Guia practica 2
Luis Ernesto Juarez Linares
29 de marzo de 2019
EJEMPLO DE REGRESION
Cargar datos
Ruta <-read.csv("C:/Users/luisn/Downloads/ejemplo_regresion.csv")
colnames(Ruta)<- c("X1", "X2", "Y")
library(readr)
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
## X1 X2 Y
## 1 3.92 7298 0.75
## 2 3.61 6855 0.71
## 3 3.32 6636 0.66
## 4 3.07 6506 0.61
## 5 3.06 6450 0.70
## 6 3.11 6402 0.72
## 7 3.21 6368 0.77
## X1 X2 Y
## 1 3.92 7298 0.75
## 2 3.61 6855 0.71
## 3 3.32 6636 0.66
## 4 3.07 6506 0.61
## 5 3.06 6450 0.70
## 6 3.11 6402 0.72
## 7 3.21 6368 0.77
## 8 3.26 6340 0.74
## 9 3.42 6349 0.90
## 10 3.42 6352 0.82
## 11 3.45 6361 0.75
## 12 3.58 6369 0.77
## 13 3.66 6546 0.78
## 14 3.78 6672 0.84
## 15 3.82 6890 0.79
## 16 3.97 7115 0.70
## 17 4.07 7327 0.68
## 18 4.25 7546 0.72
## 19 4.41 7931 0.55
## 20 4.49 8097 0.63
## 21 4.70 8468 0.56
## 22 4.58 8717 0.41
## 23 4.69 8991 0.51
## 24 4.71 9179 0.47
## 25 4.78 9318 0.32
Ejemplo regresion lineal
library(stargazer)
options(scipen = 9999)
modelo_lineal<-lm(formula = Y~X1+X2,data = Ruta)
summary(modelo_lineal)
##
## Call:
## lm(formula = Y ~ X1 + X2, data = Ruta)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.085090 -0.039102 -0.003341 0.030236 0.105692
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.56449677 0.07939598 19.705 0.00000000000000182 ***
## X1 0.23719747 0.05555937 4.269 0.000313 ***
## X2 -0.00024908 0.00003205 -7.772 0.00000009508790794 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.0533 on 22 degrees of freedom
## Multiple R-squared: 0.8653, Adjusted R-squared: 0.8531
## F-statistic: 70.66 on 2 and 22 DF, p-value: 0.000000000265
stargazer(modelo_lineal,title="Ejemplo regresion lineal", type="text",digits=8)
##
## Ejemplo regresion lineal
## ===============================================
## Dependent variable:
## ---------------------------
## Y
## -----------------------------------------------
## X1 0.23719750***
## (0.05555937)
##
## X2 -0.00024908***
## (0.00003205)
##
## Constant 1.56449700***
## (0.07939598)
##
## -----------------------------------------------
## Observations 25
## R2 0.86529610
## Adjusted R2 0.85305030
## Residual Std. Error 0.05330222 (df = 22)
## F Statistic 70.66057000*** (df = 2; 22)
## ===============================================
## Note: *p<0.1; **p<0.05; ***p<0.01
Vector de coeficientes estimados β/hat
options(scipen=999)
modelo_lineal$coefficients
## (Intercept) X1 X2
## 1.5644967711 0.2371974748 -0.0002490793
Matriz de varianza-covarianza de los parametros V[β]
var_covar<-vcov(modelo_lineal)
print(var_covar)
## (Intercept) X1 X2
## (Intercept) 0.0063037218732 0.000240996434 -0.000000982806321
## X1 0.0002409964344 0.003086843196 -0.000001675537651
## X2 -0.0000009828063 -0.000001675538 0.000000001027106
Intervalos de confianza
confint(object = modelo_lineal,level = .95)
## 2.5 % 97.5 %
## (Intercept) 1.3998395835 1.7291539588
## X1 0.1219744012 0.3524205485
## X2 -0.0003155438 -0.0001826148
Valores ajustados Y/hat
plot(modelo_lineal$fitted.values,main = "Valores Ajustados",
ylab = "Y",xlab = "casos")
modelo_lineal$fitted.values %>% as.matrix()
## [,1]
## 1 0.6765303
## 2 0.7133412
## 3 0.6991023
## 4 0.6721832
## 5 0.6837597
## 6 0.7075753
## 7 0.7397638
## 8 0.7585979
## 9 0.7943078
## 10 0.7935605
## 11 0.7984347
## 12 0.8272778
## 13 0.8021665
## 14 0.7992462
## 15 0.7544349
## 16 0.7339716
## 17 0.7048866
## 18 0.6930338
## 19 0.6350898
## 20 0.6127185
## 21 0.5701215
## 22 0.4796371
## 23 0.4374811
## 24 0.3953981
## 25 0.3773799
Residuos del modelo ϵ/hat
plot(modelo_lineal$residuals,main = "Residuos",
ylab = "Residuos",xlab = "casos")
modelo_lineal$residuals %>% as.matrix()
## [,1]
## 1 0.073469743
## 2 -0.003341163
## 3 -0.039102258
## 4 -0.062183196
## 5 0.016240338
## 6 0.012424659
## 7 0.030236216
## 8 -0.018597878
## 9 0.105692240
## 10 0.026439478
## 11 -0.048434733
## 12 -0.057277771
## 13 -0.022166535
## 14 0.040753758
## 15 0.035565142
## 16 -0.033971640
## 17 -0.024886579
## 18 0.026966239
## 19 -0.085089833
## 20 0.017281530
## 21 -0.010121525
## 22 -0.069637086
## 23 0.072518915
## 24 0.074601871
## 25 -0.057379932
Practica 2
Cargar datos
library(readr)
library(dplyr)
Mnueva<-read_csv("C:/Users/luisn/Downloads/ejercicio econometria.csv")
head(Mnueva,n=20)
## # A tibble: 14 x 3
## Y x1 x2
## <dbl> <dbl> <dbl>
## 1 320 50 7.4
## 2 450 53 5.1
## 3 370 60 4.2
## 4 470 63 3.9
## 5 420 69 1.4
## 6 500 82 2.2
## 7 570 100 7
## 8 640 104 5.7
## 9 670 113 13.1
## 10 780 130 16.4
## 11 690 150 5.1
## 12 700 181 2.9
## 13 910 202 4.5
## 14 930 217 6.2
Mnueva%>%mutate(x3=x1*x2)%>%select(Y,x1,x2,x3)->Mnueva
print(Mnueva)
## # A tibble: 14 x 4
## Y x1 x2 x3
## <dbl> <dbl> <dbl> <dbl>
## 1 320 50 7.4 370
## 2 450 53 5.1 270.
## 3 370 60 4.2 252
## 4 470 63 3.9 246.
## 5 420 69 1.4 96.6
## 6 500 82 2.2 180.
## 7 570 100 7 700
## 8 640 104 5.7 593.
## 9 670 113 13.1 1480.
## 10 780 130 16.4 2132
## 11 690 150 5.1 765
## 12 700 181 2.9 525.
## 13 910 202 4.5 909
## 14 930 217 6.2 1345.
Modelo de regresion multiple
library(stargazer)
options(scipen = 9999)
modelo_r<-lm(formula = Y~x1+x2+x3,data = Mnueva)
summary(modelo_r)
##
## Call:
## lm(formula = Y ~ x1 + x2 + x3, data = Mnueva)
##
## Residuals:
## Min 1Q Median 3Q Max
## -54.862 -34.639 -2.686 29.659 75.272
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 329.0317 85.5810 3.845 0.00324 **
## x1 1.8935 0.7226 2.621 0.02557 *
## x2 -19.2815 16.6132 -1.161 0.27276
## x3 0.2508 0.1381 1.816 0.09937 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 48.91 on 10 degrees of freedom
## Multiple R-squared: 0.9497, Adjusted R-squared: 0.9347
## F-statistic: 62.99 on 3 and 10 DF, p-value: 0.0000008497
stargazer(modelo_r,title="Modelo de Regresion Lineal", type="text",digits=8)
##
## Modelo de Regresion Lineal
## ===============================================
## Dependent variable:
## ---------------------------
## Y
## -----------------------------------------------
## x1 1.89347600**
## (0.72255180)
##
## x2 -19.28153000
## (16.61324000)
##
## x3 0.25080920*
## (0.13808420)
##
## Constant 329.03170000***
## (85.58103000)
##
## -----------------------------------------------
## Observations 14
## R2 0.94974120
## Adjusted R2 0.93466350
## Residual Std. Error 48.90988000 (df = 10)
## F Statistic 62.99002000*** (df = 3; 10)
## ===============================================
## Note: *p<0.1; **p<0.05; ***p<0.01
Vector de Coeficientes estimados
options(scipen=999)
modelo_r$coefficient
## (Intercept) x1 x2 x3
## 329.0317432 1.8934760 -19.2815258 0.2508092
Matriz de Varianza Covarianza
var_covar<-vcov(modelo_r)
print(var_covar)
## (Intercept) x1 x2 x3
## (Intercept) 7324.11290 -59.33025065 -1330.529339 10.79320150
## x1 -59.33025 0.52208115 10.997904 -0.09397975
## x2 -1330.52934 10.99790406 275.999661 -2.24756310
## x3 10.79320 -0.09397975 -2.247563 0.01906724
Intervalos de Confianza
confint(object = modelo_r,level = .95)
## 2.5 % 97.5 %
## (Intercept) 138.34532258 519.7181637
## x1 0.28353022 3.5034218
## x2 -56.29812575 17.7350742
## x3 -0.05686157 0.5584799
Valores Ajustados
plot(modelo_r$fitted.values,main = "Valores Ajustados",ylab = "Y",xlab = "casos")
modelo_r$fitted.values %>% as.matrix()
## [,1]
## 1 373.8217
## 2 398.8439
## 3 424.8618
## 4 434.7466
## 5 456.9156
## 6 487.1234
## 7 558.9751
## 8 564.7282
## 9 661.6794
## 10 793.6918
## 11 706.5864
## 12 747.4842
## 13 852.7326
## 14 957.8093
Residuos del Modelo
plot(modelo_r$residuals,main = "Residuos",ylab = "Residuos",xlab = "casos")
modelo_r$residuals %>% as.matrix()
## [,1]
## 1 -53.82165
## 2 51.15608
## 3 -54.86181
## 4 35.25340
## 5 -36.91562
## 6 12.87660
## 7 11.02490
## 8 75.27176
## 9 8.32061
## 10 -13.69180
## 11 -16.58640
## 12 -47.48422
## 13 57.26741
## 14 -27.80927