase was significant could be used to check if the rise in food sales were big enough to demonstrate a change (Kamath, 2009). It has been stated that China’s tourists contribute up to 16% of the spending. It would be much informative to include the other main contributors in the national spending to develop an oversight of the main contributors.  Hypothesis testing could have been used in this article to determine and proves the significance of the changes in sales and expenditures of the economy. It would be much effective if the author would have explained if the changes are justifiable or they are insignificance (Graham, 2011).

Conclusion

In summary, it is very important for any author or data analyst should understand the type of data and the associated data types. This information will enhance the effectiveness of analysis and presentation of the data. Choosing the best statistical tools is a good criterion to ensure that the best information about the data is presented to the target population. These tools also make it easy and for the readers and users of the articles. Finally, use of inferences and hypothesis testing are effective tools in determining the effectiveness of the results obtained in the study (Sedgwick, 2010). Therefore, it would have been better if the author used these statistical tools in the article.

References

Billard, L. and Diday, E. (2006). Symbolic data analysis. 1st ed. Chichester, England: John Wiley & Sons Inc.

Charles Henry, B. (2016). Understanding Basic Statistics. 1st ed. Cengage Learning.

Francis (2009). Effective Use of Numbers and Statistics. Acta Chirurgica Belgica, 109(3), pp.275-275.

Graham, A. (2011). Statistics. 1st ed. London: Hodder Education.

Hahn, G. and Doganaksoy, N. (2011). The Role of Statistics in Business and Industry. 1st ed. Hoboken: John Wiley & Sons.

Kamath, C. (2009). Application-Driven Data Analysis. Statistical Analysis and Data Mining, 1(5), pp.285-285.

Sedgwick, P. (2010). Statistical hypothesis testing. BMJ, 340(apr21 1), pp.c2059-c2059.

Ward, J. (2010). BIRT 2.6 data analysis and reporting. 1st ed. Birmingham, UK: Packt Pub.