Are the NRI Scales Validated?

We love talking about our proprietary suite of psychometric measurement instruments! 

These tools were developed to far exceed recommendations in the FDA's guidance on the use of Patient Reported Outcome Measures (PROMs) for the substantiation of labeling claims. The scale contains a combination of subjective and objective data which are aggregated to produce total scores on each of the relevant subdomains. 

Each of our measures are validated and norm-referenced in a population of healthy adult females. Our development priorities include elimination of floor or ceiling effects in this priority population as well as ensuring that each domain has highly precise sensitivity to change. 

Our scales were developed and pilot tested with focus groups and qualitative research to ensure face and content validity. They were then tested for psychometric properties using confirmatory factor analysis and item response theory. Internal reliability was determined via Cronbach's alpha. 

Our subscales have Cronbach's alpha scores ranging from .82 to .90, which is an ideal range for both exceeding minimum standards for internal reliability while avoiding redundancy and participant burden. 

Confirmatory factor analysis confirmed that each subscale measures a single latent factor, with each subscale contributing to broad latent factors. Factor loadings were all below 0.5, SRMRs were below 0.8, and coefficient of determinations were above 0.8. 

In item response theory testing using graded response modeling, each item in the final version of the scale was found to be highly discriminating with IRT discrimination (trait) parameters all above 1.5 and over 50% of item trait parameters above 2.0. Difficulty parameters and test information curves identified that the test is most reliable within +/- 1.5 standard deviations of the mean.

Practically speaking, this means that these tests are calibrated to identify improvements to symptoms among an average American female adult population and are capable of identifying changes that go both above and below the norm. This ensures that our measures capture the totality of your product's effects on each relevant subdomain.