Actividad Integradora 1. Aerolineas

Contexto

El conjunto de datos es de la Universidad de Nueva York y contiene 90 observaciones que incluyen los costos de 6 aerolíneas estadounidenses durante 15 años, de 1970 a 1984.

Las variables son:

*I = Airline

*T = Year

*Q = Output, in revenue passenger miles, index number

*C = Total cost, in $1000

*PF = Fuel price

*LF = Load factor, the average capacity utilization of the fleet

Fuente:
Tabla F7.1

Instalar paquetes y llamar librerías

# Paquetes necesarios
# install.packages("WDI")
# install.packages("wbstats")
# install.packages("gplots")
# install.packages("plm")
#install.packages("DataExplorer")
library(WDI)
library(wbstats)
library(dplyr)
library(tidyverse)
library(plm)
library(gplots)
library(readxl)
library(lmtest)
library(forecast)
library(readxl)
library(lavaanPlot)
library(lavaan)
library(DataExplorer)

Tema 1. Datos de Panel

Importar la Base de Datos

df=read_csv('/Users/luisangeldiazcontreras/Library/CloudStorage/OneDrive-InstitutoTecnologicoydeEstudiosSuperioresdeMonterrey/9th season/M1/vuelos.csv')

## Rows: 90 Columns: 6
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## dbl (6): I, T, C, Q, PF, LF
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

Entender la Base de Datos

summary(df)

##        I             T            C                 Q          
##  Min.   :1.0   Min.   : 1   Min.   :  68978   Min.   :0.03768  
##  1st Qu.:2.0   1st Qu.: 4   1st Qu.: 292046   1st Qu.:0.14213  
##  Median :3.5   Median : 8   Median : 637001   Median :0.30503  
##  Mean   :3.5   Mean   : 8   Mean   :1122524   Mean   :0.54499  
##  3rd Qu.:5.0   3rd Qu.:12   3rd Qu.:1345968   3rd Qu.:0.94528  
##  Max.   :6.0   Max.   :15   Max.   :4748320   Max.   :1.93646  
##        PF                LF        
##  Min.   : 103795   Min.   :0.4321  
##  1st Qu.: 129848   1st Qu.:0.5288  
##  Median : 357434   Median :0.5661  
##  Mean   : 471683   Mean   :0.5605  
##  3rd Qu.: 849840   3rd Qu.:0.5947  
##  Max.   :1015610   Max.   :0.6763

str(df)

## spc_tbl_ [90 × 6] (S3: spec_tbl_df/tbl_df/tbl/data.frame)
##  $ I : num [1:90] 1 1 1 1 1 1 1 1 1 1 ...
##  $ T : num [1:90] 1 2 3 4 5 6 7 8 9 10 ...
##  $ C : num [1:90] 1140640 1215690 1309570 1511530 1676730 ...
##  $ Q : num [1:90] 0.953 0.987 1.092 1.176 1.16 ...
##  $ PF: num [1:90] 106650 110307 110574 121974 196606 ...
##  $ LF: num [1:90] 0.534 0.532 0.548 0.541 0.591 ...
##  - attr(*, "spec")=
##   .. cols(
##   ..   I = col_double(),
##   ..   T = col_double(),
##   ..   C = col_double(),
##   ..   Q = col_double(),
##   ..   PF = col_double(),
##   ..   LF = col_double()
##   .. )
##  - attr(*, "problems")=<externalptr>

head(df)

## # A tibble: 6 × 6
##       I     T       C     Q     PF    LF
##   <dbl> <dbl>   <dbl> <dbl>  <dbl> <dbl>
## 1     1     1 1140640 0.953 106650 0.534
## 2     1     2 1215690 0.987 110307 0.532
## 3     1     3 1309570 1.09  110574 0.548
## 4     1     4 1511530 1.18  121974 0.541
## 5     1     5 1676730 1.16  196606 0.591
## 6     1     6 1823740 1.17  265609 0.575

#create_report(df)
plot_missing(df)

plot_histogram(df)

plot_correlation(df)

Revisar Heterogeneidad

plotmeans (C ~ I, main= "Heterogeneidad entre aerolíneas", data=df)

Creación de Datos de Panel

df1 <- pdata.frame(df,index=c("I", "T"))

Modelo 1. Regresión Agrupada (pooled)

pooled <- plm(C ~ Q + PF + LF, data = df1, model = "pooling")
summary(pooled)

## Pooling Model
## 
## Call:
## plm(formula = C ~ Q + PF + LF, data = df1, model = "pooling")
## 
## Balanced Panel: n = 6, T = 15, N = 90
## 
## Residuals:
##    Min. 1st Qu.  Median 3rd Qu.    Max. 
## -520654 -250270   37333  208690  849700 
## 
## Coefficients:
##                Estimate  Std. Error t-value  Pr(>|t|)    
## (Intercept)  1.1586e+06  3.6059e+05  3.2129   0.00185 ** 
## Q            2.0261e+06  6.1807e+04 32.7813 < 2.2e-16 ***
## PF           1.2253e+00  1.0372e-01 11.8138 < 2.2e-16 ***
## LF          -3.0658e+06  6.9633e+05 -4.4027 3.058e-05 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Total Sum of Squares:    1.2647e+14
## Residual Sum of Squares: 6.8177e+12
## R-Squared:      0.94609
## Adj. R-Squared: 0.94421
## F-statistic: 503.118 on 3 and 86 DF, p-value: < 2.22e-16

Modelo 2. Efectos Fijos (within)

within <- plm(C ~ Q + PF + LF, data = df1, model = "within")
summary(within)

## Oneway (individual) effect Within Model
## 
## Call:
## plm(formula = C ~ Q + PF + LF, data = df1, model = "within")
## 
## Balanced Panel: n = 6, T = 15, N = 90
## 
## Residuals:
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
## -551783 -159259    1796       0  137226  499296 
## 
## Coefficients:
##       Estimate  Std. Error t-value  Pr(>|t|)    
## Q   3.3190e+06  1.7135e+05 19.3694 < 2.2e-16 ***
## PF  7.7307e-01  9.7319e-02  7.9437 9.698e-12 ***
## LF -3.7974e+06  6.1377e+05 -6.1869 2.375e-08 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Total Sum of Squares:    5.0776e+13
## Residual Sum of Squares: 3.5865e+12
## R-Squared:      0.92937
## Adj. R-Squared: 0.92239
## F-statistic: 355.254 on 3 and 81 DF, p-value: < 2.22e-16

Prueba: Modelo Pooled vs Modelo de Efectos Fijos

pFtest(within, pooled)

## 
##  F test for individual effects
## 
## data:  C ~ Q + PF + LF
## F = 14.595, df1 = 5, df2 = 81, p-value = 3.467e-10
## alternative hypothesis: significant effects

Modelo 3. Efectos Aleatorios - Metodo Walhus

walhus <- plm(C ~ Q + PF + LF, data = df1, model = "random", random.method = "walhus")
summary(walhus)

## Oneway (individual) effect Random Effect Model 
##    (Wallace-Hussain's transformation)
## 
## Call:
## plm(formula = C ~ Q + PF + LF, data = df1, model = "random", 
##     random.method = "walhus")
## 
## Balanced Panel: n = 6, T = 15, N = 90
## 
## Effects:
##                     var   std.dev share
## idiosyncratic 7.339e+10 2.709e+05 0.969
## individual    2.363e+09 4.861e+04 0.031
## theta: 0.1788
## 
## Residuals:
##    Min. 1st Qu.  Median 3rd Qu.    Max. 
## -524180 -243611   39332  199517  824905 
## 
## Coefficients:
##                Estimate  Std. Error z-value  Pr(>|z|)    
## (Intercept)  1.1267e+06  3.6994e+05  3.0455  0.002323 ** 
## Q            2.0647e+06  7.1927e+04 28.7051 < 2.2e-16 ***
## PF           1.2075e+00  1.0358e-01 11.6578 < 2.2e-16 ***
## LF          -3.0314e+06  7.1431e+05 -4.2438 2.198e-05 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Total Sum of Squares:    1.0182e+14
## Residual Sum of Squares: 6.5784e+12
## R-Squared:      0.93539
## Adj. R-Squared: 0.93314
## Chisq: 1245.09 on 3 DF, p-value: < 2.22e-16

Modelo 3. Efectos Aleatorios - Metodo Amemiya

amemiya <- plm(C ~ Q + PF + LF, data = df1, model = "random", random.method = "amemiya")
summary(amemiya)

## Oneway (individual) effect Random Effect Model 
##    (Amemiya's transformation)
## 
## Call:
## plm(formula = C ~ Q + PF + LF, data = df1, model = "random", 
##     random.method = "amemiya")
## 
## Balanced Panel: n = 6, T = 15, N = 90
## 
## Effects:
##                     var   std.dev share
## idiosyncratic 4.270e+10 2.066e+05 0.084
## individual    4.640e+11 6.812e+05 0.916
## theta: 0.9219
## 
## Residuals:
##    Min. 1st Qu.  Median 3rd Qu.    Max. 
## -603585 -144415   22641  158005  485417 
## 
## Coefficients:
##                Estimate  Std. Error z-value  Pr(>|z|)    
## (Intercept)  1.0746e+06  4.2105e+05  2.5522    0.0107 *  
## Q            3.2090e+06  1.6482e+05 19.4695 < 2.2e-16 ***
## PF           8.1014e-01  9.6147e-02  8.4260 < 2.2e-16 ***
## LF          -3.7168e+06  6.1330e+05 -6.0603 1.359e-09 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Total Sum of Squares:    5.1238e+13
## Residual Sum of Squares: 3.8227e+12
## R-Squared:      0.92539
## Adj. R-Squared: 0.92279
## Chisq: 1066.71 on 3 DF, p-value: < 2.22e-16

Modelo Efectos Fijos VS Modelo Efectos Aleatorios

phtest(walhus,within)

## 
##  Hausman Test
## 
## data:  C ~ Q + PF + LF
## chisq = 65.039, df = 3, p-value = 4.919e-14
## alternative hypothesis: one model is inconsistent

Tema 2. Series de tiempo

Generar la serie de tiempo

df2 <- df %>% group_by(T) %>% summarise("Cost"=sum(C))
ts <- ts(data=df2$Cost, start=1970, frequency=1)

Generar modelo ARIMA

arima <- auto.arima(ts)
summary(arima)

## Series: ts 
## ARIMA(0,2,1) 
## 
## Coefficients:
##          ma1
##       0.6262
## s.e.  0.2198
## 
## sigma^2 = 9.087e+10:  log likelihood = -182.19
## AIC=368.37   AICc=369.57   BIC=369.5
## 
## Training set error measures:
##                    ME     RMSE      MAE       MPE    MAPE      MASE        ACF1
## Training set 27996.87 269624.3 201889.4 0.7953103 2.71744 0.2597085 -0.06184266

Generar el pronóstico

pronostico <- forecast(arima, level=95, h=5)
pronostico

##      Point Forecast    Lo 95    Hi 95
## 1985       14087526 13496696 14678356
## 1986       14990145 13329820 16650471
## 1987       15892764 12881265 18904264
## 1988       16795384 12198346 21392421
## 1989       17698003 11310993 24085012

plot(pronostico, main="Costos Totales de las Aerolineas")

Tema 3. Modelos de Ecuaciones Estructurales

Generar el Modelo

modelo <- '
          #Regresiones
          Q ~ LF
          C ~ I + T + PF + LF
          LF ~ PF + I
          PF ~ T
          #Variables latentes
          #Varianzas y covarianzas
          #Intercepto
          '

Generar el diagrama

df3 <- scale(df)
df4 <- cfa(modelo, df3)
summary(df4)

## lavaan 0.6-19 ended normally after 39 iterations
## 
##   Estimator                                         ML
##   Optimization method                           NLMINB
##   Number of model parameters                        13
## 
##   Number of observations                            90
## 
## Model Test User Model:
##                                                       
##   Test statistic                               166.924
##   Degrees of freedom                                 5
##   P-value (Chi-square)                           0.000
## 
## Parameter Estimates:
## 
##   Standard errors                             Standard
##   Information                                 Expected
##   Information saturated (h1) model          Structured
## 
## Regressions:
##                    Estimate  Std.Err  z-value  P(>|z|)
##   Q ~                                                 
##     LF                0.425    0.095    4.462    0.000
##   C ~                                                 
##     I                 0.105    0.025    4.158    0.000
##     T                 0.140    0.063    2.211    0.027
##     PF                0.194    0.065    2.986    0.003
##     LF                0.271    0.100    2.726    0.006
##   LF ~                                                
##     PF                0.491    0.085    5.812    0.000
##     I                -0.346    0.085   -4.099    0.000
##   PF ~                                                
##     T                 0.931    0.038   24.233    0.000
## 
## Covariances:
##                    Estimate  Std.Err  z-value  P(>|z|)
##  .Q ~~                                                
##    .C                 0.811    0.123    6.612    0.000
## 
## Variances:
##                    Estimate  Std.Err  z-value  P(>|z|)
##    .Q                 0.810    0.121    6.708    0.000
##    .C                 0.859    0.128    6.708    0.000
##    .LF                0.636    0.095    6.708    0.000
##    .PF                0.131    0.020    6.708    0.000

lavaanPlot(df4, coef=TRUE, cov=TRUE)