regression to the mean


Also found in: Dictionary, Thesaurus, Financial, Acronyms.

regression to the mean

The likelihood that over time probable events will occur and a normal distribution of events rather than that rare, unlikely, or unusual events will unfold.
References in periodicals archive ?
One of the most salient threats to the validity of competitive effects estimates in a failing schools voucher program is regression to the mean. Chakrabarti (2007a) suggests that the best test for regression to the mean is to analyze the preprogram trends of to-be-treated and to-be-controlled groups, in other words, the performance trends of treated schools and nontreated schools are compared in the period before the program took effect.
If errors of measurement were the only factor that contributed to regression to the mean, no additional regression should occur after the first retest.
While worsening performance among high-performing nursing homes and improving performance among low-performing nursing homes may seem consistent with regression to the mean, these changes were observed in P4P states above and beyond any changes that occurred in comparator states or any changes that occurred prior to the implementation of P4P that could be attributed to regression to the mean in comparator states and were not seen when using an earlier, false P4P implementation date.
With quasi-experimental pre-post designs, regression to the mean can still limit study findings, particularly when baseline group differences exist.
Regression to the mean. In: A New View of Statistics.
The lower effect size was expected because the RD design is robust to regression to the mean (a likely source of inflated impact in the pretest-posttest design given that only children with very high SAB use were enrolled in the intervention).
Regression to the mean exerts its influence not only on goals but also on everything else that happens in a football match - bookings, corners, throw-ins, goal-kicks, even the result itself.
Regression to the mean was considered as a possible concern affecting our expenditure results.
But for preventable hospitalization rates at the zip code level, regression to the mean does not appear to take place at all.
After allowing for our old friend regression to the mean, it could be contended that the goals expectation for this evening's fixture should be around 2.6 - a figure which is tucked inside every market-maker's band.
Second, if people make enrollment decisions based in part on the transitor y portion of health expenditures, especially if they consider only one year's prior utilization, then there may be a problem of regression to the mean, in which people with artificially low expenditures will enroll in HMOs in the next period.
The phenomenon known as regression to the mean will probably account for at least two of these three figures rising between now and next May.