An official website of the United States government.

This is not the current EPA website. To navigate to the current EPA website, please go to This website is historical material reflecting the EPA website as it existed on January 19, 2021. This website is no longer updated and links to external websites and some internal pages may not work. More information »

Using Professional Judgment to Develop a Sampling Design

Using professional judgment does not mean you must take judgmental samples. Implementation of a judgmental sampling design should not be confused with the application of professional judgment (or the use of professional knowledge of the study site or process). Professional judgment should always be used to develop an efficient sampling design, whether that design is judgmental or probability-based. For more information on when to use judgmental sampling or a probabilistic sampling design, see Selecting a Sampling Design.

Merits of Judgmental vs. Probabilistic Sampling

Judgmental Sampling Probabilistic Sampling
Selection of samples based on 
professional judgment and prior information
Selection of samples has a random component and may incorporate professional judgment and prior information
Should only be used to take a few samples (making it less expensive) Needs an adequate number of samples to support performance objectives (making it more expensive)
Can be cost-effective with expert knowledge Can be cost-effective with expert knowledge
Cannot reliably evaluate precision of estimates – does not allow the level of confidence in the results to be accurately quantified Can evaluate precision of estimates – allows the level of confidence of the investigation to be accurately quantified
Personal judgment is used to interpret data relative to study objectives Statistical inference is used to draw inferences from the data to the entire area/process.
Results are biased Protects against bias
Easy to implement Can be complicated to implement both in selecting samples and performing computations
Useful for emergency situations that need immediate sampling Useful for situations where the level of confidence of the final result should be accurately quantified.