The conclusion is that, unless qualitatively different phenomena occur for patients with high %TBSA, the degree of accuracy of the model parameter estimates rules out any large increase in the rate of misclassification.
However, policies designed to protect the economy against the worst-case consequences of misspecified dynamics are less aggressive and turn out to be good approximations of the estimated rule.
To identify potential confounding, we used a "10% change in the estimate" rule [ 24].
As noted in Table 1, this estimate "rule" could not be applied to either device.
We used the 10% change in estimate rule to evaluate confounding by comparing the crude odds ratio with the odds ratio adjusted for each potential confounder individually.
23 Other confounders were identified by the 'change-in-estimate' rule of thumb; 24 25 we required only a relatively small 5% change as effect estimates were expected to be small.
Based on findings from previous studies and the 10% change-in-estimate rule, we included participants' age, participants' age of first intercourse, participants' lifetime smoking, husbands' lifetime smoking and condom use in multivariable models.
Potential confounding by the risk factors listed in Table 1 was determined by comparing the unadjusted model for the exposure variable that included only those with complete data on the risk factor with the model adjusted for the risk factor using a 10%% change in the estimate rule [ 29].
Good-faith estimate rules, part of a tougher Truth in Lending Act that emerged from the mortgage crisis, mean that lenders must provide a clear picture of the costs involved in buying or refinancing a home.
The good-faith-estimate rules say that certain charges cannot increase at closing, including those for loan origination and points paid to the lender to reduce a locked interest rate, with 1 point equal to 1 percent of the loan amount.
