#install.packages("googlesheets4")
#https://github.com/tidyverse/googlesheets4
library(googlesheets4)
library(ggplot2)

Read the data in

beans <- read_sheet("https://docs.google.com/spreadsheets/d/1uet87MtwnXE16_ldijFgtu4aSv2vJ5qxN4luQxyw_p4/edit#gid=1780467196")

## Registered S3 method overwritten by 'openssl':
##   method      from
##   print.bytes Rcpp

## Using an auto-discovered, cached token.
## To suppress this message, modify your code or options to clearly consent to the use of a cached token.
## See gargle's "Non-interactive auth" vignette for more details:
## https://gargle.r-lib.org/articles/non-interactive-auth.html
## The googlesheets4 package is using a cached token for tiagoandremarques@gmail.com.

## Reading from 'Untitled spreadsheet'

## 

truebeans <- 2620

Estimates

the actual estimas, in the order they came in

beans$`What is your best guess for the number of beans in the jar?`

##  [1] 1200 3375  672  996 2419 2312 3333  150  800  850 1500  897 6200  400
## [15]  330 3000 1500  789 1500 1000 2000  953 3999  540  897 3060 1136 1000
## [29]  282  324 1745 1089 2000 5000  301 2500 1500 1000 1369 1800  989 3200
## [43]  650 2200

and sorted for easier reading

beans$`What is your best guess for the number of beans in the jar?`

##  [1] 1200 3375  672  996 2419 2312 3333  150  800  850 1500  897 6200  400
## [15]  330 3000 1500  789 1500 1000 2000  953 3999  540  897 3060 1136 1000
## [29]  282  324 1745 1089 2000 5000  301 2500 1500 1000 1369 1800  989 3200
## [43]  650 2200

ests <- beans$`What is your best guess for the number of beans in the jar?`

The minimum estimate was 150 beans, the maximum estimate was 6200 beans, and the mean estimate was 1168. The true number of beans in the jar was 2620 beans.

hist(beans$`What is your best guess for the number of beans in the jar?`,main="Beans: You've bean estimated",xlab="Estimate",breaks=seq(0,7000,250))
abline(v=truebeans,lty=2,col="green")
abline(v=mean(beans$`What is your best guess for the number of beans in the jar?`),lty=2,col="red")
legend("topright",legend=c("Truth=2620","Estimated mean"),lty=2,col=c("green","red"))

ggplot(data=beans, aes(`What is your best guess for the number of beans in the jar?`)) + 
  geom_histogram()+geom_vline(xintercept = 2620,linetype="dotted", 
                              color = "blue", size=1.5)

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

Now by sex

#about sex
p<-ggplot(beans, aes(x=`What is your best guess for the number of beans in the jar?`, y=`What is your gender?`, color=`What is your gender?`)) +
  geom_boxplot()+geom_vline(xintercept = truebeans,linetype="dotted", 
                            color = "blue", size=1.5)
p

About ISEC

#About ISEC
p<-ggplot(beans, aes(x=`What is your best guess for the number of beans in the jar?`, y=`Have you ever attended an ISEC conference?`, color=`Have you ever attended an ISEC conference?`)) +
  geom_boxplot()+geom_vline(xintercept = truebeans,linetype="dotted", 
                            color = "blue", size=1.5)
p

About country

#about country
p<-ggplot(beans, aes(x=`What is your best guess for the number of beans in the jar?`, y=`Which country do you live in?`, color=`Which country do you live in?`)) +
  geom_boxplot()+geom_vline(xintercept = truebeans,linetype="dotted", 
                            color = "blue", size=1.5)

p

About children

#about children
p<-ggplot(beans, aes(x=`What is your best guess for the number of beans in the jar?`, y=`Do you have children?`, color=`Do you have children?`)) +
  geom_boxplot()+geom_vline(xintercept = truebeans,linetype="dotted", 
                            color = "blue", size=1.5)
p

Age vs estimate

plot(beans$`How old are you?`,beans$`What is your best guess for the number of beans in the jar?`)

Influence of age on error?

beans$error <- beans$`What is your best guess for the number of beans in the jar?`-truebeans
plot(beans$`How old are you?`,beans$error)

Errors:

sort(beans$error)

##  [1] -2470 -2338 -2319 -2296 -2290 -2220 -2080 -1970 -1948 -1831 -1820
## [12] -1770 -1723 -1723 -1667 -1631 -1624 -1620 -1620 -1620 -1531 -1484
## [23] -1420 -1251 -1120 -1120 -1120 -1120  -875  -820  -620  -620  -420
## [34]  -308  -201  -120   380   440   580   713   755  1379  2380  3580