1. end+disparities Learning Exchange Part IV: Calculator Assumptions

2. Quick Review
This presentation is the fourth in a series of presentations intended to familiarize you with disparities calculation
Part I: Disparity, a National Priority
Part II: Subpopulations
Part III: Calculating Disparity
Part IV: YOU ARE HERE!
Part V: Selecting QI Projects

3. "All human beings are born free and equal in dignity and rights
"All human beings are born free and equal in dignity and rights." - United Nations, Article 1 of the Universal Declaration of Human Rights

4. Learning Objectives
Describe how was the calculator methodology developed
Understand the assumptions made within the calculator tool

5. Supreme Court of the United States
Statisticians and scientists disagree on how to calculate disparities – there are many methods
The most uniform method for calculating and interpreting disparities comes from SCOTUS
SCOTUS has decades of history dealing with disparities in case law called Disparate Impact
Housing
Employment
Jury Selection, etc.

6. NQC Guide: Qualifying Disparities in HIV Care
Overviews
What is a disparity?
How do we qualify disparities statistically?
How do we intersect probability and impact for disparity work?
Mathematical backgrounds and calculation walkthroughs
Absolute Disparity
Rate Ratio
Comparative Disparity
Odds Ratio
Absolute Impact

7. NQC Guide: Qualifying Disparities in HIV Care Instructional Slides
Co-dissemination of Materials
Disparities analysis is a challenging task that can cause confusion or concern among users who are not adequately trained in how to use the tools for QI
NQC Guide + Instructional Slides + Calculator Tool = happy users

8. Examples in this Presentation
Throughout this presentation, we’ll use examples that involve hypothetical groups of people
African-American & Latina Women
MSM of Color
Youth (ages 13-24)
Transgender People

9. But First Things First…
Terminology used in disparities statistics:
Significance
Power
Confidence

10. Statistics for Disparities
Power – ability of a statistical test to identify an effect
We avoid discussing power in this tool, because it is not completely scientific
We simplify terminology and assumptions around power to focus on whether or not results are useful
The important thing to remember is that UNDEFINED RESULT is a product of low power among other statistical assumptions

11. Statistics for Disparities
Confidence Intervals: the lower and upper bounds of the range containing the true result with 95% confidence
If a confidence interval contains the value "1", the calculated result is not significant and should be ignored
Narrower confidence intervals signify lower standard error, wider intervals signify higher standard error
For our purposes, we are only interested in the confidence intervals that fall within the range of detectable disparities based on our assumptions

12. Probability Methods Absolute Disparity Method Relative Risk Method
The absolute difference in scores between two groups
Relative Risk Method
The ratio of the scores of two different groups divided into each other
Comparative Disparity Method
The relative risk minus 1 (method is used to highlight the work that has yet to be done and supportively frames the values in terms of need
Odds Ratio Method
A measure of association between a status (e.g., race) and an outcome (e.g., the number of patients achieving or not achieving VLS) based on odds.

13. Probability Method Limitations
Absolute Disparity Method
Limitation: measured scores all > 50%*
Relative Risk Method
Limitation: measured scores all < 80%*
Comparative Disparity Method
Odds Ratio Method
Limitation: additional calculations required and challenging to interpret (use as last resort)
* If these thresholds are not met, the method does not have adequate power to detect disparity

14. Why So Many Probability Methods?
All statistical methods have limitations
Completing all four probability methods increases the likelihood we will detect true disparities
At least one of the methods will always work (odds ratio), regardless of the limitations of the other methods
Applying all four methods in all cases allows for consistent analysis
The most “probable” disparity is the group with the greatest number of SIGNIFICANT results

15. Example
Let’s go back to our populations example, but let’s just look at two groups for simplicity’s sake!

16. 47% 53% of total of total Example
Assume you have 100 people total and that 47 of them are blue and 53 of them are yellow
47%
of total
53%
of total

17. Example
Now, let’s assume that some of the people are retained in HIV care and some are not

18. 83% 91% retained retained Example
39 of the 47 blue people are retained in care (83%)
48 of the 53 yellow people are retained in care (91%)
83%
retained
91%
retained

19. 83% 91% retained retained Example
Let’s walk through each of the probability calculations to see if there is a disparity in retention
83%
retained
91%
retained

20. “For to be free is not merely to cast off one’s chains, but to live in a way that respects and enhances the freedom of others.” - Nelson Mandela

21. Some Visual Cues to Help You
Power Slider
Reminds us of the power limitations of each method
Significance Slider
Reminds us of the significance thresholds of each method
50%
0.05
0.10 ∞

22. YES Absolute Disparity
Does the Absolute Disparity Method qualify a disparity?
Are all scores > 50%
Absolute Disparity is the difference between measured scores
In this method:
A difference 0% to 5% is a NO DISPARITY
A difference 5% to 10% is a MAYBE DISPARITY
A difference more than 10% is a YES DISPARITY
91% - 83% = 8%
8% falls between 5% and 10% so a MAYBE DISPARITY
YES
50% 0% 5%
10% ∞

23. NO Relative Risk Does Relative Risk Method Qualify Disparity?
Are all measured scores <80%
Relative Risk is the ratio between measured scores
In this method:
A result greater than is a NO DISPARITY
A ratio between 0.8 and is a MAYBE DISPARITY
A ratio less than 0.8 is a YES DISPARITY
83% ÷ 91% = 0.91
Measured scores >80% so method has UNDEFINED RESULT NO
80%
0.8
0.875 ∞

24. Comparative Disparity
Does Comparative Disparity Method quality a disparity?
Are measured scores <80%
Comparative Disparity is the Relative Risk minus 1
In this method:
Greater than is a NO DISPARITY
Between and -.02 is a MAYBE DISPARITY
Less than -0.2 is a YES DISPARITY
(83% ÷ 91%) - 1 =
Measured scores >80% so method has UNDEFINED RESULT NO
80% -∞
-0.2
-0.125 ∞

25. Odds Ratio
Odds ratios should be used as a last resort, because they can be challenging to interpret based on the math behind them
Odds ratios are produced through cross-multiplication
(39 * 5) ÷ (48 * 8) = 0.53
In this method:
Greater than 0.67 is a NO DISPARITY
Less than 0.67 is a YES DISPARITY
0.53 is less than 0.67so is a YES DISPARITY
YES NO
Blue People 39 8
Yellow People 48 5
0.67 ∞

26. Let’s Review Probability Method Findings
Absolute Disparity – MAYBE DISPARITY
Relative Risk – UNDEFINED RESULT
Comparative Disparity – UNDEFINED RESULT
Odds Ratio – YES DISPARITY
Based on the findings – there is very likely a real disparity between red and blue ball durability

27. The Calculator Does All Four Every Time!
All statistical methods have limitations
Completing all four probability methods increases the likelihood we will detect true disparities
At least one of the methods will always work (odds ratio), regardless of the limitations of the other methods
Applying all four methods in all cases allows for consistent analysis
The most “probable” disparity is the group with the greatest number of YES DISPARITY results

28. Determining Priorities for Disparities
FOCUS
AVOID

29. Impact Method Absolute Impact
Measures the number of lives that are affected if the performance is raised to match average performance
Multiply the absolute difference by the size of the population being assessed
Limitation: be aware whether the population being assessed is doing better or worse than the average

30. Absolute Impact Example
Absolute impact is the absolute disparity multiplied by the population size of focus (blue people in this case since their measured performance is lower).
Absolute Disparity is the difference between measured scores
91% - 83% = 8%
47 * 0.08 = 4 red balls
If blue people were retained in HIV care as well as yellow people are retained in HIV care, we would expect an additional 4 blue people of the original 47 to be retained in HIV care

31. Don’t Forget! The Tool Does This All For You!

32. Question & Answer
Additional disparities calculation and QI resources are available or

33. Ending disparities will end the HIV epidemic.

34. Next Steps
This presentation is the fourth in a series of presentations intended to familiarize you with disparities calculation
Part I: Disparity, a National Priority
Part II: Subpopulations
Part III: Calculating Disparity
Part IV: YOU ARE HERE!
Part V: Selecting QI Projects

35. Next Steps
Want to check out the NQC Disparities Calculator? Click this link and you’ll be taken there!
THIS WILL BECOME AN ICON LINKED TO CALCULATOR
Want to learn more about the NQC Guide on this topic? Click this link and you’ll be taken there!
THIS WILL BECOME AN ICON LINKED TO GUIDE

36. NationalQualityCenter.org Michael@NationalQualityCenter.org
NationalQualityCenter.org 36