### Last Updated July 21 2021 ### ### GOAL - Grab demographics, combine pre and post and get ####MCQ and Likert Scores from Data ### --------------------------------------------- #STEP 1. Combine Pre/Post data frames ##NOTE: we are already using the CLEANED pre (pre3) and post (post3), after having been ###cleaned via OpenRefine and R. Unnecessary columns have been removed, unwanted ###responses have been removed, module and total scores have been recalculated, ###post and pp have been matched. prepost<-bind_rows("pre" = pre3, "post" = post3, .id="test") #STEP 2. Want to match pre and post by prepost$student_email (removes duplicates) prepost2<-reshape(data=prepost, timevar="test", idvar="student_email", direction="wide") #### took the first record of pre, if there were two ### matched by e-mail rather than name, assuming e-mail is less likely to have typos #STEP 3. Remove duplicated columns which hold no information ### removed columns with endings ".post", ".pp.pre", ".post.pre" prepost3<-prepost2[,c(1:86, 378:583)] #STEP 4. remove any who do not have both a pre and post total score prepost4<-prepost3[!is.na(prepost3$total_score.pre)& !is.na(prepost3$total_score.post.post),] ## Saved this R object saveRDS(prepost4, "prepost4.RDS") ##to load again prepost4 <- readRDS("prepost4.RDS") #STEP 5. what is the earliest pre and last post? table(prepost4$form_date.1.pre) ##earliest pre = 10/4/2019 table(prepost4$form_date.1.post.post) ##lastest post = 10/23/2020 #STEP 6. Grab Demographics of PRE #Gender table(prepost4$gender.post.post) #Training Level table(prepost4$training_level.post.post) #Health Profession table(prepost4$profession_category.post.post) #country table(prepost4$country.post.post) #STEP 6a. Pre/Post Historgrams prepost4$total_diff<-prepost4$total_score.post.post-prepost4$total_score.pre install.packages("tidyverse") library(tidyverse) ggplot()+ geom_histogram(mapping = aes(x = prepost4$total_diff), data=prepost4) + facet_wrap(vars(gender.post.post)) ggplot()+ geom_histogram(mapping = aes(x = prepost4$total_diff), data=prepost4) + facet_wrap(vars(training_level.post.post)) ggplot()+ geom_histogram(mapping = aes(x = prepost4$total_diff), data=prepost4) + facet_wrap(vars(profession_category.post.post)) #STEP 6b. Pre/Post Box Plots table(prepost4$gender.post.post) prepost4$gender.post.post<-factor(prepost4$gender.post.post, levels=c("Female" ,"Male","Other"), labels=c("Female" ,"Male","Additional")) levels(prepost4$gender.post.post) ggplot()+ geom_boxplot(mapping = aes(x=gender.post.post, y = total_diff), data=prepost4)+ labs(y="Difference beween pre and post score", x="Gender") + theme(text = element_text(size=20)) ggplot()+ geom_boxplot(mapping = aes(as.character(x=profession_category.post.post), y = total_diff), data=prepost4)+ labs(y="Difference beween pre and post score", x="Health Profession")+ theme(text = element_text(size=20)) prepost4$training_level.post.post<-factor(prepost4$training_level.post.post, levels=c("Post-graduate (beyond 12 months of graduation)", "Post-graduate new provider (within 12 months of graduation)", "Pre-service Student"), labels=c("Post-grad > 12", "Post-grad < 12", "Pre-service")) prepost4$training_level.post.post<-factor(prepost4$training_level.post.post, levels=c("Pre-service", "Post-grad < 12","Post-grad > 12")) levels(prepost4$training_level.post.post) ggplot()+ geom_boxplot(mapping = aes(x=training_level.post.post, y = total_diff), data=prepost4)+ labs(y="Difference beween pre and post score", x="Training Level")+ theme(text = element_text(size=20)) #STEP 7. Mean Knowledge scores and Bivariate analysis, by total and module load("./Y1 (v2.0) data pulled 6.16.2021/prepost4.RDS") ##Total mean(prepost4$total_score.pre) sd(prepost4$total_score.pre, na.rm=TRUE) mean(prepost4$total_score.post.post) sd(prepost4$total_score.post.post, na.rm=TRUE) sd(prepost4$total_score.post.post-prepost4$total_score.pre, na.rm=TRUE) t.test(prepost4$total_score.post.post, prepost4$total_score.pre, data=prepost4, paired=TRUE) wilcox.test(prepost4$total_score.post.post,prepost4$total_score.pre, paired=TRUE, conf.int=TRUE) ##M1 mean(prepost4$m1_total_score.pre) mean(prepost4$m1_total_score.post.post) t.test(prepost4$m1_total_score.post.post, prepost4$m1_total_score.pre, data=prepost4, paired=TRUE) wilcox.test(prepost4$m1_total_score.post.post, prepost4$m1_total_score.pre, data=prepost4, paired=TRUE,conf.int=TRUE) sd(prepost4$m1_total_score.pre, na.rm=TRUE) sd(prepost4$m1_total_score.post.post, na.rm=TRUE) sd(prepost4$m1_total_score.post.post-prepost4$m1_total_score.pre, na.rm=TRUE) ##M3 mean(prepost4$m3_total_score.pre) mean(prepost4$m3_total_score.post.post) t.test(prepost4$m3_total_score.post.post, prepost4$m3_total_score.pre, data=prepost4, paired=TRUE) wilcox.test(prepost4$m3_total_score.post.post, prepost4$m3_total_score.pre, data=prepost4, paired=TRUE,conf.int=TRUE) sd(prepost4$m3_total_score.pre, na.rm=TRUE) sd(prepost4$m3_total_score.post.post, na.rm=TRUE) sd(prepost4$m3_total_score.post.post-prepost4$m3_total_score.pre, na.rm=TRUE) ##M4 mean(prepost4$m4_total_score.pre) mean(prepost4$m4_total_score.post.post) t.test(prepost4$m4_total_score.post.post, prepost4$m4_total_score.pre, data=prepost4, paired=TRUE) wilcox.test(prepost4$m4_total_score.post.post, prepost4$m4_total_score.pre, data=prepost4, paired=TRUE,conf.int=TRUE) sd(prepost4$m4_total_score.pre, na.rm=TRUE) sd(prepost4$m4_total_score.post.post, na.rm=TRUE) sd(prepost4$m4_total_score.post.post-prepost4$m4_total_score.pre, na.rm=TRUE) ##M17 mean(prepost4$m17_total__score.pre) mean(prepost4$m17_total__score.post.post) t.test(prepost4$m17_total__score.post.post, prepost4$m17_total__score.pre, data=prepost4, paired=TRUE) wilcox.test(prepost4$m17_total__score.post.post, prepost4$m17_total__score.pre, data=prepost4, paired=TRUE,conf.int=TRUE) sd(prepost4$m17_total__score.pre, na.rm=TRUE) sd(prepost4$m17_total__score.post.post, na.rm=TRUE) sd(prepost4$m17_total__score.post.post-prepost4$m17_total__score.pre, na.rm=TRUE) #STEP 8. Mean Knowledge scores and Bivariate analysis, by training level tapply(X=prepost4$total_score.pre, INDEX=prepost4$training_level.pre, FUN=mean) tapply(X=prepost4$total_score.post.post, INDEX=prepost4$training_level.post.post, FUN=mean) prepost4$prepost_total_score_diff<-prepost4$total_score.post.post-prepost4$total_score.pre t.test(prepost4$total_score.post.post[prepost4$training_level.post.post=="Pre-service Student"], prepost4$total_score.pre[prepost4$training_level.post.post=="Pre-service Student"], data=prepost4, paired=TRUE) t.test(prepost4$total_score.post.post[prepost4$training_level.post.post=="Post-graduate (beyond 12 months of graduation)"], prepost4$total_score.pre[prepost4$training_level.post.post=="Post-graduate (beyond 12 months of graduation)"], data=prepost4, paired=TRUE) t.test(prepost4$total_score.post.post[prepost4$training_level.post.post=="Post-graduate new provider (within 12 months of graduation)"], prepost4$total_score.pre[prepost4$training_level.post.post=="Post-graduate new provider (within 12 months of graduation)"], data=prepost4, paired=TRUE) bytlevel<-aov(prepost4$total_score_diff_prepost~prepost4$training_level.post.post, data=prepost4) summary(bytlevel) TukeyHSD(aov(prepost4$total_score_diff_prepost~prepost4$training_level.post.post, data=prepost4)) table(prepost4$training_level.post.post) wilcox.test(prepost4$total_score.post.post[prepost4$training_level.post.post=="Pre-service Student"], prepost4$total_score.pre[prepost4$training_level.post.post=="Pre-service Student"], data=prepost4, paired=TRUE,conf.int=TRUE) wilcox.test(prepost4$total_score.post.post[prepost4$training_level.post.post=="Post-graduate (beyond 12 months of graduation)"], prepost4$total_score.pre[prepost4$training_level.post.post=="Post-graduate (beyond 12 months of graduation)"], data=prepost4, paired=TRUE,conf.int=TRUE) wilcox.test(prepost4$total_score.post.post[prepost4$training_level.post.post=="Post-graduate new provider (within 12 months of graduation)"], prepost4$total_score.pre[prepost4$training_level.post.post=="Post-graduate new provider (within 12 months of graduation)"], data=prepost4, paired=TRUE,conf.int=TRUE) tapply(X=prepost4$total_score.pre, INDEX=prepost4$training_level.pre, FUN=sd) tapply(X=prepost4$total_score.post.post, INDEX=prepost4$training_level.post.post, FUN=sd) tapply(X=prepost4$total_score.post.post-prepost4$total_score.pre, INDEX=prepost4$training_level.post.post, FUN=sd) #STEP 9. Mean Knowledge scores and Bivariate analysis, by health cadre tapply(X=prepost4$total_score.pre, INDEX=prepost4$profession_category.pre, FUN=mean) tapply(X=prepost4$total_score.post.post, INDEX=prepost4$profession_category.post.post, FUN=mean) byhc<-aov(prepost4$total_score_diff_prepost~prepost4$profession_category.post.post, data=prepost4) summary(byhc) TukeyHSD(aov(prepost4$total_score_diff_prepost~prepost4$profession_category.post.post, data=prepost4)) table(prepost4$profession_category.post.post) t.test(prepost4$total_score.post.post[prepost4$profession_category.post.post=="Laboratory"], prepost4$total_score.pre[prepost4$profession_category.post.post=="Laboratory"], data=prepost4, paired=TRUE) t.test(prepost4$total_score.post.post[prepost4$profession_category.post.post=="Medical"], prepost4$total_score.pre[prepost4$profession_category.post.post=="Medical"], data=prepost4, paired=TRUE) t.test(prepost4$total_score.post.post[prepost4$profession_category.post.post=="Nursing/midwifery"], prepost4$total_score.pre[prepost4$profession_category.post.post=="Nursing/midwifery"], data=prepost4, paired=TRUE) t.test(prepost4$total_score.post.post[prepost4$profession_category.post.post=="Other"], prepost4$total_score.pre[prepost4$profession_category.post.post=="Other"], data=prepost4, paired=TRUE) t.test(prepost4$total_score.post.post[prepost4$profession_category.post.post=="Pharmacy"], prepost4$total_score.pre[prepost4$profession_category.post.post=="Pharmacy"], data=prepost4, paired=TRUE) wilcox.test(prepost4$total_score.post.post[prepost4$profession_category.post.post=="Laboratory"], prepost4$total_score.pre[prepost4$profession_category.post.post=="Laboratory"], data=prepost4, paired=TRUE,conf.int=TRUE) wilcox.test(prepost4$total_score.post.post[prepost4$profession_category.post.post=="Medical"], prepost4$total_score.pre[prepost4$profession_category.post.post=="Medical"], data=prepost4, paired=TRUE,conf.int=TRUE) wilcox.test(prepost4$total_score.post.post[prepost4$profession_category.post.post=="Nursing/midwifery"], prepost4$total_score.pre[prepost4$profession_category.post.post=="Nursing/midwifery"], data=prepost4, paired=TRUE,conf.int=TRUE) wilcox.test(prepost4$total_score.post.post[prepost4$profession_category.post.post=="Other"], prepost4$total_score.pre[prepost4$profession_category.post.post=="Other"], data=prepost4, paired=TRUE,conf.int=TRUE) wilcox.test(prepost4$total_score.post.post[prepost4$profession_category.post.post=="Pharmacy"], prepost4$total_score.pre[prepost4$profession_category.post.post=="Pharmacy"], data=prepost4, paired=TRUE,conf.int=TRUE) tapply(X=prepost4$total_score.pre, INDEX=prepost4$profession_category.pre, FUN=sd) tapply(X=prepost4$total_score.post.post, INDEX=prepost4$profession_category.post.post, FUN=sd) tapply(X=prepost4$total_score.post.post-prepost4$total_score.pre, INDEX=prepost4$profession_category.post.post, FUN=sd) #STEP 10. Mean Knowledge scores and Bivariate analysis, by gender tapply(X=prepost4$total_score.pre, INDEX=prepost4$gender.pre, FUN=mean) tapply(X=prepost4$total_score.post.post, INDEX=prepost4$gender.post.post, FUN=mean) table(prepost4$gender.post.post) byg<-aov(prepost4$total_score_diff_prepost~prepost4$gender.post.post, data=prepost4) summary(byg) TukeyHSD(aov(prepost4$total_score_diff_prepost~prepost4$gender.post.post, data=prepost4)) t.test(prepost4$total_score.post.post[prepost4$gender.post.post=="Female"], prepost4$total_score.pre[prepost4$gender.post.post=="Female"], data=prepost4, paired=TRUE) t.test(prepost4$total_score.post.post[prepost4$gender.post.post=="Male"], prepost4$total_score.pre[prepost4$gender.post.post=="Male"], data=prepost4, paired=TRUE) t.test(prepost4$total_score.post.post[prepost4$gender.post.post=="Other"], prepost4$total_score.pre[prepost4$gender.post.post=="Other"], data=prepost4, paired=TRUE) wilcox.test(prepost4$total_score.post.post[prepost4$gender.post.post=="Other"], prepost4$total_score.pre[prepost4$gender.post.post=="Other"], data=prepost4, paired=TRUE,conf.int=TRUE) wilcox.test(prepost4$total_score.post.post[prepost4$gender.post.post=="Female"], prepost4$total_score.pre[prepost4$gender.post.post=="Female"], data=prepost4, paired=TRUE,conf.int=TRUE) wilcox.test(prepost4$total_score.post.post[prepost4$gender.post.post=="Male"], prepost4$total_score.pre[prepost4$gender.post.post=="Male"], data=prepost4, paired=TRUE,conf.int=TRUE) tapply(X=prepost4$total_score.pre, INDEX=prepost4$gender.pre, FUN=sd) tapply(X=prepost4$total_score.post.post, INDEX=prepost4$gender.post.post, FUN=sd) tapply(X=prepost4$total_score.post.post-prepost4$total_score.pre, INDEX=prepost4$gender.post.post, FUN=sd) #STEP 10a. Mean Knowledge scores and Bivariate analysis, by country prepost4$country.post.post<-factor(prepost4$country.post.post) levels(prepost4$country.post.post) prepost4$country.post.post<-factor(prepost4$country.post.post, levels = c("Botswana","Ethiopia","Ghana","Kenya", "Lesotho","Malawi","Nigeria","RSA", "South Africa","Tanzania","Uganda", "Zambia","Zimbabwe"), labels = c("Botswana","Ethiopia","Ghana","Kenya", "Lesotho","Malawi","Nigeria","South Africa", "South Africa","Tanzania","Uganda", "Zambia","Zimbabwe")) tapply(X=prepost4$total_score.pre, INDEX=prepost4$country.post.post, FUN=mean) (tapply(X=prepost4$total_score.pre, INDEX=prepost4$country.post.post, FUN=mean)/17)*100 tapply(X=prepost4$total_score.post.post, INDEX=prepost4$country.post.post, FUN=mean) (tapply(X=prepost4$total_score.post.post, INDEX=prepost4$country.post.post, FUN=mean)/17)*100 tapply(X=prepost4$total_diff, INDEX=prepost4$country.post.post, FUN=mean) (tapply(X=prepost4$total_diff, INDEX=prepost4$country.post.post, FUN=mean)/17)*100 wilcox.test(prepost4$total_score.post.post[prepost4$country.post.post=="Botswana"], prepost4$total_score.pre[prepost4$country.post.post=="Botswana"], data=prepost4, paired=TRUE,conf.int=TRUE) wilcox.test(prepost4$total_score.post.post[prepost4$country.post.post=="Ethiopia"], prepost4$total_score.pre[prepost4$country.post.post=="Ethiopia"], data=prepost4, paired=TRUE,conf.int=TRUE) wilcox.test(prepost4$total_score.post.post[prepost4$country.post.post=="Ghana"], prepost4$total_score.pre[prepost4$country.post.post=="Ghana"], data=prepost4, paired=TRUE,conf.int=TRUE) wilcox.test(prepost4$total_score.post.post[prepost4$country.post.post=="Kenya"], prepost4$total_score.pre[prepost4$country.post.post=="Kenya"], data=prepost4, paired=TRUE,conf.int=TRUE) wilcox.test(prepost4$total_score.post.post[prepost4$country.post.post=="Lesotho"], prepost4$total_score.pre[prepost4$country.post.post=="Lesotho"], data=prepost4, paired=TRUE,conf.int=TRUE) wilcox.test(prepost4$total_score.post.post[prepost4$country.post.post=="Malawi"], prepost4$total_score.pre[prepost4$country.post.post=="Malawi"], data=prepost4, paired=TRUE,conf.int=TRUE) wilcox.test(prepost4$total_score.post.post[prepost4$country.post.post=="Nigeria"], prepost4$total_score.pre[prepost4$country.post.post=="Nigeria"], data=prepost4, paired=TRUE,conf.int=TRUE) wilcox.test(prepost4$total_score.post.post[prepost4$country.post.post=="South Africa"], prepost4$total_score.pre[prepost4$country.post.post=="South Africa"], data=prepost4, paired=TRUE,conf.int=TRUE) wilcox.test(prepost4$total_score.post.post[prepost4$country.post.post=="Tanzania"], prepost4$total_score.pre[prepost4$country.post.post=="Tanzania"], data=prepost4, paired=TRUE,conf.int=TRUE) wilcox.test(prepost4$total_score.post.post[prepost4$country.post.post=="Uganda"], prepost4$total_score.pre[prepost4$country.post.post=="Uganda"], data=prepost4, paired=TRUE,conf.int=TRUE) wilcox.test(prepost4$total_score.post.post[prepost4$country.post.post=="Zambia"], prepost4$total_score.pre[prepost4$country.post.post=="Zambia"], data=prepost4, paired=TRUE,conf.int=TRUE) wilcox.test(prepost4$total_score.post.post[prepost4$country.post.post=="Zimbabwe"], prepost4$total_score.pre[prepost4$country.post.post=="Zimbabwe"], data=prepost4, paired=TRUE,conf.int=TRUE) #STEP 11. Calculate Module confidence score and do bivariate analysis ##Clinical Confidence ###Module 1 - Clinical Confidence (m1_2_1 - m1_2_5) prepost4$m1_2_1.pre[prepost4$m1_2_1.pre==5]<-NA prepost4$m1_2_2.pre[prepost4$m1_2_2.pre==5]<-NA prepost4$m1_2_3.pre[prepost4$m1_2_3.pre==5]<-NA prepost4$m1_2_4.pre[prepost4$m1_2_4.pre==5]<-NA prepost4$m1_2_5.pre[prepost4$m1_2_5.pre==5]<-NA prepost4$m1_2_1.post.post[prepost4$m1_2_1.post.post==5]<-NA prepost4$m1_2_2.post.post[prepost4$m1_2_2.post.post==5]<-NA prepost4$m1_2_3.post.post[prepost4$m1_2_3.post.post==5]<-NA prepost4$m1_2_4.post.post[prepost4$m1_2_4.post.post==5]<-NA prepost4$m1_2_5.post.post[prepost4$m1_2_5.post.post==5]<-NA prepost4$m1ccpre<-prepost4$m1_2_1.pre+prepost4$m1_2_2.pre+prepost4$m1_2_3.pre+prepost4$m1_2_4.pre+ prepost4$m1_2_5.pre prepost4$m1ccpost<-prepost4$m1_2_1.post.post+prepost4$m1_2_2.post.post+prepost4$m1_2_3.post.post+ prepost4$m1_2_4.post.post+prepost4$m1_2_5.post.post mean(prepost4$m1ccpre, na.rm=TRUE) mean(prepost4$m1ccpost) t.test(prepost4$m1ccpost,prepost4$m1ccpre,data=prepost4, paired=TRUE) ###Module 3 - Clinical Confidence (m3_2_1 - m3_2_3) prepost4$m3_2_1.pre[prepost4$m3_2_1.pre==5]<-NA prepost4$m3_2_2.pre[prepost4$m3_2_2.pre==5]<-NA prepost4$m3_2_3.pre[prepost4$m3_2_3.pre==5]<-NA prepost4$m3_2_1.post.post[prepost4$m3_2_1.post.post==5]<-NA prepost4$m3_2_2.post.post[prepost4$m3_2_2.post.post==5]<-NA prepost4$m3_2_3.post.post[prepost4$m3_2_3.post.post==5]<-NA prepost4$m3ccpre<-prepost4$m3_2_1.pre+prepost4$m3_2_2.pre+prepost4$m3_2_3.pre prepost4$m3ccpost<-prepost4$m3_2_1.post.post+prepost4$m3_2_2.post.post+prepost4$m3_2_3.post.post mean(prepost4$m3ccpre) mean(prepost4$m3ccpost) t.test(prepost4$m3ccpost,prepost4$m3ccpre,data=prepost4, paired=TRUE) ###Module 4 - Clinical Confidence (m4_2_1 - m3_2_4) prepost4$m4_2_1.pre[prepost4$m4_2_1.pre==5]<-NA prepost4$m4_2_2.pre[prepost4$m4_2_2.pre==5]<-NA prepost4$m4_2_3.pre[prepost4$m4_2_3.pre==5]<-NA prepost4$m4_2_4.pre[prepost4$m4_2_4.pre==5]<-NA prepost4$m4_2_1.post.post[prepost4$m4_2_1.post.post==5]<-NA prepost4$m4_2_2.post.post[prepost4$m4_2_2.post.post==5]<-NA prepost4$m4_2_3.post.post[prepost4$m4_2_3.post.post==5]<-NA prepost4$m4_2_4.post.post[prepost4$m4_2_4.post.post==5]<-NA prepost4$m4ccpre<-prepost4$m4_2_1.pre+prepost4$m4_2_2.pre+prepost4$m4_2_3.pre+prepost4$m4_2_4.pre prepost4$m4ccpost<-prepost4$m4_2_1.post.post+prepost4$m4_2_2.post.post+ prepost4$m4_2_3.post.post+prepost4$m4_2_4.post.post mean(prepost4$m4ccpre) mean(prepost4$m4ccpost) t.test(prepost4$m4ccpost,prepost4$m4ccpre,data=prepost4, paired=TRUE) ###Module 17 Clinical Confidence (m17_2_2 - m17_2_4) prepost4$m17_2_2.pre[prepost4$m17_2_2.pre==5]<-NA prepost4$m17_2_3.pre[prepost4$m17_2_3.pre==5]<-NA prepost4$m17_2_4.pre[prepost4$m17_2_4.pre==5]<-NA prepost4$m17_2_2.post.post[prepost4$m17_2_2.post.post==5]<-NA prepost4$m17_2_3.post.post[prepost4$m17_2_3.post.post==5]<-NA prepost4$m17_2_4.post.post[prepost4$m17_2_4.post.post==5]<-NA prepost4$m17ccpre<-prepost4$m17_2_2.pre+prepost4$m17_2_3.pre+prepost4$m17_2_4.pre prepost4$m17ccpost<-prepost4$m17_2_2.post.post+prepost4$m17_2_3.post.post+ prepost4$m17_2_4.post.post mean(prepost4$m17ccpre) mean(prepost4$m17ccpost) t.test(prepost4$m17ccpost,prepost4$m17ccpre,data=prepost4, paired=TRUE) ###Total Clinical Confidence prepost4$tccpre<-prepost4$m1ccpre+prepost4$m3ccpre+prepost4$m4ccpre+prepost4$m17ccpre prepost4$tccpost<-prepost4$m1ccpost+prepost4$m3ccpost+prepost4$m4ccpost+prepost4$m17ccpost mean(prepost4$tccpre, na.rm = TRUE) mean(prepost4$tccpre, na.rm = TRUE)/60 sd(prepost4$tccpre, na.rm = TRUE) mean(prepost4$tccpost, na.rm = TRUE) mean(prepost4$tccpost, na.rm = TRUE)/60 sd(prepost4$tccpost, na.rm = TRUE) mean(prepost4$tccpost-prepost4$tccpre, na.rm = TRUE) mean(prepost4$tccpost-prepost4$tccpre, na.rm = TRUE)/60 sd(prepost4$tccpost-prepost4$tccpre, na.rm = TRUE) t.test(prepost4$tccpost,prepost4$tccpre,data=prepost4, paired=TRUE, na.rm=TRUE) wilcox.test(prepost4$tccpost,prepost4$tccpre,data=prepost4, paired=TRUE, na.rm=TRUE,conf.int=TRUE) ##Confidence working as part of an IPE team ###Module 3 (M3_2_4) prepost4$m3_2_4.pre[prepost4$m3_2_4.pre==5]<-NA prepost4$m3_2_4.post.post[prepost4$m3_2_4.post.post==5]<-NA mean(prepost4$m3_2_4.pre) mean(prepost4$m3_2_4.post.post) t.test(prepost4$m3_2_4.post.post,prepost4$m3_2_4.pre,data=prepost4, paired=TRUE, na.rm=TRUE) ###Module 17 (m17_2_5) prepost4$m17_2_5.pre[prepost4$m17_2_5.pre==5]<-NA prepost4$m17_2_5.post.post[prepost4$m17_2_5.post.post==5]<-NA mean(prepost4$m17_2_5.pre, na.rm=TRUE) mean(prepost4$m17_2_5.post.post, na.rm=TRUE) t.test(prepost4$m17_2_5.post.post, prepost4$m17_2_5.pre, data=post4, paired=TRUE, na.rm=TRUE) ###Total Confidence as part of an IPE team prepost4$tIPEpre<-prepost4$m3_2_4.pre+prepost4$m17_2_5.pre prepost4$tIPEpost<-prepost4$m3_2_4.post.post+prepost4$m17_2_5.post.post mean(prepost4$tIPEpre, na.rm=TRUE) mean(prepost4$tIPEpre, na.rm=TRUE)/8 sd(prepost4$tIPEpre, na.rm=TRUE) mean(prepost4$tIPEpost, na.rm=TRUE) mean(prepost4$tIPEpost, na.rm=TRUE)/8 sd(prepost4$tIPEpost, na.rm=TRUE) mean(prepost4$tIPEpost-prepost4$tIPEpre, na.rm=TRUE) mean(prepost4$tIPEpost-prepost4$tIPEpre, na.rm=TRUE)/8 sd(prepost4$tIPEpost-prepost4$tIPEpre, na.rm=TRUE) t.test(prepost4$tIPEpost, prepost4$tIPEpre, data=prepost4, paired=TRUE, na.rm=TRUE) wilcox.test(prepost4$tIPEpost, prepost4$tIPEpre, data=prepost4, paired=TRUE, na.rm=TRUE,conf.int=TRUE) ##Confidence implementing QI ### Module 4 (m4_2_5) prepost4$m4_2_5.pre[prepost4$m4_2_5.pre==5]<-NA prepost4$m4_2_5.post.post[prepost4$m4_2_5.post.post==5]<-NA mean(prepost4$m4_2_5.pre, na.rm = TRUE) mean(prepost4$m4_2_5.post.post, na.rm=TRUE) t.test(prepost4$m4_2_5.post.post, prepost4$m4_2_5.pre, data=prepost4, paired=TRUE, na.rm=TRUE) ###Module 17 (m17_2_1) prepost4$m17_2_1.pre[prepost4$m17_2_1.pre==5]<-NA prepost4$m17_2_1.post.post[prepost4$m17_2_1.post.post==5]<-NA mean(prepost4$m17_2_1.pre, na.rm=TRUE) mean(prepost4$m17_2_1.post.post, na.rm=TRUE) t.test(prepost4$m17_2_1.post.post, prepost4$m17_2_1.pre, data=prepost4, paired=TRUE, na.rm=TRUE) ###Total Confidence Implementing QI prepost4$tQIpre<-prepost4$m4_2_5.pre+prepost4$m17_2_1.pre prepost4$tQIpost<-prepost4$m4_2_5.post.post+prepost4$m17_2_1.post.post mean(prepost4$tQIpre, na.rm=TRUE) mean(prepost4$tQIpre, na.rm=TRUE)/8 sd(prepost4$tQIpre, na.rm=TRUE) mean(prepost4$tQIpost, na.rm=TRUE) mean(prepost4$tQIpost, na.rm=TRUE)/8 sd(prepost4$tQIpost, na.rm=TRUE) sqrt(var(prepost4$tQIpost, na.rm=TRUE)) mean(prepost4$tQIpost-prepost4$tQIpre, na.rm=TRUE) mean(prepost4$tQIpost-prepost4$tQIpre, na.rm=TRUE)/8 sd(prepost4$tQIpost-prepost4$tQIpre, na.rm=TRUE) t.test(prepost4$tQIpost, prepost4$tQIpre, data=prepost4, paired=TRUE, na.rm=TRUE) wilcox.test(prepost4$tQIpost, prepost4$tQIpre, data=prepost4, paired=TRUE, na.rm=TRUE,conf.int=TRUE) #STEP 12. Calculate Module confidence score + bivariate analysis, by ##health profession, gender, training level ###Total Clinical Confidence prepost4$tccpre<-prepost4$m1ccpre+prepost4$m3ccpre+prepost4$m4ccpre+prepost4$m17ccpre prepost4$tccpost<-prepost4$m1ccpost+prepost4$m3ccpost+prepost4$m4ccpost+prepost4$m17ccpost mean_cc_pre <- tapply(prepost4$tccpre, prepost4$profession_category.post.post, mean, na.rm=TRUE) mean_cc_pre mean_cc_pre/60 tapply(prepost4$tccpre, prepost4$profession_category.post.post, sd, na.rm=TRUE) mean_cc_post <- tapply(prepost4$tccpost, prepost4$profession_category.post.post, mean, na.rm=TRUE) mean_cc_post mean_cc_post/60 tapply(prepost4$tccpost, prepost4$profession_category.post.post, sd, na.rm=TRUE) mean_cc_post-mean_cc_pre (mean_cc_post-mean_cc_pre)/60 tapply(prepost4$tccpost-prepost4$tccpre, prepost4$profession_category.post.post, sd, na.rm=TRUE) pre_plot <- tapply(prepost4$tccpre, prepost4$profession_category.post.post, hist) post_plot <- tapply(prepost4$tccpost, prepost4$profession_category.post.post, hist) wilcox.test(prepost4$tccpost[prepost4$profession_category.post.post=="Medical"], prepost4$tccpre[prepost4$profession_category.post.post=="Medical"], data=prepost4,paired=TRUE, na.rm=TRUE,conf.int=TRUE) wilcox.test(prepost4$tccpost[prepost4$profession_category.post.post=="Nursing/midwifery"], prepost4$tccpre[prepost4$profession_category.post.post=="Nursing/midwifery"], data=prepost4,paired=TRUE, na.rm=TRUE,conf.int=TRUE) wilcox.test(prepost4$tccpost[prepost4$profession_category.post.post=="Laboratory"], prepost4$tccpre[prepost4$profession_category.post.post=="Laboratory"], data=prepost4,paired=TRUE, na.rm=TRUE,conf.int=TRUE) wilcox.test(prepost4$tccpost[prepost4$profession_category.post.post=="Pharmacy"], prepost4$tccpre[prepost4$profession_category.post.post=="Pharmacy"], data=prepost4,paired=TRUE, na.rm=TRUE,conf.int=TRUE) wilcox.test(prepost4$tccpost[prepost4$profession_category.post.post=="Other"], prepost4$tccpre[prepost4$profession_category.post.post=="Other"], data=prepost4,paired=TRUE, na.rm=TRUE,conf.int=TRUE) prepost4$gender.post.post<-factor(prepost4$gender.post.post) levels(prepost4$gender.post.post) a<-tapply(prepost4$tccpre, prepost4$gender.post.post, mean, na.rm=TRUE) a a/60 tapply(prepost4$tccpre, prepost4$gender.post.post, sd, na.rm=TRUE) b<-tapply(prepost4$tccpost, prepost4$gender.post.post, mean, na.rm=TRUE) b b/60 tapply(prepost4$tccpost, prepost4$gender.post.post, sd, na.rm=TRUE) b-a (b-a)/60 tapply(prepost4$tccpost-prepost4$tccpre, prepost4$gender.post.post, sd, na.rm=TRUE) wilcox.test(prepost4$tccpost[prepost4$gender.post.post=="Female"], prepost4$tccpre[prepost4$gender.post.post=="Female"], data=prepost4,paired=TRUE, na.rm=TRUE,conf.int=TRUE) wilcox.test(prepost4$tccpost[prepost4$gender.post.post=="Male"], prepost4$tccpre[prepost4$gender.post.post=="Male"], data=prepost4,paired=TRUE, na.rm=TRUE,conf.int=TRUE) wilcox.test(prepost4$tccpost[prepost4$gender.post.post=="Other"], prepost4$tccpre[prepost4$gender.post.post=="Other"], data=prepost4,paired=TRUE, na.rm=TRUE,conf.int=TRUE) prepost4$training_level.post.post<-factor(prepost4$training_level.post.post) levels(prepost4$training_level.post.post) a<-tapply(prepost4$tccpre, prepost4$training_level.post.post, mean, na.rm=TRUE) a a/60 tapply(prepost4$tccpre, prepost4$training_level.post.post, sd, na.rm=TRUE) b<-tapply(prepost4$tccpost, prepost4$training_level.post.post, mean, na.rm=TRUE) b b/60 tapply(prepost4$tccpost, prepost4$training_level.post.post, sd, na.rm=TRUE) b-a (b-a)/60 tapply(prepost4$tccpost-prepost4$tccpre, prepost4$training_level.post.post, sd, na.rm=TRUE) wilcox.test(prepost4$tccpost[prepost4$training_level.post.post=="Post-graduate (beyond 12 months of graduation)"], prepost4$tccpre[prepost4$training_level.post.post=="Post-graduate (beyond 12 months of graduation)"], data=prepost4,paired=TRUE, na.rm=TRUE,conf.int=TRUE) wilcox.test(prepost4$tccpost[prepost4$training_level.post.post=="Post-graduate new provider (within 12 months of graduation)"], prepost4$tccpre[prepost4$training_level.post.post=="Post-graduate new provider (within 12 months of graduation)"], data=prepost4,paired=TRUE, na.rm=TRUE,conf.int=TRUE) wilcox.test(prepost4$tccpost[prepost4$training_level.post.post=="Pre-service Student"], prepost4$tccpre[prepost4$training_level.post.post=="Pre-service Student"], data=prepost4,paired=TRUE, na.rm=TRUE,conf.int=TRUE) ###Total Confidence as part of an IPE team prepost4$tIPEpre<-prepost4$m3_2_4.pre+prepost4$m17_2_5.pre prepost4$tIPEpost<-prepost4$m3_2_4.post.post+prepost4$m17_2_5.post.post mean_ipe_pre <- tapply(prepost4$tIPEpre, prepost4$profession_category.post.post, mean, na.rm=TRUE) mean_ipe_pre mean_ipe_pre/8 tapply(prepost4$tIPEpre, prepost4$profession_category.post.post, sd, na.rm=TRUE) mean_ipe_post <- tapply(prepost4$tIPEpost, prepost4$profession_category.post.post, mean, na.rm=TRUE) mean_ipe_post mean_ipe_post/8 tapply(prepost4$tIPEpost, prepost4$profession_category.post.post, sd, na.rm=TRUE) mean_ipe_post-mean_ipe_pre (mean_ipe_post-mean_ipe_pre)/8 tapply(prepost4$tIPEpost-prepost4$tIPEpre, prepost4$profession_category.post.post, sd, na.rm=TRUE) pre_plot2 <- tapply(prepost4$tIPEpre, prepost4$profession_category.post.post, hist) post_plot2 <- tapply(prepost4$tIPEpost, prepost4$profession_category.post.post, hist) wilcox.test(prepost4$tIPEpost[prepost4$profession_category.post.post=="Medical"], prepost4$tIPEpre[prepost4$profession_category.post.post=="Medical"], data=prepost4,paired=TRUE, na.rm=TRUE,conf.int=TRUE) wilcox.test(prepost4$tIPEpost[prepost4$profession_category.post.post=="Nursing/midwifery"], prepost4$tIPEpre[prepost4$profession_category.post.post=="Nursing/midwifery"], data=prepost4,paired=TRUE, na.rm=TRUE,conf.int=TRUE) wilcox.test(prepost4$tIPEpost[prepost4$profession_category.post.post=="Laboratory"], prepost4$tIPEpre[prepost4$profession_category.post.post=="Laboratory"], data=prepost4,paired=TRUE, na.rm=TRUE,conf.int=TRUE) wilcox.test(prepost4$tIPEpost[prepost4$profession_category.post.post=="Pharmacy"], prepost4$tIPEpre[prepost4$profession_category.post.post=="Pharmacy"], data=prepost4,paired=TRUE, na.rm=TRUE,conf.int=TRUE) wilcox.test(prepost4$tIPEpost[prepost4$profession_category.post.post=="Other"], prepost4$tIPEpre[prepost4$profession_category.post.post=="Other"], data=prepost4,paired=TRUE, na.rm=TRUE,conf.int=TRUE) a<-tapply(prepost4$tIPEpre, prepost4$gender.post.post, mean, na.rm=TRUE) a a/8 tapply(prepost4$tIPEpre, prepost4$gender.post.post, sd, na.rm=TRUE) b<-tapply(prepost4$tIPEpost, prepost4$gender.post.post, mean, na.rm=TRUE) b b/8 tapply(prepost4$tIPEpost, prepost4$gender.post.post, sd, na.rm=TRUE) b-a (b-a)/8 tapply(prepost4$tIPEpost-prepost4$tIPEpre, prepost4$gender.post.post, sd, na.rm=TRUE) wilcox.test(prepost4$tIPEpost[prepost4$gender.post.post=="Female"], prepost4$tIPEpre[prepost4$gender.post.post=="Female"], data=prepost4,paired=TRUE, na.rm=TRUE,conf.int=TRUE) wilcox.test(prepost4$tIPEpost[prepost4$gender.post.post=="Male"], prepost4$tIPEpre[prepost4$gender.post.post=="Male"], data=prepost4,paired=TRUE, na.rm=TRUE,conf.int=TRUE) wilcox.test(prepost4$tIPEpost[prepost4$gender.post.post=="Other"], prepost4$tIPEpre[prepost4$gender.post.post=="Other"], data=prepost4,paired=TRUE, na.rm=TRUE,conf.int=TRUE) a<-tapply(prepost4$tIPEpre, prepost4$training_level.post.post, mean, na.rm=TRUE) a a/8 tapply(prepost4$tIPEpre, prepost4$training_level.post.post, sd, na.rm=TRUE) b<-tapply(prepost4$tIPEpost, prepost4$training_level.post.post, mean, na.rm=TRUE) b b/8 tapply(prepost4$tIPEpost, prepost4$training_level.post.post, sd, na.rm=TRUE) b-a (b-a)/8 tapply(prepost4$tIPEpost-prepost4$tIPEpre, prepost4$training_level.post.post, sd, na.rm=TRUE) wilcox.test(prepost4$tIPEpost[prepost4$training_level.post.post=="Post-graduate (beyond 12 months of graduation)"], prepost4$tIPEpre[prepost4$training_level.post.post=="Post-graduate (beyond 12 months of graduation)"], data=prepost4,paired=TRUE, na.rm=TRUE,conf.int=TRUE) wilcox.test(prepost4$tIPEpost[prepost4$training_level.post.post=="Post-graduate new provider (within 12 months of graduation)"], prepost4$tIPEpre[prepost4$training_level.post.post=="Post-graduate new provider (within 12 months of graduation)"], data=prepost4,paired=TRUE, na.rm=TRUE,conf.int=TRUE) wilcox.test(prepost4$tIPEpost[prepost4$training_level.post.post=="Pre-service Student"], prepost4$tIPEpre[prepost4$training_level.post.post=="Pre-service Student"], data=prepost4,paired=TRUE, na.rm=TRUE,conf.int=TRUE) ###Total Confidence Implementing QI prepost4$tQIpre<-prepost4$m4_2_5.pre+prepost4$m17_2_1.pre prepost4$tQIpost<-prepost4$m4_2_5.post.post+prepost4$m17_2_1.post.post mean_QI_pre <- tapply(prepost4$tQIpre, prepost4$profession_category.post.post, mean, na.rm=TRUE) mean_QI_pre mean_QI_pre/8 tapply(prepost4$tQIpre, prepost4$profession_category.post.post, sd, na.rm=TRUE) mean_QI_post <- tapply(prepost4$tQIpost, prepost4$profession_category.post.post, mean, na.rm=TRUE) mean_QI_post mean_QI_post/8 tapply(prepost4$tQIpost, prepost4$profession_category.post.post, sd, na.rm=TRUE) mean_QI_post-mean_QI_pre (mean_QI_post-mean_QI_pre)/8 tapply(prepost4$tQIpost-prepost4$tQIpre, prepost4$profession_category.post.post, sd, na.rm=TRUE) pre_plot3 <- tapply(prepost4$tQIpre, prepost4$profession_category.post.post, hist) post_plot3 <- tapply(prepost4$tQIpost, prepost4$profession_category.post.post, hist) wilcox.test(prepost4$tQIpost[prepost4$profession_category.post.post=="Medical"], prepost4$tQIpre[prepost4$profession_category.post.post=="Medical"], data=prepost4,paired=TRUE, na.rm=TRUE,conf.int=TRUE) wilcox.test(prepost4$tQIpost[prepost4$profession_category.post.post=="Nursing/midwifery"], prepost4$tQIpre[prepost4$profession_category.post.post=="Nursing/midwifery"], data=prepost4,paired=TRUE, na.rm=TRUE,conf.int=TRUE) wilcox.test(prepost4$tQIpost[prepost4$profession_category.post.post=="Laboratory"], prepost4$tQIpre[prepost4$profession_category.post.post=="Laboratory"], data=prepost4,paired=TRUE, na.rm=TRUE,conf.int=TRUE) wilcox.test(prepost4$tQIpost[prepost4$profession_category.post.post=="Pharmacy"], prepost4$tQIpre[prepost4$profession_category.post.post=="Pharmacy"], data=prepost4,paired=TRUE, na.rm=TRUE,conf.int=TRUE) wilcox.test(prepost4$tQIpost[prepost4$profession_category.post.post=="Other"], prepost4$tQIpre[prepost4$profession_category.post.post=="Other"], data=prepost4,paired=TRUE, na.rm=TRUE,conf.int=TRUE) a<-tapply(prepost4$tQIpre, prepost4$gender.post.post, mean, na.rm=TRUE) a a/8 tapply(prepost4$tQIpre, prepost4$gender.post.post, sd, na.rm=TRUE) b<-tapply(prepost4$tQIpost, prepost4$gender.post.post, mean, na.rm=TRUE) b b/8 tapply(prepost4$tQIpost, prepost4$gender.post.post, sd, na.rm=TRUE) b-a (b-a)/8 tapply(prepost4$tQIpost-prepost4$tQIpre, prepost4$gender.post.post, sd, na.rm=TRUE) wilcox.test(prepost4$tQIpost[prepost4$gender.post.post=="Female"], prepost4$tQIpre[prepost4$gender.post.post=="Female"], data=prepost4,paired=TRUE, na.rm=TRUE,conf.int=TRUE) wilcox.test(prepost4$tQIpost[prepost4$gender.post.post=="Male"], prepost4$tQIpre[prepost4$gender.post.post=="Male"], data=prepost4,paired=TRUE, na.rm=TRUE,conf.int=TRUE) wilcox.test(prepost4$tQIpost[prepost4$gender.post.post=="Other"], prepost4$tQIpre[prepost4$gender.post.post=="Other"], data=prepost4,paired=TRUE, na.rm=TRUE,conf.int=TRUE) a<-tapply(prepost4$tQIpre, prepost4$training_level.post.post, mean, na.rm=TRUE) a a/8 tapply(prepost4$tQIpre, prepost4$training_level.post.post, sd, na.rm=TRUE) b<-tapply(prepost4$tQIpost, prepost4$training_level.post.post, mean, na.rm=TRUE) b b/8 tapply(prepost4$tQIpost, prepost4$training_level.post.post, sd, na.rm=TRUE) b-a (b-a)/8 tapply(prepost4$tQIpost-prepost4$tQIpre, prepost4$training_level.post.post, sd, na.rm=TRUE) wilcox.test(prepost4$tQIpost[prepost4$training_level.post.post=="Post-graduate (beyond 12 months of graduation)"], prepost4$tQIpre[prepost4$training_level.post.post=="Post-graduate (beyond 12 months of graduation)"], data=prepost4,paired=TRUE, na.rm=TRUE,conf.int=TRUE) wilcox.test(prepost4$tQIpost[prepost4$training_level.post.post=="Post-graduate new provider (within 12 months of graduation)"], prepost4$tQIpre[prepost4$training_level.post.post=="Post-graduate new provider (within 12 months of graduation)"], data=prepost4,paired=TRUE, na.rm=TRUE,conf.int=TRUE) wilcox.test(prepost4$tQIpost[prepost4$training_level.post.post=="Pre-service Student"], prepost4$tQIpre[prepost4$training_level.post.post=="Pre-service Student"], data=prepost4,paired=TRUE, na.rm=TRUE,conf.int=TRUE) #STEP 13. Look at when post taken prepost4$form_date.1.pre<-as.Date(prepost4$form_date.1.pre) prepost4$form_date.1.post.post<-as.Date(prepost4$form_date.1.post.post) prepost4$timediff_prepost<-difftime(prepost4$form_date.1.post.post, prepost4$form_date.1.pre, units="days") prepost4$form_date.1.post.post-prepost4$form_date.1.pre prepost4$form_date.1.post.post[973] prepost4$form_date.1.pre[973] mean(prepost4$timediff_prepost) range(prepost4$timediff_prepost) table(prepost4$timediff_prepost) sum(prepost4$timediff_prepost<0) sum(prepost4$timediff_prepost>=0) sum(prepost4$timediff_prepost>=0&prepost4$timediff_prepost<=7) sum(prepost4$timediff_prepost>7) #STEP 14. do linear regression #Timediff vs. Pre/Post score difference ##make total score diff column prepost4$total_score_diff_prepost <- prepost4$total_score.post.post-prepost4$total_score.pre summary(lm(prepost4$total_score_diff_prepost~prepost4$timediff_prepost)) plot((lm(prepost4$total_score_diff_prepost~prepost4$timediff_prepost))) plot(prepost4$total_score_diff_prepost~prepost4$timediff_prepost) #STEP 15. Look at before and after 14 days #mean score of those with more than 14 days time diff mean(prepost4$total_score.post.post) mean(prepost4$total_score.post.post[prepost4$timediff_prepost>14]) mean(prepost4$total_score.post.post[prepost4$timediff_prepost<0]) mean(prepost4$total_score.post.post[prepost4$timediff_prepost>=0& prepost4$timediff_prepost<=14]) hist(prepost4$total_score_diff_prepost) t.test(prepost4$total_score.post.post[prepost4$timediff_prepost>=0& prepost4$timediff_prepost<=14], prepost4$total_score.post.post[prepost4$timediff_prepost>14], data=prepost4, paired=FALSE, na.rm=TRUE) t.test(prepost4$total_score.post.post[prepost4$timediff_prepost<14], prepost4$total_score.post.post[prepost4$timediff_prepost>14], data=prepost4, paired=FALSE, na.rm=TRUE) t.test(prepost4$total_score.post.post[prepost4$timediff_prepost>=0& prepost4$timediff_prepost<=14], prepost4$total_score.post.post[prepost4$timediff_prepost<0], data=prepost4, paired=FALSE, na.rm=TRUE) #STEP 16. Grab data for a spine graph for the confidence questions #Clinical Confidence PRE cc_pre<-prepost4[,c("m1_2_1.pre","m1_2_2.pre","m1_2_3.pre","m1_2_4.pre","m1_2_5.pre", "m3_2_1.pre","m3_2_2.pre","m3_2_3.pre","m4_2_1.pre","m4_2_2.pre", "m4_2_3.pre","m4_2_4.pre","m17_2_2.pre","m17_2_3.pre","m17_2_4.pre")] cc_pre_print<-for (i in 1:ncol(cc_pre)) { print(table(cc_pre[,i])) } prepost4$m1_2_1.pre prepost4$m1_2_2.pre prepost4$m1_2_3.pre prepost4$m1_2_4.pre prepost4$m1_2_5.pre prepost4$m3_2_1.pre prepost4$m3_2_2.pre prepost4$m3_2_3.pre prepost4$m4_2_1.pre prepost4$m4_2_2.pre prepost4$m4_2_3.pre prepost4$m4_2_4.pre prepost4$m17_2_2.pre prepost4$m17_2_3.pre prepost4$m17_2_4.pre #Clinical Confidence POST table(prepost4$m1_2_1.post.post) table(prepost4$m1_2_2.post.post) table(prepost4$m1_2_3.post.post) table(prepost4$m1_2_4.post.post) table(prepost4$m1_2_5.post.post) table(prepost4$m3_2_1.post.post) table(prepost4$m3_2_2.post.post) table(prepost4$m3_2_3.post.post) table(prepost4$m4_2_1.post.post) table(prepost4$m4_2_2.post.post) table(prepost4$m4_2_3.post.post) table(prepost4$m4_2_4.post.post) table(prepost4$m17_2_2.post.post) table(prepost4$m17_2_3.post.post) table(prepost4$m17_2_4.post.post) ###Total Confidence as part of an IPE team #PRE table(prepost4$m3_2_4.pre) table(prepost4$m17_2_5.pre) #POST table(prepost4$m3_2_4.post.post) table(prepost4$m17_2_5.post.post) ###Total Confidence Implementing QI #PRE table(prepost4$m4_2_5.pre) table(prepost4$m17_2_1.pre) #POST table(prepost4$m4_2_5.post.post) table(prepost4$m17_2_1.post.post)