Skip to Main Content
UMass Chan Medical School, Lamar Soutter Library. Education. Research. Health Care. Empowering the future. Preserving the past.
UMass Chan Medical School Homepage Lamar Soutter Library Homepage

Analysis-Ready Data Sets Tutorial

Step by step tutorial on how to make your data analysis-ready using Excel or REDCap.

Standardization

Best Practices for Standardizing Data Sets

Standardization ensures that the data in a set is internally consistent. That is it ensures that the data is of the same kind and format for each data element that you are collecting.

Standardization helps to minimize data collection and analysis errors and prevents inconsistencies.

  1. Data should be coded harmoniously
    If data is coded as “no” = 0 and “yes” = 1, then all yes/no questions should use that same coding scheme.
  2. Standardize free text into categorical data
    Whenever possible, free  text should be standardized into categorical data. Rather than asking an open-ended question, ask questions with controlled choices.
  3. Treat date and time data consistently
    Choose one date format and employ that standard throughout all of your date fields using active validation. (ie: YYYY-MM-DD)