Statistics and Data for Health

Note: credit to Will Dean for this information.

Raw Data vs. Statistics

Before diving into the data access options available from the CDC, first consider what kind of data you are looking for: raw data or statistics. 

Raw Data

• Raw data is unprocessed or mostly unprocessed data collected by researchers and is not usually interpretable without statistical analysis.

  • Raw data will likely have variable names that are not human readable and need to be decoded by a data dictionary or guide, and the data will need to be weighted correctly during analysis.
  • Raw data may include different demographic populations and variables in the same dataset, such as adults aged 18-24 in Bergan County, NJ who were injured by a vehicle, or Native Americans living in North Dakota who were injured at work. If you plan on doing your own statistical analysis of data, using SAS, SPSS, R or another statistical software, you should look for raw data.

Statistics

• Statistics are processed data derived from raw data and are usually presented in a human readable format.
  • Statistics are already weighted and can be used as is in a research paper by displaying a table of variables and values, or quoting a statistic, like “During August 2020–February 2021, the percentage of adults with recent symptoms of an anxiety or a depressive disorder increased from 36.4% to 41.5%.” (Vahratian A, Blumberg SJ, Terlizzi EP, Schiller JS. Symptoms of Anxiety or Depressive Disorder and Use of Mental Health Care Among Adults During the COVID-19 Pandemic — United States, August 2020–February 2021. MMWR Morb Mortal Wkly Rep 2021;70:490–494. DOI: http://dx.doi.org/10.15585/mmwr.mm7013e2)

Citing can be a challenge when looking at the variety of sources and formats that statistical information comes in. Here are a few helpful sources.

Citing National Center for Health Statistics (NCHS)

New resources or hot topics.