In addition to this previous experience with explanatory variables, our approach to identifying confounders was reinforced with bivariate analyses which show strong association between explanatory variables and health measures.
In a previous study the explanatory models for pain and disability included other personal factors as valid predictors of outcome, although the odds were low [ 24].
To quantify the causal relationship between the land surface temperature and explanatory variables, previous empirical studies have been used regression approaches such as simple regression and spatial regression approaches [19, 20, 26] and correlation analysis [18].
Although it is evident that aging-related mortality patterns among blacks were different from those of whites, previous studies provided no explanatory framework for understanding these distinctions.
Among explanatory variables, previous history of piercing with sharp materials (AOR = 3.0, 95% CI 1.17-7.80) and history of abortion (AOR = 6.6, 95% CI 2.50-17.71) were significantly associated with HIV infection.
Third, previous studies showed that explanatory abilities of the ACG-based morbidities were quite good for the same-year and next-year ambulatory visits and costs but not as good for inpatient costs in Taiwan [ 20, 21].
While previous cost displays high explanatory power, it is strongly influenced by factors other than healthcare needs [ 32, 33] and, except when used as a complement to clinical variables, it does not enable the identification of target populations.
Additional neighbourhood factors in the hospital's catchment area such as education, home prices, age distribution and race/ethnicity breakdown may influence charges, but were not included in our regression due to absence from previous literature on potential explanatory factors in charge setting, 4 7 11 14 on which we based our decisions of which variables to include.
It also helps to distinguish between models because it provides an ecologically sound, plausible historical narrative that tries to link ecological/selective causations with cell biological changes and, as a whole theory, can compete with previous models in its explanatory power (see also the section on historical narratives in my reply to Igor Zhulin).
Secondly, the test for internal impact: the explained variable is CAR; the explanatory variables are Previous Pollution Control, Previous CSR performance; and the control variables are Market, Industry, Size, Ownership, ROE and PE.
The inclusion of dummies for the education-occupation mismatch in the home country along with covariates typically used in previous studies almost doubles the explanatory power of a probit model for over-education and almost quadruples that for under-education.
