CV=read.csv("/Users/maxineharlemon/INFM_Mercer/Covid_Depression_Case_Study.csv")
CV$Females=(CV$Percent_Female)*((0.01)*(CV$Sample_size))
CV$Females=round(CV$Females, digits = 0)
CV$Males=(CV$Sample_size)-(CV$Females)
colnames(CV)[4]="Sample_Size"
knitr::kable(CV)
Study Country Sampling.Method Sample_Size Mean_age Percent_Female Response_rate Depression_Assessment Depression_Prevalence Quality_score Females Males
Ahmed China Convenience 1074 33.54 46.80 NR BDI-II 37.1 6 503 571
Gao China Convenience 4872 32.2 67.70 83.3 WHO-5 48.3 7 3298 1574
Huang China Convenience 7236 35.3 54.60 85.3 CES-D 20.1 7 3951 3285
Kazmi India Random 1000 NR 62.00 66.7 DASS-21 38.9 6 620 380
Lei China Convenience 1593 32.3 61.30 80.2 SDS 14.7 7 977 616
Mazza Italy Convenience 2766 32.94 71.66 98.4 DASS-21 32.7 7 1982 784
Nguyen Vietnam Convenience 3947 44.4 55.70 NR PHQ-9 7.4 6 2198 1749
Ni China(Wuhan) Convenience 1577 NR 60.80 NR PHQ-9 19.2 6 959 618
Shevlin UK Quota 2025 45.44 51.70 NR PHQ-9 22.1 7 1047 978
Sonderskov Denmark NR 2458 49.1 51.00 NR WHO-5 25.4 7 1254 1204
Wang China Snowball 1210 NR 67.30 93.8 DASS-21 30.3 7 814 396
Wang China NR 600 34 55.50 99.2 SDS 17.2 7 333 267 
library(ggplot2)
## Warning: package 'ggplot2' was built under R version 4.5.2
ggplot(data = CV, mapping = aes(x=Study)) + geom_point(aes(y=Females), color ="darkred")+ geom_point(aes(y=Males), color="steelblue") + scale_size_manual(values = c(6)) + ylab("Males and Females") +scale_colour_manual(breaks = c("Females","Males"), values = c("darkred","steelblue"))