Data Analysis and Practical Application


Data analysis can be carried out with the aid of statistical software like SPSS or SAS in computer. Effective data analysis can be achieved by feeding proper information into the computer. It is good to choose the correct data technique for relevance and comprehensiveness if research work. Research analysis begins by defining the objectives based on content and focus together with characteristics of the data. Focus of the analysis entails description, estimation and hypothesis-testing (Diamantopoulos, 2000).

Learning Points

Definition of data analysis

  • Undertaking data analysis- choosing the method to be used whether SPSS or SAS.
  • The objectives of the data analysis- the kind of information required, reasons for the data analysis. Differentiating between analysis objectives and research objectives.
  • Analysis objectives- content of the analysis and focus of the analysis.
  • Description of the data-descriptive focus and descriptive statistics.
  • Estimation-estimation focus and sampling era.
  • Hypothesis- testing- significance test, statistical inference.
  • Characteristics of the data- sample size, sample type, variables, measurement, data values.

Critical Analysis

Data analysis is defined as the exercise where unorganized data is ordered and arranged systematically for the information to be utilized. It is the processing of data for comprehensiveness to refine it so that useful information is obtained. The various forms of analyzing data are charts, graphs and pictures. Data analysis is an important stage in the research process. A successful data analysis depends on the information and the instructions that are fed into a computer. There are several statistical soft wares that are used to analyses data. The soft wares are based on the field of research. Examples are SPSS for social sciences, SAS, RATS, Stata and MATLAB. The results that are generated from the data analysis can be valid depending on the quality based on the instructions and the information that is fed into the computer and the method of analysis that is applied. The tragedy in data analysis is to allow the computer to automatically run without instructions. To create a perfect data analysis, it is imperative that two factors are considered: first is the objective of the analysis and second, the characteristics of the data. Choosing the best method of data analysis depends the variables, whether dependent or independent variables (Good, 2006).

Data analysis is a form of descriptive statistics or a statistical inference. The objectives of the data are necessary in order to identify the kind of information that is required and how the data can be manipulated. The correct technique of data analysis should be selected. There are various forms data analysis techniques. Examples are univariate analysis which involves analyzing a univariable distribution, there is also bivariate technique of analysis and multivariate analysis which involves the statistical analysis of multiple measurements. Multivariate analysis encompasses both univariate and bivariate.

There are several factors that should be factored in while choosing data analysis technique: first, the researcher has to ensure all the assumptions that concern the technique are satisfied, these assumptions are normal distribution, independence among the observed sample, linearity and the lack of co-linearity and second, the provision of added statistics in the research.

Relevance is fundamental to data analysis because it facilitates the understanding of the research and to check on the comprehensiveness, which is the extent to which data is utilized. Data objectives are necessary to avoid redundancy that is experienced when some data analysis overlap. Research objectives also are of essence. This concerns the content of analysis and the focus of the analysis. Content of analysis is useful in selecting the variable while the focus of analysis concerns the orientation which can be descriptive or examination. The following aspects are useful in statistical analysis:

Descriptive statistics: This is the information sample that defines the abstraction of the population. It encompasses the following: association, tendency, causal relationship, the trend, pattern, dispersion and range. It is an abstraction phenomenon. Parametric analysis is widely used in abstraction phenomenon analysis.

Nature of the research: The research can be descriptive that is it attempts to deduce or infer and furthermore predict the cause and effect of relationship in the research. The common mistake in data analysis is the mistaking of statistics which can be avoided. A comprehensive analysis must have the exact data or information to be fed, the scientific reasoning or argument behind the analysis, the findings and the lessons (Hamid & Iman, n.d.).

Practical Application

Statistics serve the purpose of facilitating the understanding of data. Data analysis in business depends on several factors. Like any other venture, business operation depends on availability of market and capital; this relationship needs to be analyzed critically. This analysis can be arrived at based on various variables. This can be achieved through the undertaking of exploratory data analysis. Putting into consideration the above points is instrumental in the analysis of data. While undertaking a market research, for example, data analysis is mandatory in order to gauge market share or so that the business can position itself in the market well. Several data analyses are relevant in undertaking market research. Brand mapping is also necessary in the sense that it allows the rows and columns in the data matrix like the average satisfaction score for some of their products to be displayed in a multi-dimensional space. This is easily interpretable. Brand mapping demonstrates the image of the customer in the market (Lewis-Beck, 1995).

Choosing the right statistical packages is necessary if accomplished results are to be achieved. Perfect results of a market survey can be achieved through parametric and non-parametric tests. In a business, for example, identifying and analyzing the distribution of a sample population by use of statistical inferential procedures will enhance the understanding of how a population is distributed which can be confirmed via a symmetrical curve known as normal distribution. Having the knowledge of data analysis is important for a business to derive sense out of their research work. Employability of statistical procedures is important also to realize the response pattern. Data analysis is important if a person is to enter a new market, to launch a new product or to start a new business.


Data analysis sorts and organizes data in a manner that a reliable conclusion can be drawn out of it. It is important to identify the field of the research since it will be a precursor to the identification of the technique of analysis, characteristics of the data and objectives of the data. Data analysis involves making some of assumption because there can be missing problems or values that needs to be found out or some respondents might not have answered particular questions which need to be fed to the data analysis system. Data analysis is performed by the use of soft wares which are installed into the computer.


Diamantopoulos, A. (2000). Getting started with data analysis: Choosing the right method. Marketing Review, 1(1), 77-87.

Good, P. (2006). Resampling methods: a practical guide to data analysis (3rd ed). New York, NY: Birkhauser.

Hamid, A & Iman, M. (n.d.). Techniques of data analysis. Web.

Lewis-Beck, M.S. (1995). Data analysis: an introduction. New York, NY: SAGE.