db <- read.csv("~/Downloads/ComiteEtica/ComiteEtica_db.csv")
knitr::kable(db)
Point | Type | Location | Value |
---|---|---|---|
1 | Marker | 910.0 | 0.00 |
2 | Marker | 621.5 | 100.00 |
3 | Marker | 331.5 | 200.00 |
4 | Marker | 39.5 | 300.00 |
5 | RiseNif | 457.5 | 156.27 |
6 | RiseNif | 401.5 | 175.56 |
7 | RiseHET | 595.5 | 108.71 |
8 | RiseHET | 571.5 | 116.98 |
9 | RiseHET | 497.5 | 142.48 |
10 | DropRise | 245.5 | 229.32 |
11 | DropRise | 221.5 | 237.59 |
12 | DropRise | 161.5 | 258.27 |
13 | DropHET | 199.5 | 245.17 |
14 | DropHET | 163.5 | 257.58 |
15 | DropGsMT | 241.5 | 230.70 |
16 | DropGsMT | 209.5 | 241.73 |
17 | DropGsMT | 227.5 | 235.52 |
18 | DropGsMT | 165.5 | 256.89 |
19 | DropGsMT | 93.5 | 281.70 |
Extriago datos de los valures calculados de los puntos
db1 <- db[(5:nrow(db)),]
db1$Type <- factor(db1$Type, levels = c("RiseNif", "RiseHET", "DropRise", "DropHET", "DropGsMT"))
library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
res <- db1 %>% # tomo la base de datos
group_by(Type) %>% # la agrupo por la variable tipo
summarise(
size = mean(Value), # Promedio por grupo
sd = sd(Value), # desviacion estandar por grupo
n = n(), # n por grupo (cross check)
se = sd / sqrt(n) # error estandar
)
res
## # A tibble: 5 × 5
## Type size sd n se
## <fct> <dbl> <dbl> <int> <dbl>
## 1 RiseNif 166. 13.6 2 9.64
## 2 RiseHET 123. 17.6 3 10.2
## 3 DropRise 242. 14.9 3 8.61
## 4 DropHET 251. 8.78 2 6.20
## 5 DropGsMT 249. 20.6 5 9.22
library(ggplot2)
ggplot(res, aes(x=Type, y=size, fill=Type)) +
#geom_bar(stat="identity", color="black", position=position_dodge()) +
geom_point(data = db1, aes(x=Type, y=Value, col = Type)) +
geom_errorbar(aes(ymin=size-2*sd, ymax=size+2*sd), width=.2,
position=position_dodge(.9)) +
ylim(0, 300)