Related Experiment Video
Updated: Aug 26, 2026

Assessment of Child Anthropometry in a Large Epidemiologic Study
Published on: February 2, 2017
Good measurement for good improvement work
Eugene C Nelson1, Mark E Splaine, Stephen K Plume
1Dartmouth Medical School, Lebanon, NH, USA. eugene.c.nelson@hitchcock.org
Purpose:
To provide guidance on using measurement to support the conduct of local quality improvement projects that will strengthen the evaluation of results and increase their potential for publication.
Target Group:
Individuals leading quality improvement efforts who wish to enhance their use of measurement.
Procedures To Promote Good Measurement:
Eleven procedures are offered to promote intelligent measurement in quality improvement research that may become publishable: 1. Start with an important topic 2. Develop a clear aim statement 3. Turn the aim statement into key questions 4. Develop a theory about causes and effects, process changes and predictable sources of variation 5. Construct a research design and accompanying dummy data displays to answer your primary research questions 6. Develop and use operational definitions for each variable needed to make your dummy data displays 7. Design a data collection plan to gather information on each variable that will enable you to generate reliable, valid, and sensitive measures related to each research question 8. Pilot test the data collection plan, construct preliminary data displays, and revise your methods based on what you learn 9. Stay close to the data collection process as the data plan goes from idea to execution 10. Perform data analysis and display results in a way that answers your key questions. 11. Review and document the strengths and limitations of your measurement work and use this knowledge to guide intelligent interpretation of the observed results.
Related Concept Videos
Accuracy and Precision
Quality Assurance
Measurement: Standard Units
Measurement: Derived Units
Uncertainty in Measurement: Accuracy and Precision
Testing a Claim about Standard Deviation
The hypothesis testing for the claim of population standard deviation (or variance) requires the data and samples to be random and unbiased. The population distribution also must be normal. There is no specific requirement on the sample size as the estimation is based on the chi-square distribution.
As a first step, the hypothesis (null and alternative) concerning the claim about...