Dissertation Data Analysis In Management Science

In Brief

  •    You will find the best dissertation research areas/topics for future researchers enrolled   in management.
  •    In order to identify future research topics, we have reviewed the management science. (recent peer-reviewed studies).
  • The reason for using data analysis tool in management science
  • Various data analysis tool used in management science
  • How does statistical modeling utilised in the management science

Introduction

Management Science is very much crucial in management decision making. The primary purpose of decision-making is for effective and efficient utilization of scarce or the limited resources for which there are both private and public sectors of that economy. There are many types of management science methods and techniques which are applied in various systems of industry. It can optimize the utilization of those resources. The utility of the management science within the industry, government and in the case of non-profit sectors have grown up rapidly after the era of the Second World War (Smith & von Winterfeldt, 2004). This article discusses the requirements of data analysis tools in management science and indicates various types of data analysis models utilised in management science. This study evaluates statistical modeling to provide some effective knowledge of data analysis.

Reasons for using data analysis tool in management science

Data analysis tools are essential for providing in-depth approach in the case of recording, presenting findings, analysing or separating the data in the case of research in management science. Those tools are utilised for predicting the trends and behaviour of consumers or users. It helps in interpreting and delivering data in a meaningful way as the result of the research. A researcher performing research based on the business information system needs in-depth knowledge in data analysis as it can be utilised further for a company or business to control the label of the Business Intelligence (Sun, 2019). At the same time, researchers require to be very particular in using the data storage system through which they can store a large number of data as well. Further, the researcher has to know about the process of data mining by which information can be searched from hidden or in the case of unknown relations of the huge data system. Thus, development and proper utilisation of data are very much crucial in performing  research in management science (Prokopova, 2018)

Various data analysis tools used in management science

An analytical practitioner or a researcher needs  wide range of analytical capabilities and multiple techniques to perform the research of management science. In this respect, the researcher has to know about various data analysis techniques, like descriptive analytics, prescriptive analytics or predictive analytics. In descriptive analytics, the researcher needs to prepare data for subsequent analysis. In predictive analytics, the researcher needs to provide advance models for forecasting or predicting the future (Jelonek, 2017). Further, in the case of prescriptive analytics, the researcher needs to utilise the machine-based learning algorithm and some dynamic rules for providing interpretations and recommendations. To perform simple research, the researcher generally utilises MS Excel which is easy to understand and use. Also, there are some database servers, like MS SQL Server or ORACLE which are used for storing and analysing huge data system. Again Data cubes are also found to be utilised for better visualisation of data interpretation (Prokopova, 2018).

Figure .1 Data analysis through data cubes

Source Prokopová, et al.(2018)

Further, there are other data analysis tools which are used for data analytics process, data preparation, data analysis by actual number crunching or data visualization. Some of the most popular and effective data analysis tools are R Programming, Python, IBM SPSS Modeler etc (Jelonek, 2017).

R programming is found to offer one set of various inbuilt libraries as it helps to build up the visualization by utilising minimum code. R Studio is most used for the analysis in the case of R programming. The data set is needed to be set at first before analysing the data. It is very much important to identify all the variables and set up a correlation among the variables while pursuing analysis by R Programming (Horton & Kleinman, 2015).

Further, Python is utilised for import data sets, cleaning and preparing data for the analysis, manipulating the dataFrame and summarising the data. It helps to build up the machine learning model in some cases of research. Again for preparing data pipelines, Python is used. Python is considered as an interpreted language. For this, it needs more CPU time (McKinney, 2017).

Moreover, IBM SPSS Modeler is considered as the data mining along with the text analytics software. It is utilised for building up predictive models in data analysis. There is a visual interface in this software and it allows the users analysing data mining algorithms without any programming. For avoiding complexity of the data transformation, this software is very much useful (IBM, 2018).

Usage of statistical modeling in the management science

Statistics is considered as a scientific discipline. Statistical methods are found to be developed in the case where data are very scarce. Researchers utilise statistical data based on the data sets available for the research. Researchers need to have adequate knowledge of statistics for the proper designing of the study. Any improper statistical methods can result in an erroneous conclusion and can lead to unethical practice (Galeano & Peña, 2019). The variables utilised in the case of statistical models are quantitative and qualitative variables. Quantitative variables are categorised as discrete, ordinal and continuous variables. The continuous variables are two types, interval and ratio (Ali & Bhaskar, 2016).

In a statistical model, the most important part is to understand the relationship within the variables and based on that researcher has to select descriptive or inferential types of statistics processes in research. In the case of descriptive statistics, random selection is performed and the researcher needs to calculate the mean, mode and the median value (Ali & Bhaskar, 2016). Besides this, , the normal distribution has to be performed with the statistical variables. In this case, the symmetrical deviations in both the side with positive and negative directions are needed to consider.

Figure2 Example of a normal distribution

Source Ali & Bhaskar,  (2016)

Figure 3 Example of skewed distribution

Source Ali & Bhaskar, (2016)

In the instance of a skewed distribution, an asymmetry of variables is found about the mean. It can be positive or negative skewed distribution. Moreover, in the case of a statistical model, the researcher needs to perform parametric or non-parametric tests based on the objective of the research. In this case, there are various median test are available, such as sign test, Wilcoxon’s signed-rank test, Mann-Whitney test, Jonckheere test and Friedman test etc. (Galeano & Peña, 2019). Therefore, for analysing data, it is very much important to know the exact utilisation of various statistical approaches in a better way. When a researcher uses a statistical model, it becomes much easier to be a better communicator of the problem which he or she searches for. In this respect, data visualization plays a significant field in the research of management science.

Thus, there is much significance of data analysis tool in performing research on management science. For prediction or storage, the researcher has to know about the right process of data analysis. Statistical modeling plays an important role in data analysis as well.

References 

  1. Ali, Z., & Bhaskar, Sb. (2016). Basic statistical tools in research and data analysis. Indian Journal of Anaesthesia, 60(9), 662. https://doi.org/10.4103/0019-5049.190623

  2. Galeano, P., & Peña, D. (2019). Data science, big data and statistics. TEST, 28(2), 289–329. https://doi.org/10.1007/s11749-019-00651-9
  3. Jelonek, D. (2017). Big Data Analytics in the Management of Business. MATEC Web of Conferences, 125, 04021. https://doi.org/10.1051/matecconf/201712504021

  4. Prokopova, R. S. S. (2018). Cybernetics Approaches in Intelligent Systems (R. Silhavy, P. Silhavy, & Z. Prokopova (eds.); Vol. 661). Springer International Publishing. https://doi.org/10.1007/978-3-319-67618-0

  5. Smith, J. E., & von Winterfeldt, D. (2004). Anniversary Article: Decision Analysis in Management Science. Management Science, 50(5), 561–574. https://doi.org/10.1287/mnsc.1040.0243

  6. Sun, Z. (2019). Intelligent Big Data Analytics (pp. 1–19). https://doi.org/10.4018/978-1-5225-7277-0.ch001

X