Data Analytics
Identifying Data Needs
As you begin your investigation into your research project it's important to think about what data you think you will need and the sources where you might find this data. An advantage of being a university student is that you have a wealth of information at your fingertips. You may want to find a research article where the authors have done a similar study and examine the data sources they used in the process of writing the article. Reading such research articles can also provide you an idea if your research topic is adequately focused or if the topic might be to broad to treat in one paper.
Where to find data
As you consider which data sources you need you may have to be flexible in how you approach finding data. For example, you may want to find employee satisfaction at a specific company after moving to a four-day work week. Data from that company might not be available, however, research might have been done about four-day work weeks, flexible schedules, or non-traditional work weeks. You may have to consider these outside sources as you approach your research question:
- Other Researchers - look through our article databases or the Research a Topic tab for this information.
- Government Data - think U.S. Census, federal, and local agencies
- Organization/Association Data - Non-profit centers, foundations, trade associations, and advocacy groups
- Data Repositories - Researchers, government agencies, universities, etc.
- [See Sources for Data Sets tab for other specific sources]
Types of data
Quantitative Data - generally refers to observations that are represented in numerical form. Examples include program funding level (in dollars), clients’ ages, number of hours of services received, and children's standardized test scores. All of these can be expressed as numbers, as amounts, or as degrees; that is, as quantitative data. Quantitative data can be analyzed with statistics, both descriptive and inferential. (Chua & Mark, 2005)
Qualitative Data - Qualitative data is the general term given to evidence that is text based rather than numeric in representation. These kinds of data result from interviews (group, individual, focus, and so on), observations (more typically unstructured but also structured), and documents (both formal, such as mission statements, as well as informal, such as letters) that may be analyzed from a variety of perspectives. The distinction between qualitative and quantitative data is somewhat arbitrary because all evidence has dimensions of both. (Chua & Mark, 2005)
Longitudinal Data - Present information about what happened to a set of research units (such as people, business firms, nations, cars, etc.) during a series of time points. The participants in a typical longitudinal study are asked to provide information about their behavior and attitudes regarding the issues of interest at a number of separate occasions in time (also called the ‘phases’ or ‘waves’ of the study). (Taris, 2000)
Cross-sectional Data - Refer to the situation at one particular point in time. (Taris, 2000)
Reference List
Chua, P. & Mark, M.M. (2005). Quantitative Data. In S. Mathison (Ed.) Encyclopedia of Evaluation. : SAGE Publications Ltd doi: 10.4135/9781412950558.n461
Taris, T. W. (2000). Longitudinal data and longitudinal designs. In Taris, T. W. (Ed.) A primer in longitudinal data analysis (pp. 1-16). : SAGE Publications Ltd doi: 10.4135/9781849208512
Further Reading
The electronic book below is a great primer for understanding data needs. Includes case studies and examples showing how companies use data for improved decision making (see also: Research a Topic tab on this guide):
Data Strategy by
Data can be a cost for some organizations, but for those who succeed, it is a way to drive profitability, customer loyalty, and outperform others in their field. A well thought out, fit-for-purpose data strategy is vital for every modern data-driven organisation - public or private sector. This book is your essential guide to planning, developing and implementing a data strategy, presenting a framework which takes you from strategy definition to successful strategy delivery and execution with support and engagement from stakeholders. It covers vital topics such as data-driven business transformation, change enablers, benefits realisation and measurement. Written by an experienced practitioner with over 30 years in the field, this book guides the reader through the complexity of working across an organisation to achieve a successful outcome. Whether you're just starting to consider a data strategy or are looking to improve your existing approach, this book is a valuable resource for any modern data-driven organization. Offers a structured guide for those embarking on a data strategy from definition to a successful implementation. Incorporates insights from a model that has been developed through a highly successful workshop delivered to many practitioners across the globe. Provides case studies, example scenarios and reader questions throughout the book are designed to stimulate real-world thinking and help you put the framework into practice in the context of your own organisation.
ISBN: 9781780175430Publication Date: 2021-08-23
SAGE Research Methods
Check out the SAGE Research Methods Database for in-depth explanations of data types and collection methods.
- SAGE Research Methods This link opens in a new windowAn award-winning tool designed to help you create research projects and understand the methods behind them. See the Help - Sage Research Methods page for help using the platform.
