Unit 2. Data Sources

Selecting, understanding, and utilizing data sources is a critical step in the data analysis process. After determining a research problem, selecting a data source is generally the next step in an analysis. In this Unit, we will discuss key features and attributes of commonly used health data sources relevant to public health. We will in particular focus on health equity challenges and how to address these concerns.

Health Equity and Data Sources

Health data sources may have particular biases or other disadvantages that should be recognized and addressed when conducting a health analytics project. In this unit, we review commonly used data sources in terms of the potential for bias. More extensive treatment of bias in analytic methods can be found in subsequent units.

In this unit, we will cover five types of health data sources that may be generated outside of public health but utilized by public health researchers to address questions of importance. We do not focus on case reports, surveillance data, or other content generated specifically by public health entities. Instead, our goal is to familiarize public health researchers with data sources that may be less familiar and thus more challenging to address from a health equity perspective.

Lessons:

• Electronic Health Records

• Claims Data

• Social Media Data

• Survey Data

• Geospatial Data