Fig. 2
From: Addressing health disparities using multiply imputed injury surveillance data
Analyzing missing data patterns of NEISS-AIPa 2018 data: A. Bar chart of unweighted counts and proportions for both missing and non-missing datab; B. The Venn diagram for presenting the missing data patternsb. Note: A (Age) and S (Sex) overlay in Fig. 2B and represent small population sizes. A and S both intersect with P (CAUSE) and R (RACE). D (DISP) represents a small population size, and it intersects with L (LOC) only.aNEISS-AIP: National Electronic Injury Surveillance Systems-All Injury Program. bLOC (L): location where the injury occurred. RACE (R): race and ethnicity of patient. CAUSE (P): external cause of injury. BDYPT (B): primary body part affected. TYPE (T): work-relatedness. AGE (A): patient age in year. DISP (D): disposition at emergency department discharge. SEX (S): gender of patient