June 03, 2020
In this seventh edition of the OWSD Nigeria National Chapter University of Port Harcourt Branch series of scientific communications, Linda Oghenekaro gives us an overview of research data.
Data has become one of the most valuable assets in recent times and research data in particular, has proven to be an important resource that fuels the knowledge economy. As it is rightly said by Clive Humby, “Data is the new oil in today’s information economy”. Science, as we know, is a data-driven field and the quality of our scientific study depends largely on the value of our research data.
II. What is Research Data?
Research data can be defined as recorded facts or statistics generated and collected, for processing and interpretation in a bid to produce original research results. It can exist in many forms such as text, number, image, audio, video and script. Organizing research data electronically as on a computer system for easy access and management, gives rise to a database.
III. What category of research data should we be interested in?
Depending on the nature of the research, a choice can be from the two broad categories of research data.
- Quantitative Data: They are measurable data used to formulate facts and they are structured, numerical in nature and statistical. Examples are data gotten from measurements. Researchers who want to quantify a research problem usually adopt this category of data.
- Qualitative Data: This category holds text-based data, which is less structured in nature. They are usually gotten from questionnaires. It is more concerned in describing a topic rather than measuring it.
Fortunately, both categories do not contradict each other, rather they complement themselves. A research might begin with the quantitative data to prove the general points of the study and then adopt the qualitative data to give more details of one’s findings.
IV. How do we generate Research Data?
Research data can be generated by the researcher using either the primary or secondary data collection techniques. For primary data collection, techniques such as experiment, survey or direct observation can be applied. While techniques used in collecting information from existing sources such as data repositories, market surveys, and standard reports, can be applied for secondary data collection.
Based on the technique applied to data generation; four main types of research data can be envisaged, and their individual nature affects the way they ought to be managed. They include:
- Observational Data: They are captured through examination of an activity or behavior.
- Experimental Data: This type of data is gotten from experiment through active intervention by the researcher.
- Simulation Data: They are generated by imitating the operation of real-world processes over time using computer test models.
- Compiled Data: Derived data involves using existing data points, often from different data sources and integrated to create new data through some sort of transformation.
Some helpful tips that can be applied when generating research data include:
- Start sourcing for your data early, to avoid falsifying them.
- Avoid factors that will lead to bias; be open to your findings on the field.
- Consider large sample size, as it increases the accuracy of our research results.
- Consult credible sources, for secondary data collection.
V. How do we manage our research data?
Given that research data has a longer lifespan than the research itself; there is a need to properly manage our data through its lifecycle. Managing research data involves organizing data from the point of generation to the point of dissemination and documentation. It has several benefits, not only to us but also to other researchers within our domain of study.
Steps involved in managing our research data include:
- Identify the purpose for which the data is sourced.
- Organize data as they grow in size.
- Create a metadata for sourced data.
- Proper labeling of data files for easy identification.
- Always backup your research data either online or offline.
- Use the right tools to analyze your data.
- Secure your data, it is an asset.
Reasons why we need to manage our research data include:
- Increase transparency and accessibility.
- Enable reusability.
- Reduce risk of data loss.
- Improve the research integrity of home institution.
- Avoid repetition of work, as a result of senseless collation of data.
- Easily identify different versions of a given data.
- Increase efficiency in report writing.
- Enable collaboration.
- Ease of retrieval in personal files.
VI. Why research data?
Research data continues to play important roles in scientific study and a few of its advantages have been highlighted:
- Improves the quality of human life in general.
- It transforms to well-informed knowledge.
- Provides indisputable evidence.
- Proffer solutions to problems.
- Reduces uncertainty in decision and policy making.
- An objective way to keep track of progress in academic and industry.
- Serves as a catalyst for societal change.
- Influences the quality of our research.
Research data is precious to scientific study, and as Daniel Keys Moran rightly said “You can have data without information, but you cannot have information without data.” So, as female researchers, we are encouraged to pay more attention to our research data, as this will enable us make cutting edge impact in our scientific world.
Dunie, M. (2017). The Importance of Research Data Management: The Value of Electronic Laboratory Notebooks in the Management of Data Integrity and Data Availability. 355 – 359
Whyte, A., Tedds, J. (2011). Making the Case for Research Data Management. Digital Curation Centre. Briefing Papers. Edinburgh.
About the author
Department of Computer Science,
Faculty of Science,
University of Port Harcourt,
ResearchGate: Linda Oghenekaro
Linkedln: Linda Oghenekaro