Data analysis is the core element of every empirical and scientific research. With enough data, a conclusion can be made based on the interpretation on the findings from data analysis. It is essential for decision making and problem solving for top management in an organization. That is why the ability to manage the numerical data through different statistical methods is one of the current skill required by employers. In order to achieve this, we should improve our knowledge on statistics and research methods and should be able to use different statistical software to analyze the data more effectively. This article aims to provide general guidance on the procedure of conducting data analysis in the field of social sciences.
The four purpose of data analysis in a scientific study are as follow:
to answer the research questions
to achieve research objective
to test hypotheses (for quantitative research)
to determine the trends and relationship among the variables.
Phase one refer to the proposal stage in which the initial procedure was to plan the data analysis before the data collection is carried out. The four procedure at this phase are:
- Determine the data collection procedure
- Determine the data analysis methods (descriptive and inferential statistics) based on the research objectives
- Determine how to process the data (screening and key in data)
- Consult a statistician for further details (to ensure the correct analysis used in phase two)
Phase two refer to the full research stage (after collecting full data) in which all the data analysis methods that has been determined in Phase One will be carried out. The four procedure at this phase are:
- Screening the data (remove the incomplete form/questionnaires, finalize the total respondents and estimate the response rate)
- Key in the data in Statistical Software (SPSS, SMART_PLS, etc..). Need to reverse coding on the reverse items (if any).
- Run analysis (follow the step by step guide for each analysis methods)
- Interpret and discuss the findings (write down the findings)
As a conclusion, we need to realize that currently we live in a world that’s flooded with data. Therefore, the ability to analyze the empirical data isn’t limited to data scientists only. With enough training, practically anyone can follow these procedures to find the answers they need to solve some of the daily life problems or issues.
There’s no better time to learn the data analytical skill. As data continues to transform the way countless industries or company to operate, there’s been a huge increase in demand for people who have the analytical chops to make the most of it.
Are you ready to become a data scientist or data analyst yourself?