# Analyzing data

Introduction

Research studies involve collecting all the necessary data that pertains to a particular problem of study. An individual may employ either inferential or descriptive statistics during the process of analysis. Ordinarily both inferential and descriptive statistics analyze research studies when drawing conclusions when a group of people conducts a research. The paper will analyze existing types of statistics and investigate how they are employed in the research study that aims at determining some of the problems affecting Airtel Company.

## Types of Descriptive Statistics that might be best for summarizing the Data

Researchers employ descriptive statistics when describing some of the basic features of data in a particular study for example the research on problems affecting Airtel Company (Zikmund, Babin, Carr, Griffin, 2013). They supply simple summaries on measures as well as sample. Descriptive statistics are used with graphic analysis in forming basis of each quantitative data that has to be analyzed. This means that the statistics are used to describe what a particular data shows or what it is like in the given study on problems affecting Airtel Company. It is however important to note that descriptive statistics are useful tools in presenting quantitative data in a manageable structure that are descriptive in nature (Zikmund et al., 2013). This means that when a sample of data is collected, one is able to measure a large number of samples. Therefore, it is plausible to indicate that descriptive statistics is an effective method of simplifying voluminous data in sensible manner. This is by reducing excess sample data to achieve a simpler summary.

It is worth noting that every time a researcher try to describe a voluminous set of observations as in the case of the above baseball sports to find a single indicator, he or she always runs the risks of getting original data distorted. In addition, there is always a chance of losing some important details in such a particular study. However, it is important to note that descriptive statistics are an ideal way of providing powerful summary that researchers can use when comparing with other relevant information elsewhere (Bhattacharya & Michael, 2008).

## Types of Inferential Statistics that might be best for analyzing the Data

The type of statistics is normally used when a researcher is trying to achieve summaries or conclusions that extend available data collected or sampled (Anderson, Sweeney, Williams, 2011). Inferential statistics are useful tools when individuals want to infer using the available data. This means that this type of statistics makes it possible to make accurate judgments as far as the probability is concerned. Collected data or samples normally have different features that make it possible for a person to categorize them into different groups. In this case, inferential statistics enable researchers in the process of making inferences from available data to more generalized conditions (Anderson et al, 2011). This is contrast to descriptive statistics used to describe what is presented by collected data. It is therefore important to note that inferential statistics is a useful tool during quasi-experimental and experimental programs or research design as far as outcome evaluation process is concerned.

Moreover, a simplest inferential investigation is employed when researchers want to compare two or more groups’ performances usually on a simple measure with the main goal of determining whether there is any difference (Brooks & Weatherston, 2000). Major inferential statistics are generally developed from a statistical models identified as the General Linear Models. The elements include analysis of variance, t-test, regression analysis as well as various multivariate methods. The types are better suited when conducting such a research on problems affecting Airtel Company. The multivariate methods include; multidimensional scaling, analysis, discriminate function and cluster analysis (Anderson et al, 2011). Therefore, due to the significance and popularity of the General Linear Model it would be an ideal decision to be able to understand its working and hence employ it during research processes.

It is therefore important for any researcher to learn how to analyze program outcome evaluations by way of comparisons between the non-program and the program group of outcome variables or a distinct variable. This normally depends on the type of research design that a researcher uses. However, research designs are mainly divided into two main broad types and they include; quasi-experimental and experimental designs (Bryman & Bell, 2015). The two designs normally differ from each other and therefore researchers are forced to present inferred data separately during presentations. For instance, inferential statistics are applicable when one may want to find out if eight-grade girls and boys differ from each other in a particular test such as math. It is also used when determining any existing differences on program group as far as the outcome measures from a specific control group is concerned. During such studies, a researcher may have to consider using the t-test because it is effective in measuring average performance between two categories or classes of available data.

## The role of Trend analysis or Probability

In this regard, trend analysis or probabilities are vital to the company’s business environment as they are effective in the process of improving business performance. This is done by identifying specific areas of the business that are performing through the collected data over a period and be able to duplicate success through improving certain their performance (Zikmund et al., 2013). On the other hand, if the collected data indicate some under-performing areas in the business environment, business individuals would employ new tactics or processes that will improve their performance. Moreover, it is worth noting that trend analysis or probabilities will be critical tools that help Airtel business managers to make informed decisions on business activities such as in the identified business problem on challenges affecting Airtel Company.

References

Anderson, D. R., Sweeney, D. J., & Williams, T. A. (2011). Fundamentals of business statistics. Cengage Learning.

Bhattacharya, A. K., & Michael, D. C. (2008). How local companies keep multinationals at bay. Harvard Business Review86(3), 20-33.

Brooks, I., & Weatherston, J. (2000). The business environment: Challenges and Changes. Ft Press.

Bryman, A., & Bell, E. (2015). Business research methods. Oxford University Press, USA.

Gwinner, K. P., Gremler, D. D., & Bitner, M. J. (2013). Relational benefits in services industries: the customer’s perspective. Journal of the academy of marketing science, 26(2), 101-114.

Zikmund, W. G., Babin, B. J., Carr, J. C., & Griffin, M. (2013). Business research methods. Cengage Learning.