Finding a good, available data source is typically harder than it sounds. In this video, learn where to look for publicly available data sets that fit your budget and timing.
- [Instructor] One of the biggest challenges … to being able to find good data … to be used in models and algorithms is availability. … The availability of data can include everything … from not being able to gain access to the information, … to the information not even existing … because the data is not being collected. … If data is not available, then of course … it is not usable within a model or an algorithm. … The availability of data … may also be restricted for legal purposes. … For instance, in cases where there's … personal identifiable information for patients and clients, … that information may not be released to the public … in order to protect their privacy. … Although data at the county, state, and federal level … is not as detailed or granular as patient information, … models typically will take patient-level data … and aggregate it into a population study. … Hence, in most cases, … when we look at populations and patterns of behaviors, … we rarely need the individual-level data …
This course was created by Madecraft. We are pleased to host this content in our library.
- Identifying high-quality data sources
- Evaluating data usability, accuracy, and more
- COVID-19 data sources
- Challenges and takeaways