# Visualize Prevalence Estimates Visualize prevalence estimates for calibration or outcome variables using different weighting methods. ```r plot_prevalence(df, mean, mean_se, method, cal_vars, cal_levels) ``` ## Arguments - `df`: data.frame with representative sample - `mean`: character name of mean prevalence estimate variable - `mean_se`: character name of mean prevalence estimate variable - `method`: character name of the weighting method variable - `cal_vars`: character name of the variable with calibration variable names - `cal_levels`: character name of the variable with calibration variable levels ## Returns ggplot object ## Details Specify columns and weighting methodologies of interest to visualize. ## Examples ```r library(dplyr) library(stringr) # Prepare the NHIS data calVars <- c( "SEX_A_R", "AGEP_A_R", "HISPALLP_A_R", "ORIENT_A_R", "HICOV_A_R", "EDUCP_A_R", "REGION_R", "EMPLASTWK_A_R", "HOUTENURE_A_R", "MARITAL_A_R" ) stuVars <- "DIBTYPE_A_R" vars_dummies <- c("AGEP_A_R","HISPALLP_A_R","EDUCP_A_R","REGION_R") nhis_keep_vars <- c("PPSU","PSTRAT","WTFA_A") nhis_imputed <- impute_data(nhis_processed, c(calVars, stuVars), nhis_keep_vars) nhis_dummied <- dummies(nhis_imputed, vars=paste0(vars_dummies, '_I')) factor_vars <- setdiff(names(nhis_dummied), nhis_keep_vars) nhis_dummied[factor_vars] <- lapply(nhis_dummied[factor_vars], as.factor) # Prepare the synthetic All of Us data aou_imputed <- impute_data(aou_synthetic, c(calVars, stuVars)) aou_dummied <- dummies(aou_imputed, vars=paste0(vars_dummies, '_I')) aou_dummied[] <- lapply(aou_dummied, as.factor) # Calculate IPW weights using NHIS data and applied to All of Us weights_df <- calculate_weights( nhis_dummied, aou_dummied, 'ipw', paste0(calVars, '_I'), paste0(stuVars, '_I'), weight='WTFA_A', strata='PSTRAT', psu='PPSU' ) # Get IPW results by group ipw_outcome_df <- summarize_results_by_group( weights_df, paste0(stuVars, '_I'), paste0(calVars, '_I'), weight_col='ipw_weight', label='AoU: IPW' ) # Process data prior to plotting to make labels more readable plot_df <- ipw_outcome_df %>% mutate( Name = case_when( group_var == 'SEX_A_R_I' & level_var == 1 ~ 'Sex: Male', group_var == 'SEX_A_R_I' & level_var == 0 ~ 'Sex: Female', group_var == 'AGEP_A_R_I1' & level_var == 1 ~ 'Age: 18-29', group_var == 'AGEP_A_R_I2' & level_var == 1 ~ 'Age: 30-39', group_var == 'AGEP_A_R_I3' & level_var == 1 ~ 'Age: 40-49', group_var == 'AGEP_A_R_I4' & level_var == 1 ~ 'Age: 50-59', group_var == 'AGEP_A_R_I5' & level_var == 1 ~ 'Age: 60-69', group_var == 'AGEP_A_R_I6' & level_var == 1 ~ 'Age: 70+', group_var == 'HISPALLP_A_R_I1' & level_var == 1 ~ 'Race/Eth: Hispanic', group_var == 'HISPALLP_A_R_I2' & level_var == 1 ~ 'Race/Eth: White', group_var == 'HISPALLP_A_R_I3' & level_var == 1 ~ 'Race/Eth: Black', group_var == 'HISPALLP_A_R_I4' & level_var == 1 ~ 'Race/Eth: Other', TRUE ~ group_var ) ) %>% filter(str_detect(group_var, "SEX|AGEP|HISPALLP")) %>% filter(!str_detect(Name, "_")) %>% mutate( condition = case_when( outcome_var == 'DIBTYPE_A_R_I' ~ "Diabetes" ), VAR = case_when( str_detect(group_var, "SEX") ~ "Sex", str_detect(group_var, "AGE") ~ "Age", str_detect(group_var, "HISPALL") ~ "Race", str_detect(group_var, "EDUC") ~ "Educ" ) ) # Plot plot_prevalence( plot_df, 'WMEAN', 'SEMEAN', 'Method', 'VAR', 'Name' ) ```

plot_prevalence function