Caso de negocios 1: Costos en aerolineas

Contexto

La base 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 = Aerolínea
• T = Año
• Q = Output
• C = Costo total en $1000
• PF = Precio del combustible
• LF = Factor de carga (Utilización promedio de la capacidad de la flota)

Fuente Tabla F7.1

Instalar paquetes y llamar librerias

library(plm)
library(tidyverse)
library(forecast)
library(lavaan)
library(lavaanPlot)
library(DataExplorer)
library(ggplot2)
library(gplots)

Importar base de datos

df <- read.csv("/Users/hectordelagarzatrevino/Library/CloudStorage/GoogleDrive-a01177960@tec.mx/My Drive/LIT/8. Octavo semestre/Generación de escenarios futuros con analítica/Modulo 1/Actividades/Caso de negocios/Cost Data for U.S. Airlines.csv")

Analisis descriptivo

df$I <- as.factor(df$I)
df$Y <- df$T + 1969
summary(df)

##  I            T            C                 Q                 PF         
##  1:15   Min.   : 1   Min.   :  68978   Min.   :0.03768   Min.   : 103795  
##  2:15   1st Qu.: 4   1st Qu.: 292046   1st Qu.:0.14213   1st Qu.: 129848  
##  3:15   Median : 8   Median : 637001   Median :0.30503   Median : 357434  
##  4:15   Mean   : 8   Mean   :1122524   Mean   :0.54499   Mean   : 471683  
##  5:15   3rd Qu.:12   3rd Qu.:1345968   3rd Qu.:0.94528   3rd Qu.: 849840  
##  6:15   Max.   :15   Max.   :4748320   Max.   :1.93646   Max.   :1015610  
##        LF               Y       
##  Min.   :0.4321   Min.   :1970  
##  1st Qu.:0.5288   1st Qu.:1973  
##  Median :0.5661   Median :1977  
##  Mean   :0.5605   Mean   :1977  
##  3rd Qu.:0.5947   3rd Qu.:1981  
##  Max.   :0.6763   Max.   :1984

str(df)

## 'data.frame':    90 obs. of  7 variables:
##  $ I : Factor w/ 6 levels "1","2","3","4",..: 1 1 1 1 1 1 1 1 1 1 ...
##  $ T : int  1 2 3 4 5 6 7 8 9 10 ...
##  $ C : int  1140640 1215690 1309570 1511530 1676730 1823740 2022890 2314760 2639160 3247620 ...
##  $ Q : num  0.953 0.987 1.092 1.176 1.16 ...
##  $ PF: int  106650 110307 110574 121974 196606 265609 263451 316411 384110 569251 ...
##  $ LF: num  0.534 0.532 0.548 0.541 0.591 ...
##  $ Y : num  1970 1971 1972 1973 1974 ...

head(df)

##   I T       C        Q     PF       LF    Y
## 1 1 1 1140640 0.952757 106650 0.534487 1970
## 2 1 2 1215690 0.986757 110307 0.532328 1971
## 3 1 3 1309570 1.091980 110574 0.547736 1972
## 4 1 4 1511530 1.175780 121974 0.540846 1973
## 5 1 5 1676730 1.160170 196606 0.591167 1974
## 6 1 6 1823740 1.173760 265609 0.575417 1975

# create_report(df)
plot_missing(df)

plot_histogram(df)

plot_correlation(df)

ggplot(df, aes(x=Y, y=C, color=I, group=I)) +
  geom_line() +
  labs(title = "Costo por Aerolínea (En miles de USD)", x = "Año", y = "Costo (USD)", color = "Aerolínea") +
  theme_minimal()

ggplot(df, aes(x=Y, y=Q, color=I, group=I)) +
  geom_line() +
  labs(title = "Millas voladas (Por pasajero)", x = "Año", y = "Indice normalizado", color = "Aerolínea") +
  theme_minimal()

ggplot(df, aes(x=Y, y=PF, color=I, group=I)) +
  geom_line() +
  labs(title = "Precio del combustible", x = "Año", y = "Costo en USD", color = "Aerolínea") +
  theme_minimal()

ggplot(df, aes(x=Y, y=LF, color=I, group=I)) +
  geom_line() +
  labs(title = "Factor de carga", x = "Año", y = "Porcentaje", color = "Aerolínea") +
  theme_minimal()

Tema 1. Datos de panel

Heterogeneidad

plotmeans(C ~ I, main="Heterogeneidad entre aerolíneas", xlab="aerolínea", ylab="Costo (Miles de USD)", data=df)

Como el valor promedio (circulo) y el rango intercuartil (lineas azules) varían entre individuos, se observa presencia de heterogeneidad

Creación de datos panel

df_panel <- pdata.frame(df, index=c("I", "Y"))
df_panel <- df_panel %>% select(-c("I", "T", "Y"))

Modelo 1. Regresión agrupada (Pooled)

# El modelo de regresion agrupada es una técnica de estimación en datos donde se asume que no hay efectos individuales especificos para cada unidad (Ej. Aerolíneas) ni variaciones en el tiempo. Ignora heterogeneidad.
pooled <- plm(C ~ Q + PF + LF, data = df_panel, model = "pooling")
summary(pooled)

## Pooling Model
## 
## Call:
## plm(formula = C ~ Q + PF + LF, data = df_panel, 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

# Prueba de Breush-Pagan (BP): Para verificar si el modelo pooled es adecuado.

Modelo 2. Efectos Fijos (Within)

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

## Oneway (individual) effect Within Model
## 
## Call:
## plm(formula = C ~ Q + PF + LF, data = df_panel, 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

Modelo 3. Efectos Aleatorios (random)

walhus = plm(C ~ Q + PF + LF, data = df_panel, 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 = df_panel, 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 4. Efectos Aleatorios (random) Modelo Amemiya

amemiya = plm(C ~ Q + PF + LF, data = df_panel, model = "random")
summary(amemiya)

## Oneway (individual) effect Random Effect Model 
##    (Swamy-Arora's transformation)
## 
## Call:
## plm(formula = C ~ Q + PF + LF, data = df_panel, model = "random")
## 
## Balanced Panel: n = 6, T = 15, N = 90
## 
## Effects:
##                     var   std.dev share
## idiosyncratic 4.428e+10 2.104e+05 0.793
## individual    1.154e+10 1.074e+05 0.207
## theta: 0.5486
## 
## Residuals:
##    Min. 1st Qu.  Median 3rd Qu.    Max. 
## -535726 -238494   49890  207491  722934 
## 
## Coefficients:
##                Estimate  Std. Error z-value  Pr(>|z|)    
## (Intercept)  1.0743e+06  3.7747e+05  2.8461  0.004427 ** 
## Q            2.2886e+06  1.0949e+05 20.9015 < 2.2e-16 ***
## PF           1.1236e+00  1.0344e-01 10.8622 < 2.2e-16 ***
## LF          -3.0850e+06  7.2568e+05 -4.2512 2.126e-05 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Total Sum of Squares:    6.6198e+13
## Residual Sum of Squares: 5.8721e+12
## R-Squared:      0.91129
## Adj. R-Squared: 0.9082
## Chisq: 883.501 on 3 DF, p-value: < 2.22e-16

Modelo 5. Efectos Aleatorios (random) Modelo Nerlove

nerlove = plm(C ~ Q + PF + LF, data = df_panel, model = "random", random.method = "nerlove")
summary(nerlove)

## Oneway (individual) effect Random Effect Model 
##    (Nerlove's transformation)
## 
## Call:
## plm(formula = C ~ Q + PF + LF, data = df_panel, model = "random", 
##     random.method = "nerlove")
## 
## Balanced Panel: n = 6, T = 15, N = 90
## 
## Effects:
##                     var   std.dev share
## idiosyncratic 3.985e+10 1.996e+05 0.066
## individual    5.602e+11 7.485e+05 0.934
## theta: 0.9313
## 
## Residuals:
##    Min. 1st Qu.  Median 3rd Qu.    Max. 
## -601947 -145039   18713  154903  483623 
## 
## Coefficients:
##                Estimate  Std. Error z-value  Pr(>|z|)    
## (Intercept)  1.0752e+06  4.4535e+05  2.4142   0.01577 *  
## Q            3.2323e+06  1.6521e+05 19.5652 < 2.2e-16 ***
## PF           8.0229e-01  9.5804e-02  8.3743 < 2.2e-16 ***
## LF          -3.7338e+06  6.0963e+05 -6.1247 9.084e-10 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Total Sum of Squares:    5.1133e+13
## Residual Sum of Squares: 3.7726e+12
## R-Squared:      0.92622
## Adj. R-Squared: 0.92365
## Chisq: 1079.63 on 3 DF, p-value: < 2.22e-16

Comparando el sus R2 ajustadas, el mejor método en el modelo de efectos aleatorios es el de Walhus.

Efectos Fijos vs Efectos Aleatorios

phtest(within, walhus)

## 
##  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 serie de tiempo

df_a1= df[df$I =="1", ]
ts_a1= ts(df_a1$C, start=1970, frequency=1)

df_a2= df[df$I =="2", ]
ts_a2= ts(df_a2$C, start=1970, frequency=1)

df_a3= df[df$I =="3", ]
ts_a3= ts(df_a3$C, start=1970, frequency=1)

df_a4= df[df$I =="4", ]
ts_a4= ts(df_a4$C, start=1970, frequency=1)

df_a5= df[df$I =="5", ]
ts_a5= ts(df_a5$C, start=1970, frequency=1)

df_a6= df[df$I =="6", ]
ts_a6= ts(df_a6$C, start=1970, frequency=1)

Generar modelo ARIMA

arima_a1 <- auto.arima(ts_a1)
summary(arima_a1)

## Series: ts_a1 
## ARIMA(0,1,0) with drift 
## 
## Coefficients:
##           drift
##       257691.43
## s.e.   44509.37
## 
## sigma^2 = 2.987e+10:  log likelihood = -188.19
## AIC=380.37   AICc=381.46   BIC=381.65
## 
## Training set error measures:
##                    ME   RMSE      MAE       MPE     MAPE     MASE      ACF1
## Training set 58.86321 160892 129527.1 -1.742419 5.395122 0.502644 0.4084903

arima_a2 <- auto.arima(ts_a2)
summary(arima_a2)

## Series: ts_a2 
## ARIMA(0,2,0) 
## 
## sigma^2 = 1.392e+10:  log likelihood = -170.26
## AIC=342.53   AICc=342.89   BIC=343.09
## 
## Training set error measures:
##                    ME     RMSE      MAE      MPE     MAPE      MASE      ACF1
## Training set 11689.89 109830.2 79466.33 1.387268 3.747652 0.3056315 0.3172172

arima_a3 <- auto.arima(ts_a3)
summary(arima_a3)

## Series: ts_a3 
## ARIMA(0,1,0) with drift 
## 
## Coefficients:
##          drift
##       63155.14
## s.e.  13344.11
## 
## sigma^2 = 2.685e+09:  log likelihood = -171.32
## AIC=346.64   AICc=347.74   BIC=347.92
## 
## Training set error measures:
##                    ME     RMSE      MAE        MPE     MAPE     MASE       ACF1
## Training set 14.87618 48235.79 38474.72 -0.9277567 5.324145 0.538349 0.09130379

arima_a4 <- auto.arima(ts_a4)
summary(arima_a4)

## Series: ts_a4 
## ARIMA(0,2,0) 
## 
## sigma^2 = 1.469e+09:  log likelihood = -155.65
## AIC=313.3   AICc=313.66   BIC=313.86
## 
## Training set error measures:
##                    ME    RMSE      MAE      MPE     MAPE      MASE      ACF1
## Training set 7232.074 35684.5 27472.98 1.761789 5.046326 0.2977402 0.1925091

arima_a5 <- auto.arima(ts_a5)
summary(arima_a5)

## Series: ts_a5 
## ARIMA(1,2,0) 
## 
## Coefficients:
##           ar1
##       -0.4543
## s.e.   0.2354
## 
## sigma^2 = 775697764:  log likelihood = -151.09
## AIC=306.18   AICc=307.38   BIC=307.31
## 
## Training set error measures:
##                   ME     RMSE      MAE      MPE     MAPE      MASE        ACF1
## Training set 3061.06 24911.01 14171.99 2.393894 4.771228 0.3823654 0.008627682

arima_a6 <- auto.arima(ts_a6)
summary(arima_a6)

## Series: ts_a6 
## ARIMA(1,2,0) 
## 
## Coefficients:
##          ar1
##       0.5824
## s.e.  0.2281
## 
## sigma^2 = 386182350:  log likelihood = -146.65
## AIC=297.3   AICc=298.5   BIC=298.43
## 
## Training set error measures:
##                    ME     RMSE      MAE      MPE     MAPE      MASE       ACF1
## Training set 6829.403 17576.86 10190.16 2.076518 3.550582 0.1516841 -0.2989742

Generar el pronostico

pronostico_a6 <- forecast(arima_a6, level = 95, h=5)
pronostico_a6

##      Point Forecast   Lo 95   Hi 95
## 1985        1234478 1195962 1272994
## 1986        1471026 1364365 1577687
## 1987        1714311 1510670 1917953
## 1988        1961521 1635113 2287929
## 1989        2211016 1738872 2683160

plot(pronostico_a6, main = "Pronostico de costo total (USD)", xlab = "Año", ylab = "Dolares")

Tema 3. Modelo de ecuaciones estructurales

Estructurar el modelo

modelo <- '
          # Regresiones
          C ~ Q + PF + LF + I + Y
          Q ~ LF + PF + I
          PF ~ Y
          LF ~ I
          # Variables latentes
          # Varianzas y covarianzas
          # Intercepto
          '

Generar el analisis factorial confirmatorio (CFA)

df_escalada <- df
df_escalada$I <- as.numeric(df_escalada$I)
df_escalada <- scale(df_escalada)
cfa <- cfa(modelo, df_escalada)

Generar el modelo de ecuaciones estructurales (SEM)

lavaanPlot(cfa)