Secondary data sources: social networks, data from governments, non governmental organisation, industrials (this data request specific authorisation to use, can have a cost), diverse associations
Secondary Data Methods: Data wrangling, all process to use data ethically (request ethical approval, risk assessment, anonymisation), data linkage, data cleaning and preparation dependent on the research question(s) (e.g., outliers and missing values management, data reduction, some transformations): the most important stages, application of machine learning technics selecting the more appropriate model
Secondary data methods refer to the techniques used to collect and analyze data that has already been collected by someone else for a different purpose. These methods are commonly employed in research and analysis to complement primary data collection efforts or to answer research questions that can be addressed using existing data.
It is important to note that while secondary data sources offer convenience and cost savings, they may have limitations such as data quality, relevance to the research question, and potential biases. Researchers need to critically evaluate and validate the secondary data sources before using them in their analysis.
Rahul Jain While secondary data sources are convenient and cost-effective, they may have constraints such as data quality, relevance to the study issue, and potential biases as a researcher. Before incorporating secondary data sources in your analysis, researchers must rigorously assess and validate them.
Secondary data methods and sources are invaluable tools for researchers, analysts, and decision-makers across various fields. By effectively leveraging existing data, they can gain insights, save resources, and make more informed decisions.