Consequently, we implemented a propensity score matching method to reduce this bias 16 by first creating a propensity score to represent the relationship between multiple characteristics and the matching outcome: being in the prison group (treatments) or not (controls).
To address potential response bias issues, we will implement a propensity-based imputation methodology and pattern-mixture methods in a sensitivity analysis of the primary analyses described above.
Implementing a new right has opportunity costs.
Computational methods such as PREDITOP [ 2], PEOPLE [ 3], BEPITOPE [ 4] and BcePred [ 5] implemented a variety of physicochemical propensity scales, such as hydrophilicity, flexibility or solvent accessibility, in their prediction models.
There are four approaches that are commonly used in implementing the propensity score (a) stratification on (hat{e}(Z)), (b) propensity score weighting, (c) optimal full matching, and (d) propensity score regression.
Table 2 shows the matched samples after implementing the propensity score matching method: 82% of the 6065 prison participants found a matching counterpart in the general population, resulting in a final sample of 9954 participants included in the analyses.
Still another approach to implementing the propensity score is based on weighting.
The third common approach for implementing the propensity score is based on the idea of statistical matching (see e.g. Hansen 2004; Hansen and Klopfer 2006; Rässler 2002; Rosenbaum 1989).
When implementing the propensity score matching for our two comparisons, we use kernel-based matching as developed in STATA package ATTK [ 17].
We therefore implemented a cluster analysis.
