Data in the MMWR
Adjustment (5 of 12)
Posted to LinkedIn on 2026-01-13. The text below is the post as published.
Links to works now on this site point to their pages here; the words are as published. Where the post showed a web address, the icon stands in for it (hover over it to see the address as posted).
Data in the MMWR (§5.4): Adjust quantities: standardization and regression models On this site (opens in a new tab)
[2026-01-13]
Principles: Standardization methods should indicate the reference population or distribution used for standardization. Each type of regression model should be sufficiently described and justified. Details might include model form and family (e.g., linear, logistic, loglinear; Gaussian, Poisson, negative binomial), curve types (e.g., linear, segmented, fractional polynomials), and extensions to handle correlation.
Observations: Many reports in this review standardize mortality and other measures to the age distribution of the 2000 Census (based on a 1999 HHS policy). In contrast, one report standardized to each of 11 specific years, and another report standardized to an internal distribution, called direct standardization. A large proportion of reports present regression models. Reports generally adequately describe both unadjusted values and values that are standardized or adjusted through a regression model.
Recommendations: When standardizing ratios or rates, the reference population should be stated and justified explicitly. Describe how continuous predictors are included, including functional form (such as cutpoints) and methods for detecting linearity and nonlinearity. Describe efforts to select models through iteratively adding or removing predictor terms, and describe the implications for interpreting results. Important model parameters should be interpreted correctly and in context. Focus on the main association of interest. Annual percent change (APC) and its variants can be calculated empirically or from a loglinear regression model. Therefore, when an APC is reported, the method for calculating it should also be stated.
Next topic: Draw conclusions under incomplete information (§5.5)
Data in the MMWR
- Introduction · How learners read
- 1 · Sources
- 2 · Methods
- 3 · Description
- 4 · Comparison
- 5 · Adjustment (this post)
- 6 · Conclusions
- 7 · Tables
- 8 · Figures
- 9 · Interpretation
- 10 · Impact
- 11 · Context
- 12 · Additional practices