Validity

As explained in Data Without Labels

Validity is the degree to which data conforms to the properties, characteristics, scope, and variations required by its use case.

Validity measures whether data conforms to the properties, characteristics, scope, and variations required by its use case. It asks whether captured observations and measurements are reliable for the analysis being performed. section 1.2.3

Scope check

If a study covers 2015–2019, including 2014 data is invalid because the observation falls outside the defined scope. section 1.2.3

Assess validity alongside other data-quality attributes:

• Check that observations match the use case's required properties, characteristics, and variations. section 1.2.3
• Separate validity from completeness, which concerns missing values, and accuracy, which concerns correctness. section 1.2.3

Figure 1.5 Data quality is of paramount importance; attributes of good-quality data are shown.

Use the data-quality overview to compare validity with completeness, accuracy, representativeness, and availability. section 1.2.3

How Data Without Labels covers it

How deep it goes

Defines conformance and gives a scope-based example, but stops short of procedural validation checks or implementation details.

Examples

Uses a 2015–2019 study that incorrectly includes 2014 data to demonstrate invalid scope.

What it assumes

Assumes a defined use case, scope, properties, characteristics, and variations against which data can be compared.

What you can do after

Evaluate whether observations and measurements conform to a use case's defined scope and required characteristics.

How it connects

Connects validity with data quality, completeness, accuracy, representativeness, availability, observations, and measurements.

liveBookmanning.com

Read Data Without Labels on liveBook Get the book at manning.com

Also explained in

• 

  liveBookmanning.com
  Effective Data AnalysisValidity is the degree to which a measure accurately represents or supports conclusions about the construct it is intended to measure.

Compare how 2 books explain validity →

Related concepts

• data qualitypart of · Data quality is the degree to which data is accurate, complete, consistent, relevant, and suitable for its intended use.
• criterion validityincludes · Criterion validity is the degree to which a measure is associated with an external criterion representing an established measure or outcome of interest.
• content validityincludes · Content validity is the degree to which a measure comprehensively captures all relevant facets of the concept or process it is intended to measure.
• discriminant validityincludes · Discriminant validity is the degree to which a measure is not associated with measures of theoretically unrelated constructs.
• convergent validityincludes · Convergent validity is the degree to which a measure is associated with other measures that theoretically assess the same construct.

This explainer was generated by Manning's knowledge graph from the text of Data Without Labels. The section links point to the parts of the book it draws on.