Hypothesis Tests for Continuous Audiometric Threshold Data.
Zechen Liu, Zhuoran Wei, Jiaxuan Li and 3 others
PMID 38538557WHAT IT FOUND
For hearing-threshold studies, using both ears together in one analysis was less likely to wrongly find or miss associations than using one ear or separate frequency tests.
The simulation and real-data example supported this approach.
Key findings
01In the simulation without an ear-level confounder, the both-ear analysis that included all frequencies in one model and the average-ear analysis performed better than worse-ear, better-ear, left-ear, and separate-frequency analyses.
02In the simulation with an ear-level confounder, the both-ear analysis performed best, while worse-ear and better-ear tests wrongly found associations too often.
03In the CHEARS example, the overall diet-threshold association met or nearly met the usual evidence threshold with the both-ear and average-ear methods, but not with the left- or right-ear methods.
STILL TO COME
How it was doneWhat they found
Read the rest of this summary
You get three full summaries a month, free, and we do not ask for a card. Search, the TL;DRs and your library stay unlimited either way.
What it does not show
The main comparison is based on simulated data, so the exact error rates and detection abilities depend on the chosen correlations, effect sizes, and sample sizes. The paper states that the abilities to detect a true association shown in the tables may not generalize to different scenarios. Small samples of 200 produced rates of wrongly finding an association when none existed of 7.8 to 12.4% and low ability to detect a true association. The CHEARS analysis is an observational illustration of methods, not a test of whether changing diet helps hearing. The paper does not report clinical patient outcomes or therapy effects.
Declared interests
The supplied metadata lists NIH extramural research support. No author conflict-of-interest declaration appears in the supplied text.
The easy way to misread this
Do not read the diet-threshold result as evidence that diet changes hearing. It was an illustration of analysis methods, and the overall association met or nearly met the usual evidence threshold only with some methods. The paper does not test whether changing diet helps patients.