EJERCICIO 1

Literal A-1 (Matrices A, P & M)

options(scipen = 999999)
# Cargamos los datos
load("C:/Users/USUARIO/Desktop/UES CICLO 1-2021/Econometria/Practicas en R/Primera Guia/Telegram Desktop/Guia 1 Archivos/modelo_ventas.RData")
# Generando la Matriz X
matriz_x<-model.matrix(modelo_ventas)
# Generando la matriz x'x
matriz_xx<-t(matriz_x)%*%(matriz_x)
# Generando la matriz A
matriz_A<-solve(matriz_xx)%*%t(matriz_x)
matriz_A[1:4,1:4]
##                          1              2             3             4
## (Intercept) -0.01128647020  0.01410377973  0.0350639188  0.0004283381
## tv          -0.00006704103  0.00003094914 -0.0006120193 -0.0002120642
## periodico    0.00139818182 -0.00190724690 -0.0025468816  0.0002293243
## radio       -0.00058002134  0.00064866654 -0.0001093284 -0.0001899710
# Generando la matriz P
matriz_P<-matriz_x%*%matriz_A
matriz_P[1:4,1:4]
##            1          2          3          4
## 1 0.03181459 0.00370346 0.01758786 0.02250872
## 2 0.00370346 0.02460480 0.03447285 0.01212022
## 3 0.01758786 0.03447285 0.06766822 0.02641047
## 4 0.02250872 0.01212022 0.02641047 0.02031981
# Generando la matriz M
n<-nrow(matriz_x)
matriz_M<-diag(n)-matriz_P
matriz_M[1:4,1:4]
##             1           2           3           4
## 1  0.96818541 -0.00370346 -0.01758786 -0.02250872
## 2 -0.00370346  0.97539520 -0.03447285 -0.01212022
## 3 -0.01758786 -0.03447285  0.93233178 -0.02641047
## 4 -0.02250872 -0.01212022 -0.02641047  0.97968019

Literal B-1 (Comparación de residuos)

library(magrittr)
# Residuos del modelo
residuos_modelo_ventas<-modelo_ventas$residuals
# Residuos por matrices
datos_modelo<-modelo_ventas$model
residuos_matrices<-matriz_M%*%datos_modelo$ventas
# Comparativa
cbind(residuos_matrices,residuos_modelo_ventas,
      residuos_modelo_ventas-residuos_matrices) %>% round(digits = 2) %>% as.data.frame()->comparacion
names(comparacion)<-c("Por_matrices","En_modelo","Diferencia")
head(comparacion,n=10)
##    Por_matrices En_modelo Diferencia
## 1        -15.93    -15.93          0
## 2         19.33     19.33          0
## 3         38.02     38.02          0
## 4        -15.43    -15.43          0
## 5          5.16      5.16          0
## 6         80.22     80.22          0
## 7        -16.35    -16.35          0
## 8        -22.89    -22.89          0
## 9        -34.40    -34.40          0
## 10        46.09     46.09          0

Literal C-1 (Auto_Valores_Positivos)

eigen(x=matriz_xx,symmetric = TRUE)->descomposicion
auto_valores<-descomposicion$values
print(auto_valores)
## [1] 311421698.6388     70252.5341     40973.4590      3714.3627        12.7735
print(auto_valores>0)
## [1] TRUE TRUE TRUE TRUE TRUE

EJERCICIO 2

Literal A-2 (Estimación del Modelo)

#Cargamos los datos
load("C:/Users/USUARIO/Desktop/UES CICLO 1-2021/Econometria/Practicas en R/Primera Guia/Telegram Desktop/Guia 1 Archivos/datos_cajas.RData")
#Generando el Modelo
modelo_cajas<-lm(formula=Tiempo~Distancia+N_cajas,data = datos_cajas)
summary(modelo_cajas)
## 
## Call:
## lm(formula = Tiempo ~ Distancia + N_cajas, data = datos_cajas)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -9.2716 -0.5405  0.5212  1.4051  2.9381 
## 
## Coefficients:
##             Estimate Std. Error t value  Pr(>|t|)    
## (Intercept)   2.3112     5.8573   0.395   0.70007    
## Distancia     0.4559     0.1468   3.107   0.00908 ** 
## N_cajas       0.8772     0.1530   5.732 0.0000943 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 3.141 on 12 degrees of freedom
## Multiple R-squared:  0.7368, Adjusted R-squared:  0.6929 
## F-statistic:  16.8 on 2 and 12 DF,  p-value: 0.0003325

Literal B-2 (Matrices A, P & M)

#Generando la matriz x
mat_x<-model.matrix(modelo_cajas)

#Generando la matriz x'x
mat_xx<-t(mat_x)%*%(mat_x)

#Generando la matriz A
mat_A<-solve(mat_xx)%*%t(mat_x)
print(mat_A)
##                        1            2            3            4            5
## (Intercept)  0.459747079  0.505626389 -0.317731768  0.707001469  0.053149816
## Distancia   -0.003015297 -0.009318829  0.018819615 -0.019989342 -0.006641453
## N_cajas     -0.017147338 -0.009890695 -0.007919488 -0.004479623  0.011082085
##                        6            7            8             9          10
## (Intercept) -0.166576988  0.633594572 -0.125532551  0.1260628274 -0.90735239
## Distancia    0.006550474 -0.009903692  0.009409808  0.0003379213  0.02334256
## N_cajas      0.002768355 -0.016090251 -0.003959744 -0.0038254420  0.01780152
##                       11           12           13            14          15
## (Intercept)  0.277217608  0.368482344  0.487274665 -0.3674581822 -0.73350489
## Distancia   -0.011931220 -0.007473259 -0.006797416  0.0001559637  0.01645417
## N_cajas      0.006862401 -0.005142468 -0.012793352  0.0238754370  0.01885861
#Generando la matriz P
mat_P<-mat_x%*%mat_A 
print(mat_P)
##              1            2           3            4           5           6
## 1   0.19781478  0.127154573  0.16766180  0.062524965 -0.03527291 0.057620774
## 2   0.12715457  0.124295239  0.03396629  0.140073563  0.05334477 0.038710181
## 3   0.16766180  0.033966286  0.35585795 -0.137368460 -0.10168744 0.123125512
## 4   0.06252497  0.140073563 -0.13736846  0.257600846  0.15524536 0.006698639
## 5  -0.03527291  0.053344771 -0.10168744  0.155245361  0.18408997 0.046742309
## 6   0.05762077  0.038710181  0.12312551  0.006698639  0.04674231 0.086318088
## 7   0.17558129  0.144648497  0.07654437  0.133523089  0.01345706 0.036955589
## 8   0.11716423  0.050316476  0.21126231 -0.035350897 -0.01751039 0.094896089
## 9   0.09794605  0.077129229  0.10132526  0.055636570  0.03786105 0.067680430
## 10 -0.02906036 -0.056765574  0.20436525 -0.131155907  0.05122193 0.136694350
## 11 -0.01209498  0.081873124 -0.13140718  0.199703669  0.18629079 0.030873007
## 12  0.09285990  0.104513848  0.01812731  0.131114317  0.07550894 0.044246890
## 13  0.15541865  0.125438973  0.08744449  0.109054124  0.01789770 0.046274418
## 14 -0.12402490 -0.005427535 -0.12246527  0.112857904  0.23285894 0.067134558
## 15 -0.05129385 -0.039271650  0.11324781 -0.060157783  0.09995191 0.116029165
##              7           8          9          10          11           12
## 1   0.17558129  0.11716423 0.09794605 -0.02906036 -0.01209498  0.092859897
## 2   0.14464850  0.05031648 0.07712923 -0.05676557  0.08187312  0.104513848
## 3   0.07654437  0.21126231 0.10132526  0.20436525 -0.13140718  0.018127310
## 4   0.13352309 -0.03535090 0.05563657 -0.13115591  0.19970367  0.131114317
## 5   0.01345706 -0.01751039 0.03786105  0.05122193  0.18629079  0.075508940
## 6   0.03695559  0.09489609 0.06768043  0.13669435  0.03087301  0.044246890
## 7   0.18301556  0.07160552 0.08894348 -0.08682757  0.04935470  0.112467995
## 8   0.07160552  0.13896449 0.08399596  0.13551596 -0.03237026  0.042396988
## 9   0.08894348  0.08399596 0.07465547  0.05440619  0.04101064  0.069478345
## 10 -0.08682757  0.13551596 0.05440619  0.34795579 -0.01326471 -0.021162536
## 11  0.04935470 -0.03237026 0.04101064 -0.01326471  0.20329083  0.095597926
## 12  0.11246799  0.04239699 0.06947834 -0.02116254  0.09559793  0.094228911
## 13  0.15702161  0.07705558 0.08545596 -0.04568349  0.04428588  0.099852268
## 14 -0.07689788 -0.02789930 0.01907176  0.16357209  0.20867158  0.042323339
## 15 -0.07939330  0.08995724 0.04540362  0.29018859  0.04818497 -0.001554438
##             13           14           15
## 1   0.15541865 -0.124024902 -0.051293849
## 2   0.12543897 -0.005427535 -0.039271650
## 3   0.08744449 -0.122465266  0.113247813
## 4   0.10905412  0.112857904 -0.060157783
## 5   0.01789770  0.232858944  0.099951911
## 6   0.04627442  0.067134558  0.116029165
## 7   0.15702161 -0.076897883 -0.079393301
## 8   0.07705558 -0.027899299  0.089957240
## 9   0.08545596  0.019071756  0.045403621
## 10 -0.04568349  0.163572088  0.290188586
## 11  0.04428588  0.208671580  0.048184973
## 12  0.09985227  0.042323339 -0.001554438
## 13  0.13743085 -0.052866482 -0.044080529
## 14 -0.05286648  0.352392093  0.210699107
## 15 -0.04408053  0.210699107  0.262089133
#Alternativamente, mat_P<-mat_x%*%solve(mat_xx)%*%t(mat_x)

#Generando la matriz M
n<-nrow(mat_x)
mat_M<-diag(n)-mat_P
print(mat_M)
##              1            2           3            4           5            6
## 1   0.80218522 -0.127154573 -0.16766180 -0.062524965  0.03527291 -0.057620774
## 2  -0.12715457  0.875704761 -0.03396629 -0.140073563 -0.05334477 -0.038710181
## 3  -0.16766180 -0.033966286  0.64414205  0.137368460  0.10168744 -0.123125512
## 4  -0.06252497 -0.140073563  0.13736846  0.742399154 -0.15524536 -0.006698639
## 5   0.03527291 -0.053344771  0.10168744 -0.155245361  0.81591003 -0.046742309
## 6  -0.05762077 -0.038710181 -0.12312551 -0.006698639 -0.04674231  0.913681912
## 7  -0.17558129 -0.144648497 -0.07654437 -0.133523089 -0.01345706 -0.036955589
## 8  -0.11716423 -0.050316476 -0.21126231  0.035350897  0.01751039 -0.094896089
## 9  -0.09794605 -0.077129229 -0.10132526 -0.055636570 -0.03786105 -0.067680430
## 10  0.02906036  0.056765574 -0.20436525  0.131155907 -0.05122193 -0.136694350
## 11  0.01209498 -0.081873124  0.13140718 -0.199703669 -0.18629079 -0.030873007
## 12 -0.09285990 -0.104513848 -0.01812731 -0.131114317 -0.07550894 -0.044246890
## 13 -0.15541865 -0.125438973 -0.08744449 -0.109054124 -0.01789770 -0.046274418
## 14  0.12402490  0.005427535  0.12246527 -0.112857904 -0.23285894 -0.067134558
## 15  0.05129385  0.039271650 -0.11324781  0.060157783 -0.09995191 -0.116029165
##              7           8           9          10          11           12
## 1  -0.17558129 -0.11716423 -0.09794605  0.02906036  0.01209498 -0.092859897
## 2  -0.14464850 -0.05031648 -0.07712923  0.05676557 -0.08187312 -0.104513848
## 3  -0.07654437 -0.21126231 -0.10132526 -0.20436525  0.13140718 -0.018127310
## 4  -0.13352309  0.03535090 -0.05563657  0.13115591 -0.19970367 -0.131114317
## 5  -0.01345706  0.01751039 -0.03786105 -0.05122193 -0.18629079 -0.075508940
## 6  -0.03695559 -0.09489609 -0.06768043 -0.13669435 -0.03087301 -0.044246890
## 7   0.81698444 -0.07160552 -0.08894348  0.08682757 -0.04935470 -0.112467995
## 8  -0.07160552  0.86103551 -0.08399596 -0.13551596  0.03237026 -0.042396988
## 9  -0.08894348 -0.08399596  0.92534453 -0.05440619 -0.04101064 -0.069478345
## 10  0.08682757 -0.13551596 -0.05440619  0.65204421  0.01326471  0.021162536
## 11 -0.04935470  0.03237026 -0.04101064  0.01326471  0.79670917 -0.095597926
## 12 -0.11246799 -0.04239699 -0.06947834  0.02116254 -0.09559793  0.905771089
## 13 -0.15702161 -0.07705558 -0.08545596  0.04568349 -0.04428588 -0.099852268
## 14  0.07689788  0.02789930 -0.01907176 -0.16357209 -0.20867158 -0.042323339
## 15  0.07939330 -0.08995724 -0.04540362 -0.29018859 -0.04818497  0.001554438
##             13           14           15
## 1  -0.15541865  0.124024902  0.051293849
## 2  -0.12543897  0.005427535  0.039271650
## 3  -0.08744449  0.122465266 -0.113247813
## 4  -0.10905412 -0.112857904  0.060157783
## 5  -0.01789770 -0.232858944 -0.099951911
## 6  -0.04627442 -0.067134558 -0.116029165
## 7  -0.15702161  0.076897883  0.079393301
## 8  -0.07705558  0.027899299 -0.089957240
## 9  -0.08545596 -0.019071756 -0.045403621
## 10  0.04568349 -0.163572088 -0.290188586
## 11 -0.04428588 -0.208671580 -0.048184973
## 12 -0.09985227 -0.042323339  0.001554438
## 13  0.86256915  0.052866482  0.044080529
## 14  0.05286648  0.647607907 -0.210699107
## 15  0.04408053 -0.210699107  0.737910867

Literal C-2 (Comparación de Residuos)

library(magrittr)
#Residuos modelo
residuos_modelo_cajas<-modelo_cajas$residuals
#Residuos por matrices
mat_Y<-datos_cajas$Tiempo
residuos_por_matrices<-mat_M%*%mat_Y
#Comparacion
comparacion_model_cajas<-cbind(residuos_modelo_cajas,residuos_por_matrices,residuos_modelo_cajas-residuos_por_matrices) %>% round(digits = 2) %>% as.data.frame()

names(comparacion_model_cajas)<-c("Residuos_modelo","Residuos_matrices","Diferencia")

print(comparacion_model_cajas)
##    Residuos_modelo Residuos_matrices Diferencia
## 1            -0.76             -0.76          0
## 2             0.13              0.13          0
## 3            -0.32             -0.32          0
## 4             2.94              2.94          0
## 5            -9.27             -9.27          0
## 6             0.77              0.77          0
## 7             1.31              1.31          0
## 8            -2.09             -2.09          0
## 9             1.43              1.43          0
## 10            0.52              0.52          0
## 11            0.52              0.52          0
## 12            1.38              1.38          0
## 13           -1.02             -1.02          0
## 14            2.89              2.89          0
## 15            1.59              1.59          0

Literal D-2 (Auto_Valores_Positivos)

descomposicion<-eigen(t(mat_x)%*%mat_x)
autovalores<-descomposicion$values
print(autovalores)
## [1] 16976.7781334   709.9345923     0.2872743
print(autovalores>0)
## [1] TRUE TRUE TRUE

EJERCICIO 3

Literaal A-3 (Matrices A, P & M)

# Cargamos los datos
load("C:/Users/USUARIO/Desktop/UES CICLO 1-2021/Econometria/Practicas en R/Primera Guia/Telegram Desktop/Guia 1 Archivos/modelo_estimado.RData")
# Generamos la matriz x
MAT_X<-model.matrix(modelo_estimado_1)
# Generamos la matriz x'x
MAT_XX<-t(MAT_X)%*%MAT_X
# Generamos la matriz A
MAT_A<-solve(MAT_XX)%*%t(MAT_X)
MAT_A[1:3,1:3]
##                       1            2            3
## (Intercept) -0.12023796  0.007496216  0.043732382
## poverty     -0.01182361  0.003994776  0.008825494
## single       0.02723384 -0.003960021 -0.013241432
# Generando la matriz P
MAT_P<-MAT_X%*%MAT_A
MAT_P[1:4,1:4]
##             1           2           3          4
## 1  0.16161108 -0.01277963 -0.06530809 0.02720791
## 2 -0.01277963  0.03146508  0.04501952 0.02109951
## 3 -0.06530809  0.04501952  0.07855895 0.01942366
## 4  0.02720791  0.02109951  0.01942366 0.02234121
# Generando la matriz M
n<-nrow(MAT_X)
MAT_M<-diag(n)-MAT_P
MAT_M[1:4,1:4]
##             1           2           3           4
## 1  0.83838892  0.01277963  0.06530809 -0.02720791
## 2  0.01277963  0.96853492 -0.04501952 -0.02109951
## 3  0.06530809 -0.04501952  0.92144105 -0.01942366
## 4 -0.02720791 -0.02109951 -0.01942366  0.97765879

Literal B-3 (Comparación de Residuos)

# Residuos por modelo
Residuos_estimados<-resid(modelo_estimado_1)
# Residuos por matrices
Datos_Modelo<-modelo_estimado_1$model
y<-Datos_Modelo$crime
Residuos_MAT<- MAT_M%*%y
# Comparativa
comparativa_residuos<-cbind(Residuos_estimados,Residuos_MAT,Residuos_estimados-Residuos_MAT)%>%round(digits = 2)%>%as.data.frame()
names(comparativa_residuos)<-c("Resid_Model","Resid_Mat","Dif")
head(comparativa_residuos,n=10)
##    Resid_Model Resid_Mat Dif
## 1      -311.71   -311.71   0
## 2       116.80    116.80   0
## 3        45.25     45.25   0
## 4       -34.45    -34.45   0
## 5       243.00    243.00   0
## 6      -145.12   -145.12   0
## 7        86.13     86.13   0
## 8        88.31     88.31   0
## 9       689.82    689.82   0
## 10     -163.29   -163.29   0

Literal C-3 (Auto_Valores_Positivos)

Descomposicion<-eigen(MAT_XX)
Auto_Valores<-Descomposicion$values
print(Auto_Valores)
## [1] 17956.580914   279.157317     1.681762
print(Auto_Valores>0)
## [1] TRUE TRUE TRUE

EJERCICIO 4

Literal A-4 (Ecuación de Inversión, formato APA)

#Carga de Datos
library(readxl)
Investiment_Equation <- read_excel("C:/Users/USUARIO/Desktop/UES CICLO 1-2021/Econometria/Practicas en R/Primera Guia/Telegram Desktop/Guia 1 Archivos/Investiment_Equation.xlsx")
#Generación la ecuación de inversión
ecuacion_inversion<-lm(formula = InvReal~Trend+Inflation+PNBr+Interest,data = Investiment_Equation)
library(stargazer)
library(magrittr)
stargazer(ecuacion_inversion,title="Ecuacion de inversion",type = "text")
## 
## Ecuacion de inversion
## ===============================================
##                         Dependent variable:    
##                     ---------------------------
##                               InvReal          
## -----------------------------------------------
## Trend                        -0.016***         
##                               (0.002)          
##                                                
## Inflation                     0.00002          
##                               (0.001)          
##                                                
## PNBr                         0.665***          
##                               (0.054)          
##                                                
## Interest                      -0.240*          
##                               (0.120)          
##                                                
## Constant                     -0.503***         
##                               (0.054)          
##                                                
## -----------------------------------------------
## Observations                    15             
## R2                             0.973           
## Adjusted R2                    0.962           
## Residual Std. Error       0.007 (df = 10)      
## F Statistic           90.089*** (df = 4; 10)   
## ===============================================
## Note:               *p<0.1; **p<0.05; ***p<0.01

Literal B-4 (Residuos mediante matriz M)

#Generando la matriz M. Recordemos que M=I-P & P=XA

#Generamos x
Mat_x<-model.matrix(ecuacion_inversion)
# Matriz x'x
Mat_xx<-t(Mat_x)%*%(Mat_x)
# Matriz A
Mat_A<-solve(Mat_xx)%*%t(Mat_x)
#Generamos P
Mat_P<-Mat_x%*%Mat_A
#Habiendo Optenido "P" ahora generamos "M"
n<-nrow(Mat_x)
Mat_M<-diag(n)-Mat_P
#Alternativamente podemos calcular "M" de la siguente manera: Mat_M_Alter<-diag(n)-Mat_x%*%solve(t(Mat_x)%*%Mat_x)%*%t(Mat_x)

#Generando los Residuos
Y<-Investiment_Equation$InvReal
Residuos<-Mat_M%*%Y
print(Residuos)
##             [,1]
## 1  -0.0100602233
## 2  -0.0009290882
## 3   0.0029656679
## 4   0.0078576839
## 5   0.0028109133
## 6   0.0006259732
## 7   0.0075909286
## 8  -0.0055352778
## 9  -0.0037254127
## 10  0.0006953129
## 11  0.0019904770
## 12 -0.0001288433
## 13 -0.0101976729
## 14  0.0068712384
## 15 -0.0008316770

Literal C-4 (Intervalo de confianza del 93% para el inpacto del PNBr en la inversión)

confint(ecuacion_inversion,parm = "PNBr",level = 0.93)
##         3.5 %   96.5 %
## PNBr 0.554777 0.774317

Interpretació: Se tiene la confianza de que en el 93% de las veces en que hechemos a correr el modelo, una variación en el PNBr de 1 millon, ocacionará una variación en el nivél de inversión que ronde entre 0.55 millomes como mínimo y un 0.77 millones como máximo.

EJERCICIO 5

Literal A-5 (Residuos del modelo)

# Carga de datos
load("C:/Users/USUARIO/Desktop/UES CICLO 1-2021/Econometria/Practicas en R/Primera Guia/Telegram Desktop/Guia 1 Archivos/consumption_equation.RData")
# Calculando los residuos
n<-nrow(P)
M<-diag(n)-P
resid<-M%*%C
head(resid,n=20)
##          [,1]
## 1   -5.859103
## 2    2.605057
## 3   45.765735
## 4   31.102448
## 5  -21.037889
## 6    7.008120
## 7   17.859663
## 8   10.705631
## 9   22.002328
## 10  -2.689665
## 11   7.784083
## 12 -13.127696
## 13  17.521565
## 14  17.304695
## 15 -16.308260
## 16  -5.255508
## 17   2.788211
## 18 -16.379339
## 19 -14.327554
## 20  11.749135

Literal B-5 (Varianza del error del Modelo)

#sigma cuadrado
k<-4
var_error<-t(resid)%*%(resid)/n-k
# Convertimos var_error de una matriz a un escalar
var_error<-as.vector(var_error)
print(var_error)
## [1] 1318.913

Literal C-5 (Matriz de varianza y covarianza)

var_co_var<-var_error*solve(XX)
print(var_co_var)
##               (Intercept)             Yd               W             I
## (Intercept) 151.874861381 -0.08616035509  0.008927474359  9.7100781972
## Yd           -0.086160355  0.00017457489 -0.000030250443 -0.0067296849
## W             0.008927474 -0.00003025044  0.000005691765  0.0003871057
## I             9.710078197 -0.00672968492  0.000387105701  4.9113816007

Literal D-5 (calcular las estimaciones)

C_estimada<- P%*%C
Cuadro_C_estimada<-as.data.frame(cbind(C,C_estimada,resid))
names(Cuadro_C_estimada)<-c("C_observado","C_estimada","Residuos")
head(Cuadro_C_estimada,n=20)
##    C_observado C_estimada   Residuos
## 1        976.4   982.2591  -5.859103
## 2        998.1   995.4949   2.605057
## 3       1025.3   979.5343  45.765735
## 4       1090.9  1059.7976  31.102448
## 5       1107.1  1128.1379 -21.037889
## 6       1142.4  1135.3919   7.008120
## 7       1197.2  1179.3403  17.859663
## 8       1221.9  1211.1944  10.705631
## 9       1310.4  1288.3977  22.002328
## 10      1348.8  1351.4897  -2.689665
## 11      1381.8  1374.0159   7.784083
## 12      1393.0  1406.1277 -13.127696
## 13      1470.7  1453.1784  17.521565
## 14      1510.8  1493.4953  17.304695
## 15      1541.2  1557.5083 -16.308260
## 16      1617.3  1622.5555  -5.255508
## 17      1684.0  1681.2118   2.788211
## 18      1784.8  1801.1793 -16.379339
## 19      1897.6  1911.9276 -14.327554
## 20      2006.1  1994.3509  11.749135

EJERCICIO 6

Literal A-6 (Ecuacion de ventas en APA)

library(stargazer)
library(readxl)
# Cargamos la data
load("C:/Users/USUARIO/Desktop/UES CICLO 1-2021/Econometria/Practicas en R/Primera Guia/Telegram Desktop/Guia 1 Archivos/datos_ventas.RData")
modelo_ventas<-lm(formula = ventas~tv+radio+periodico,data = datos_ventas)
stargazer(modelo_ventas,title = "Ecuacion_de_ventas",type = "text")
## 
## Ecuacion
## ===============================================
##                         Dependent variable:    
##                     ---------------------------
##                               ventas           
## -----------------------------------------------
## tv                             0.045           
##                               (0.118)          
##                                                
## radio                        -3.450***         
##                               (0.206)          
##                                                
## periodico                    18.485***         
##                               (0.563)          
##                                                
## Constant                    -33.289***         
##                               (7.172)          
##                                                
## -----------------------------------------------
## Observations                    200            
## R2                             0.847           
## Adjusted R2                    0.844           
## Residual Std. Error      33.875 (df = 196)     
## F Statistic          360.758*** (df = 3; 196)  
## ===============================================
## Note:               *p<0.1; **p<0.05; ***p<0.01

Literal B-6: (Residuos mediante matriz M)

# Generando la Matriz M
mat_x_6<-model.matrix(modelo_ventas)
mat_xx_6<-t(mat_x_6)%*%(mat_x_6)
mat_A_6<-solve(mat_xx_6)%*%t(mat_x_6)
mat_P_6<-mat_x_6%*%mat_A_6
n<-nrow(mat_x_6)
mat_M_6<-diag(n)-mat_P_6
# Usando M para calcular los Residuos
Y_6<-datos_ventas$ventas
Resid_6<-mat_M_6%*%Y_6
head(Resid_6,n=10)
##         [,1]
## 1  -17.85246
## 2   19.08216
## 3   33.79319
## 4  -17.35090
## 5   10.25721
## 6   74.20385
## 7  -15.24652
## 8  -23.42430
## 9  -39.64052
## 10  45.16139

Literal C=6: (Intervalo de confianza del 96.8% para el impaco del gasto en tv en las ventas)

confint(modelo_ventas,parm ="tv",level = 0.968)
##         1.6 %    98.4 %
## tv -0.2097376 0.2998052

Interpretación: De forma individual el gasto en TV no es significativo para explicar la variación de las ventas, ya que se incluye el “0” dentro del intervalo.