Last week, with much fanfare, a study comparing standardized test scores of New Jersey's charter school students to those of their public school peers was released by the Center for Research on Education Outcomes CREDOO).
We assessed covariate balance by comparing propensity adjusted standardized differences between patients in the pre-intervention and post-intervention groups (<10% indicates good balance).
We performed subgroup analyses, separately for superiority and noninferiority trials, comparing the standardized differences according to various study characteristics using t tests or one-way analysis of variance.
Baseline characteristics were compared using standardized differences, which is better at identifying meaningful differences between very large groups than traditional hypothesis tests; a standardized difference >10% was considered an important difference.
Using Cohen's d to compare the standardized differences and interpreted the effect sizes as follows:.2 small,.5 medium, and.8 large.
The standardized density of cycE in the mock SK-BR3 warbitrarilyily set at 100%, and the relative level of cycE in other samples was obtained by comparing those standardized densities of cycE to that of cycE in the mock SK-BR3.
The balance of covariates was measured by their standardized differences.
We assessed the appropriateness of our propensity score matching by using standardized differences for continuous variables and differences for non-continuous variables as recommended by Austin [ 48].
Fig. 2 Covariates balances as measured by standardized differences across groups exposed or not to ARDS risk factors.
Covariate balance after the IPTW weighting was assessed by computing their standardized differences, and groups were considered balanced if the standardized differences of all covariates were < 0.25 [ 24] and no further adjustment was required for the outcome analysis.
