PRACTICA 4

CARGAR LIBRERIAS

library(readr)
library(ggplot2)
library(corrplot)

## corrplot 0.84 loaded

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

CARGAR DATOS

datos<- read.csv("../titulacio/rutas millas tarifas de vuelos.csv")
str(datos)

## 'data.frame':    18 obs. of  3 variables:
##  $ ruta  : chr  "Dallas-Austin " "Houston-Dallas " "Chicago-Detroit " "Chicago-San Luis " ...
##  $ millas: int  178 232 238 262 301 593 1092 1608 714 901 ...
##  $ costo : int  125 123 148 136 129 162 224 264 287 256 ...

summary(datos)

##      ruta               millas         costo      
##  Length:18          Min.   : 178   Min.   :123.0  
##  Class :character   1st Qu.: 374   1st Qu.:151.5  
##  Mode  :character   Median :1048   Median :275.5  
##                     Mean   :1196   Mean   :280.7  
##                     3rd Qu.:1752   3rd Qu.:364.0  
##                     Max.   :2574   Max.   :513.0

COEFICIENTE DE CORELACION

MILLAS VARIABLE INDEPENDIENTE X

COSTO VARIABLE DEPENDIENTE Y

r<-cor(datos$millas, datos$costo)
r<- round(r,6)
r

## [1] 0.835779

LA INTERPRETACION DE LA CORRELACION SIGNIFICA QUE ES UNA CORRELACION POSITIVA CONSIDERABLE

MODELO DE REGRESION LINEAL SIMPLE (MRL) SU FORMULA ESTA DADA POR:COSTO=a+b*millas

mrl<-lm(data = datos,formula=costo ~ millas)
mrl

## 
## Call:
## lm(formula = costo ~ millas, data = datos)
## 
## Coefficients:
## (Intercept)       millas  
##    128.5770       0.1272

summary(mrl)

## 
## Call:
## lm(formula = costo ~ millas, data = datos)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -130.58  -40.95  -18.36   46.06  155.71 
## 
## Coefficients:
##              Estimate Std. Error t value Pr(>|t|)    
## (Intercept) 128.57699   30.24824   4.251  0.00061 ***
## millas        0.12715    0.02088   6.089 1.57e-05 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 72.38 on 16 degrees of freedom
## Multiple R-squared:  0.6985, Adjusted R-squared:  0.6797 
## F-statistic: 37.07 on 1 and 16 DF,  p-value: 1.567e-05

DETERMINAR COEFICIENTES

a<-mrl$coefficients[1]
b<-mrl$coefficients[2]
a

## (Intercept) 
##     128.577

b

##    millas 
## 0.1271535

PREDICCION EN FORMA MANUAL

millas.nuevo<-200
prediccion.manual<-a+b*millas.nuevo
prediccion.manual

## (Intercept) 
##    154.0077

PREDICCION POR MEDIO DE PREDICT() SE REALIZA CON EL MISMO VALOR PARA VER SI COINCIDEN

prediccion<-predict(mrl,newdata=data.frame(millas=c(200)))
prediccion

##        1 
## 154.0077

PREDICT() UTILIZANDO VARIOS VALORES

prediccion<-predict(mrl,newdata=data.frame(millas=c(156,245,365,129,478)))
prediccion

##        1        2        3        4        5 
## 148.4129 159.7296 174.9880 144.9798 189.3563