Ejercicio de Pruebas de Normalidad

library(wooldridge)

## Warning: package 'wooldridge' was built under R version 4.5.3

data(hprice1)
head(force(hprice1), n = 5)

##   price assess bdrms lotsize sqrft colonial   lprice  lassess llotsize   lsqrft
## 1   300  349.1     4    6126  2438        1 5.703783 5.855359 8.720297 7.798934
## 2   370  351.5     3    9903  2076        1 5.913503 5.862210 9.200593 7.638198
## 3   191  217.7     3    5200  1374        0 5.252274 5.383118 8.556414 7.225482
## 4   195  231.8     3    4600  1448        1 5.273000 5.445875 8.433811 7.277938
## 5   373  319.1     4    6095  2514        1 5.921578 5.765504 8.715224 7.829630

1. Estimacion del modelo.

modelo_estimado <- lm(price ~ lotsize + sqrft + bdrms, data = hprice1)

summary(modelo_estimado)

## 
## Call:
## lm(formula = price ~ lotsize + sqrft + bdrms, data = hprice1)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -120.026  -38.530   -6.555   32.323  209.376 
## 
## Coefficients:
##               Estimate Std. Error t value Pr(>|t|)    
## (Intercept) -2.177e+01  2.948e+01  -0.739  0.46221    
## lotsize      2.068e-03  6.421e-04   3.220  0.00182 ** 
## sqrft        1.228e-01  1.324e-02   9.275 1.66e-14 ***
## bdrms        1.385e+01  9.010e+00   1.537  0.12795    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 59.83 on 84 degrees of freedom
## Multiple R-squared:  0.6724, Adjusted R-squared:  0.6607 
## F-statistic: 57.46 on 3 and 84 DF,  p-value: < 2.2e-16

Ajuste de los residuos a la Distribución Normal.

Verificando el ajuste de los residuos a la distribución normal, se usará la librería fitdistrplus.

library(fitdistrplus)

## Warning: package 'fitdistrplus' was built under R version 4.5.3

## Cargando paquete requerido: MASS

## 
## Adjuntando el paquete: 'MASS'

## The following object is masked from 'package:wooldridge':
## 
##     cement

## Cargando paquete requerido: survival

fit_normal <- fitdist(data = modelo_estimado$residuals, distr = "norm")

plot(fit_normal)

# 2.Verique el supuesto de normalidad, a través de:

a) Prueba de Normalidad de Jarque Bera

#Usando tseries.

library(tseries)

## Warning: package 'tseries' was built under R version 4.5.3

## Registered S3 method overwritten by 'quantmod':
##   method            from
##   as.zoo.data.frame zoo

salida_JB<-jarque.bera.test(modelo_estimado$residuals)
salida_JB

## 
##  Jarque Bera Test
## 
## data:  modelo_estimado$residuals
## X-squared = 32.278, df = 2, p-value = 9.794e-08

library(fastGraph)

## Warning: package 'fastGraph' was built under R version 4.5.3

alpha_sig <- 0.05
JB <- salida_JB$statistic
gl <- salida_JB$parameter
VC <- qchisq(1 - alpha_sig, gl, lower.tail = TRUE)

shadeDist(JB,
          ddist = "dchisq",
          parm1 = gl,
          lower.tail = FALSE,
          xmin = 0,
          sub = paste("VC:", round(VC,2), " ", "JB:", round(JB,2)))

cat("JB=", salida_JB$statistic, "\n")

## JB= 32.27791

cat("p-value=", salida_JB$p.value, "\n")

## p-value= 9.793561e-08

En este caso, dado que el p-value = 9.793561e-08 < 0.05, se rechaza la hipótesis nula de normalidad, por lo que los residuos no siguen una distribución normal.

b) Prueba de Kolmogorov Smirnov -Lilliefors

#Cálculo Manual

library(dplyr)

## Warning: package 'dplyr' was built under R version 4.5.3

## 
## Adjuntando el paquete: 'dplyr'

## The following object is masked from 'package:MASS':
## 
##     select

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

library(gt)

## Warning: package 'gt' was built under R version 4.5.3

library(gtExtras)

## Warning: package 'gtExtras' was built under R version 4.5.3

## 
## Adjuntando el paquete: 'gtExtras'

## The following object is masked from 'package:MASS':
## 
##     select

# Residuos de TU modelo
residuos <- modelo_estimado$residuals

# Construcción de la tabla KS
residuos %>%
  as_tibble() %>%
  mutate(posicion = row_number()) %>%
  arrange(value) %>%
  mutate(dist1 = row_number()/n()) %>%
  mutate(dist2 = (row_number()-1)/n()) %>%
  mutate(zi = as.vector(scale(value, center = TRUE))) %>%
  mutate(pi = pnorm(zi, lower.tail = TRUE)) %>%
  mutate(dif1 = abs(dist1 - pi)) %>%
  mutate(dif2 = abs(dist2 - pi)) %>%
  rename(residuales = value) -> tabla_KS

tabla_KS %>%
  gt() %>%
  tab_header("Tabla para calcular el Estadístico KS") %>%
  tab_source_note(source_note = "Fuente: Elaboración propia") %>%
  
 
  tab_style(
    style = list(
      cell_fill(color = "#A569BD"),
      cell_text(style = "italic")
    ),
    locations = cells_body(
      columns = dif1,
      rows = dif1 == max(dif1)
    )
  ) %>%
  
  tab_style(
    style = list(
      cell_fill(color = "#3498DB"),
      cell_text(style = "italic")
    ),
    locations = cells_body(
      columns = dif2,
      rows = dif2 == max(dif2)
    )
  )

Tabla para calcular el Estadístico KS
residuales	posicion	dist1	dist2	zi	pi	dif1	dif2
-120.026447	81	0.01136364	0.00000000	-2.041515459	0.02059981	0.0092361731	0.0205998094
-115.508697	77	0.02272727	0.01136364	-1.964673586	0.02472601	0.0019987418	0.0133623781
-107.080889	24	0.03409091	0.02272727	-1.821326006	0.03427866	0.0001877487	0.0115513850
-91.243980	48	0.04545455	0.03409091	-1.551957925	0.06033615	0.0148816002	0.0262452366
-85.461169	12	0.05681818	0.04545455	-1.453598781	0.07302879	0.0162106057	0.0275742421
-77.172687	32	0.06818182	0.05681818	-1.312620980	0.09465535	0.0264735301	0.0378371665
-74.702719	54	0.07954545	0.06818182	-1.270609602	0.10193378	0.0223883300	0.0337519664
-65.502849	39	0.09090909	0.07954545	-1.114130117	0.13261169	0.0417025941	0.0530662305
-63.699108	69	0.10227273	0.09090909	-1.083450505	0.13930425	0.0370315271	0.0483951634
-62.566594	83	0.11363636	0.10227273	-1.064187703	0.14362184	0.0299854747	0.0413491110
-59.845223	36	0.12500000	0.11363636	-1.017900230	0.15436269	0.0293626861	0.0407263225
-54.466158	13	0.13636364	0.12500000	-0.926408352	0.17711690	0.0407532663	0.0521169027
-54.300415	14	0.14772727	0.13636364	-0.923589260	0.17785010	0.0301228311	0.0414864675
-52.129801	15	0.15909091	0.14772727	-0.886669532	0.18762842	0.0285375141	0.0399011505
-51.441108	17	0.17045455	0.15909091	-0.874955638	0.19079902	0.0203444766	0.0317081129
-48.704980	47	0.18181818	0.17045455	-0.828417174	0.20371714	0.0218989601	0.0332625965
-48.350295	29	0.19318182	0.18181818	-0.822384375	0.20542908	0.0122472664	0.0236109028
-47.855859	11	0.20454545	0.19318182	-0.813974573	0.20782976	0.0032843043	0.0146479407
-45.639765	1	0.21590909	0.20454545	-0.776281294	0.21879146	0.0028823668	0.0142460032
-43.142550	9	0.22727273	0.21590909	-0.733806463	0.23153335	0.0042606233	0.0156242596
-41.749618	57	0.23863636	0.22727273	-0.710114247	0.23881665	0.0001802823	0.0115439187
-40.869022	27	0.25000000	0.23863636	-0.695136302	0.24348494	0.0065150566	0.0048485798
-37.749811	34	0.26136364	0.25000000	-0.642082009	0.26040997	0.0009536682	0.0104099682
-36.663785	71	0.27272727	0.26136364	-0.623609925	0.26644190	0.0062853771	0.0050782592
-36.646568	79	0.28409091	0.27272727	-0.623317083	0.26653809	0.0175528221	0.0061891857
-33.801248	37	0.29545455	0.28409091	-0.574921384	0.28267223	0.0127823120	0.0014186757
-29.766931	16	0.30681818	0.29545455	-0.506302171	0.30632227	0.0004959124	0.0108677240
-26.696234	22	0.31818182	0.30681818	-0.454073044	0.32488813	0.0067063089	0.0180699452
-24.271531	23	0.32954545	0.31818182	-0.412831567	0.33986501	0.0103195566	0.0216831929
-23.651448	86	0.34090909	0.32954545	-0.402284648	0.34373728	0.0028281851	0.0141918214
-19.683427	88	0.35227273	0.34090909	-0.334793052	0.36889060	0.0166178738	0.0279815102
-17.817835	10	0.36363636	0.35227273	-0.303061413	0.38092153	0.0172851663	0.0286488027
-16.762094	60	0.37500000	0.36363636	-0.285104441	0.38778206	0.0127820638	0.0241457002
-16.596960	21	0.38636364	0.37500000	-0.282295711	0.38885839	0.0024947507	0.0138583870
-16.271207	58	0.39772727	0.38636364	-0.276755010	0.39098411	0.0067431583	0.0046204781
-13.815798	56	0.40909091	0.39772727	-0.234991254	0.40710776	0.0019831485	0.0093804879
-13.462160	75	0.42045455	0.40909091	-0.228976273	0.40944368	0.0110108666	0.0003527698
-12.081520	4	0.43181818	0.42045455	-0.205493119	0.41859344	0.0132247451	0.0018611087
-11.629207	51	0.44318182	0.43181818	-0.197799788	0.42160086	0.0215809622	0.0102173258
-11.312669	74	0.45454545	0.44318182	-0.192415834	0.42370825	0.0308372092	0.0194735728
-8.236558	3	0.46590909	0.45454545	-0.140094626	0.44429261	0.0216164775	0.0102528411
-7.662789	70	0.47727273	0.46590909	-0.130335452	0.44815052	0.0291222111	0.0177585748
-6.752801	67	0.48863636	0.47727273	-0.114857588	0.45427900	0.0343573625	0.0229937262
-6.707262	31	0.50000000	0.48863636	-0.114083016	0.45458599	0.0454140074	0.0340503710
-6.402439	85	0.51136364	0.50000000	-0.108898313	0.45664157	0.0547220642	0.0433584278
-5.446904	82	0.52272727	0.51136364	-0.092645733	0.46309251	0.0596347676	0.0482711313
-3.537785	43	0.53409091	0.52272727	-0.060173762	0.47600862	0.0580822876	0.0467186512
-2.824941	61	0.54545455	0.53409091	-0.048049090	0.48083856	0.0646159857	0.0532523493
-2.745208	68	0.55681818	0.54545455	-0.046692922	0.48137899	0.0754391961	0.0640755598
-0.195089	65	0.56818182	0.55681818	-0.003318245	0.49867621	0.0695056040	0.0581419676
1.399296	55	0.57954545	0.56818182	0.023800450	0.50949411	0.0700513452	0.0586877088
5.363331	26	0.59090909	0.57954545	0.091224254	0.53634280	0.0545662924	0.0432026561
6.700640	53	0.60227273	0.59090909	0.113970383	0.54536936	0.0569033628	0.0455397265
7.386314	80	0.61363636	0.60227273	0.125632935	0.54998875	0.0636476093	0.0522839730
9.099900	41	0.62500000	0.61363636	0.154779103	0.56150227	0.0634977329	0.0521340965
12.433611	46	0.63636364	0.62500000	0.211481796	0.58374433	0.0526193043	0.0412556680
16.718018	62	0.64772727	0.63636364	0.284354766	0.61193074	0.0357965328	0.0244328965
18.093192	5	0.65909091	0.64772727	0.307744934	0.62086179	0.0382291219	0.0268654856
18.801816	38	0.67045455	0.65909091	0.319797835	0.62543921	0.0450153400	0.0336517036
19.168108	33	0.68181818	0.67045455	0.326028052	0.62779843	0.0540197476	0.0426561112
19.219211	72	0.69318182	0.68181818	0.326897255	0.62812720	0.0650546167	0.0536909803
20.334434	59	0.70454545	0.69318182	0.345865960	0.63527827	0.0692671805	0.0579035442
24.909926	78	0.71590909	0.70454545	0.423689939	0.66410402	0.0518050676	0.0404414312
26.236229	40	0.72727273	0.71590909	0.446248874	0.67229126	0.0549814685	0.0436178321
30.924022	25	0.73863636	0.72727273	0.525982978	0.70054998	0.0380863808	0.0267227444
32.253952	45	0.75000000	0.73863636	0.548603608	0.70836125	0.0416387548	0.0302751184
32.529367	49	0.76136364	0.75000000	0.553288104	0.70996693	0.0513967091	0.0400330727
32.675968	18	0.77272727	0.76136364	0.555781630	0.71081993	0.0619073452	0.0505437088
33.275839	20	0.78409091	0.77272727	0.565984762	0.71429793	0.0697929786	0.0584293423
36.031430	52	0.79545455	0.78409091	0.612854281	0.73001365	0.0654408934	0.0540772571
37.147186	84	0.80681818	0.79545455	0.631832029	0.73625168	0.0705665028	0.0592028664
40.320875	7	0.81818182	0.80681818	0.685812928	0.75358446	0.0645973596	0.0532337232
44.334467	30	0.82954545	0.81818182	0.754079634	0.77459930	0.0549461574	0.0435825211
46.907165	28	0.84090909	0.82954545	0.797838357	0.78751785	0.0533912405	0.0420276041
54.418366	87	0.85227273	0.84090909	0.925595465	0.82267187	0.0296008528	0.0182372164
55.091131	35	0.86363636	0.85227273	0.937038450	0.82563061	0.0380057535	0.0266421172
55.470305	44	0.87500000	0.86363636	0.943487765	0.82728426	0.0477157353	0.0363520989
62.939597	6	0.88636364	0.87500000	1.070532059	0.85781006	0.0285535797	0.0171899433
66.478628	50	0.89772727	0.88636364	1.130727018	0.87091500	0.0268122757	0.0154486394
67.426518	63	0.90909091	0.89772727	1.146849569	0.87427810	0.0348128083	0.0234491719
67.603959	19	0.92045455	0.90909091	1.149867648	0.87490081	0.0455537393	0.0341901029
69.707122	64	0.93181818	0.92045455	1.185640095	0.88211777	0.0497004123	0.0383367759
69.843246	8	0.94318182	0.93181818	1.187955411	0.88257451	0.0606073068	0.0492436705
74.848732	2	0.95454545	0.94318182	1.273093116	0.89850750	0.0560379553	0.0446743189
112.729191	66	0.96590909	0.95454545	1.917397313	0.97240626	0.0064971714	0.0178608078
163.795081	73	0.97727273	0.96590909	2.785970904	0.99733162	0.0200588896	0.0314225260
198.660139	42	0.98863636	0.97727273	3.378986513	0.99963623	0.0109998685	0.0223635048
209.375830	76	1.00000000	0.98863636	3.561248407	0.99981545	0.0001845478	0.0111790885
Fuente: Elaboración propia

#Calculo del Estadistico.

# Cálculo del estadístico D (KS)
D <- max(max(tabla_KS$dif1), max(tabla_KS$dif2))

# Mostrar resultado
print(D)

## [1] 0.0754392

En este caso dado que 0.0754392<0.1726 No se rechaza la Hipótesis Nula: ϵ∼N(0,σ2), por lo que los residuos siguen una distribución normal.

Usando nortest

library(nortest)

prueba_KS <- lillie.test(modelo_estimado$residuals)

prueba_KS

## 
##  Lilliefors (Kolmogorov-Smirnov) normality test
## 
## data:  modelo_estimado$residuals
## D = 0.075439, p-value = 0.2496

p.value <- prueba_KS$p.value

p.value

## [1] 0.2496425

En este caso dado que 0.2496425>0.05 No se rechaza la Hipótesis Nula: ϵ∼N(0,σ2) , por lo que los residuos siguen una distribución normal.

c) Prueba de Shapiro - Wilk

#Cálculo Manual

library(dplyr)
library(gt)

# Residuos de tu modelo
residuos <- modelo_estimado$residuals

# Construcción de la tabla SW
residuos %>%  
  as_tibble() %>%
  rename(residuales = value) %>%
  arrange(residuales) %>%
  mutate(pi = (row_number() - 0.375)/(n() + 0.25)) %>%
  mutate(mi = qnorm(pi, lower.tail = TRUE)) %>% 
  mutate(ai = 0) -> tabla_SW

# Cálculos auxiliares
m <- sum(tabla_SW$mi^2)
n <- nrow(tabla_SW)  
theta <- 1/sqrt(n)

# Cálculo de coeficientes ai
tabla_SW$ai[n] <- -2.706056*theta^5 + 4.434685*theta^4 - 2.071190*theta^3 - 0.147981*theta^2 + 0.2211570*theta + tabla_SW$mi[n]/sqrt(m)

tabla_SW$ai[n-1] <- -3.582633*theta^5 + 5.682633*theta^4 - 1.752461*theta^3 - 0.293762*theta^2 + 0.042981*theta + tabla_SW$mi[n-1]/sqrt(m)

tabla_SW$ai[1] <- -tabla_SW$ai[n]
tabla_SW$ai[2] <- -tabla_SW$ai[n-1]

omega <- (m - 2*tabla_SW$mi[n]^2 - 2*tabla_SW$mi[n-1]^2) /
         (1 - 2*tabla_SW$ai[n]^2 - 2*tabla_SW$ai[n-1]^2)

tabla_SW$ai[3:(n-2)] <- tabla_SW$mi[3:(n-2)] / sqrt(omega)

# Cálculo final
tabla_SW %>% 
  mutate(ai_ui = ai * residuales,
         ui2 = residuales^2) -> tabla_SW

# Mostrar tabla bonita
tabla_SW %>%
  gt() %>%
  tab_header("Tabla para calcular el Estadístico W") %>%
  tab_source_note(source_note = "Fuente: Elaboración propia")

Tabla para calcular el Estadístico W
residuales	pi	mi	ai	ai_ui	ui2
-120.026447	0.007082153	-2.45306927	-0.286093929	34.338837782	1.440635e+04
-115.508697	0.018413598	-2.08767462	-0.226331231	26.143225495	1.334226e+04
-107.080889	0.029745042	-1.88455395	-0.201511408	21.578020632	1.146632e+04
-91.243980	0.041076487	-1.73832835	-0.185875811	16.960048752	8.325464e+03
-85.461169	0.052407932	-1.62194155	-0.173430814	14.821600075	7.303611e+03
-77.172687	0.063739377	-1.52411994	-0.162970954	12.576906330	5.955624e+03
-74.702719	0.075070822	-1.43903134	-0.153872609	11.494702279	5.580496e+03
-65.502849	0.086402266	-1.36324747	-0.145769197	9.548297773	4.290623e+03
-63.699108	0.097733711	-1.29457343	-0.138426027	8.817614500	4.057576e+03
-62.566594	0.109065156	-1.23151500	-0.131683320	8.238976839	3.914579e+03
-59.845223	0.120396601	-1.17300649	-0.125427129	7.506214499	3.581451e+03
-54.466158	0.131728045	-1.11825971	-0.119573169	6.512691096	2.966562e+03
-54.300415	0.143059490	-1.06667420	-0.114057239	6.193355472	2.948535e+03
-52.129801	0.154390935	-1.01778137	-0.108829231	5.673246083	2.717516e+03
-51.441108	0.165722380	-0.97120790	-0.103849228	5.342119306	2.646188e+03
-48.704980	0.177053824	-0.92665123	-0.099084876	4.825926905	2.372175e+03
-48.350295	0.188385269	-0.88386232	-0.094509548	4.569564512	2.337751e+03
-47.855859	0.199716714	-0.84263354	-0.090101040	4.311862673	2.290183e+03
-45.639765	0.211048159	-0.80278966	-0.085840618	3.917745629	2.082988e+03
-43.142550	0.222379603	-0.76418130	-0.081712307	3.525277277	1.861280e+03
-41.749618	0.233711048	-0.72667986	-0.077702356	3.244043648	1.743031e+03
-40.869022	0.245042493	-0.69017366	-0.073798824	3.016085791	1.670277e+03
-37.749811	0.256373938	-0.65456498	-0.069991263	2.642156946	1.425048e+03
-36.663785	0.267705382	-0.61976766	-0.066270458	2.429725818	1.344233e+03
-36.646568	0.279036827	-0.58570518	-0.062628228	2.295109622	1.342971e+03
-33.801248	0.290368272	-0.55230918	-0.059057264	1.996209250	1.142524e+03
-29.766931	0.301699717	-0.51951819	-0.055550992	1.653582575	8.860702e+02
-26.696234	0.313031161	-0.48727661	-0.052103467	1.390966354	7.126889e+02
-24.271531	0.324362606	-0.45553386	-0.048709282	1.182248861	5.891072e+02
-23.651448	0.335694051	-0.42424369	-0.045363489	1.072912217	5.593910e+02
-19.683427	0.347025496	-0.39336354	-0.042061540	0.827915257	3.874373e+02
-17.817835	0.358356941	-0.36285409	-0.038799229	0.691318234	3.174752e+02
-16.762094	0.369688385	-0.33267878	-0.035572645	0.596272007	2.809678e+02
-16.596960	0.381019830	-0.30280344	-0.032378138	0.537378676	2.754591e+02
-16.271207	0.392351275	-0.27319601	-0.029212277	0.475319006	2.647522e+02
-13.815798	0.403682720	-0.24382619	-0.026071824	0.360203050	1.908763e+02
-13.462160	0.415014164	-0.21466524	-0.022953704	0.309006447	1.812298e+02
-12.081520	0.426345609	-0.18568573	-0.019854987	0.239878409	1.459631e+02
-11.629207	0.437677054	-0.15686137	-0.016772858	0.195055032	1.352385e+02
-11.312669	0.449008499	-0.12816677	-0.013704604	0.155035654	1.279765e+02
-8.236558	0.460339943	-0.09957734	-0.010647596	0.087699542	6.784089e+01
-7.662789	0.471671388	-0.07106908	-0.007599268	0.058231584	5.871833e+01
-6.752801	0.483002833	-0.04261848	-0.004557105	0.030773222	4.560033e+01
-6.707262	0.494334278	-0.01420234	-0.001518626	0.010185824	4.498736e+01
-6.402439	0.505665722	0.01420234	0.001518626	-0.009722911	4.099122e+01
-5.446904	0.516997167	0.04261848	0.004557105	-0.024822110	2.966876e+01
-3.537785	0.528328612	0.07106908	0.007599268	-0.026884576	1.251592e+01
-2.824941	0.539660057	0.09957734	0.010647596	-0.030078835	7.980294e+00
-2.745208	0.550991501	0.12816677	0.013704604	-0.037621996	7.536170e+00
-0.195089	0.562322946	0.15686137	0.016772858	-0.003272200	3.805971e-02
1.399296	0.573654391	0.18568573	0.019854987	0.027782994	1.958028e+00
5.363331	0.584985836	0.21466524	0.022953704	0.123108313	2.876532e+01
6.700640	0.596317280	0.24382619	0.026071824	0.174697904	4.489858e+01
7.386314	0.607648725	0.27319601	0.029212277	0.215771059	5.455764e+01
9.099900	0.618980170	0.30280344	0.032378138	0.294637808	8.280817e+01
12.433611	0.630311615	0.33267878	0.035572645	0.442296424	1.545947e+02
16.718018	0.641643059	0.36285409	0.038799229	0.648646203	2.794921e+02
18.093192	0.652974504	0.39336354	0.042061540	0.761027520	3.273636e+02
18.801816	0.664305949	0.42424369	0.045363489	0.852915978	3.535083e+02
19.168108	0.675637394	0.45553386	0.048709282	0.933664777	3.674164e+02
19.219211	0.686968839	0.48727661	0.052103467	1.001387528	3.693781e+02
20.334434	0.698300283	0.51951819	0.055550992	1.129598008	4.134892e+02
24.909926	0.709631728	0.55230918	0.059057264	1.471112049	6.205044e+02
26.236229	0.720963173	0.58570518	0.062628228	1.643128534	6.883397e+02
30.924022	0.732294618	0.61976766	0.066270458	2.049349072	9.562951e+02
32.253952	0.743626062	0.65456498	0.069991263	2.257494854	1.040317e+03
32.529367	0.754957507	0.69017366	0.073798824	2.400629035	1.058160e+03
32.675968	0.766288952	0.72667986	0.077702356	2.538999708	1.067719e+03
33.275839	0.777620397	0.76418130	0.081712307	2.719045583	1.107281e+03
36.031430	0.788951841	0.80278966	0.085840618	3.092960242	1.298264e+03
37.147186	0.800283286	0.84263354	0.090101040	3.347000059	1.379913e+03
40.320875	0.811614731	0.88386232	0.094509548	3.810707636	1.625773e+03
44.334467	0.822946176	0.92665123	0.099084876	4.392875123	1.965545e+03
46.907165	0.834277620	0.97120790	0.103849228	4.871272904	2.200282e+03
54.418366	0.845609065	1.01778137	0.108829231	5.922308882	2.961359e+03
55.091131	0.856940510	1.06667420	0.114057239	6.283542333	3.035033e+03
55.470305	0.868271955	1.11825971	0.119573169	6.632760113	3.076955e+03
62.939597	0.879603399	1.17300649	0.125427129	7.894332885	3.961393e+03
66.478628	0.890934844	1.23151500	0.131683320	8.754126443	4.419408e+03
67.426518	0.902266289	1.29457343	0.138426027	9.333585010	4.546335e+03
67.603959	0.913597734	1.36324747	0.145769197	9.854574914	4.570295e+03
69.707122	0.924929178	1.43903134	0.153872609	10.726016772	4.859083e+03
69.843246	0.936260623	1.52411994	0.162970954	11.382420482	4.878079e+03
74.848732	0.947592068	1.62194155	0.173430814	12.981076532	5.602333e+03
112.729191	0.958923513	1.73832835	0.185875811	20.953629849	1.270787e+04
163.795081	0.970254958	1.88455395	0.201511408	33.006577315	2.682883e+04
198.660139	0.981586402	2.08767462	0.226331231	44.962993843	3.946585e+04
209.375830	0.992917847	2.45306927	0.286093929	59.901153719	4.383824e+04
Fuente: Elaboración propia

#Cálculo del estadístico W (Shapiro-Wilk manual)

W <- (sum(tabla_SW$ai_ui)^2) / sum(tabla_SW$ui2)

print(W)

## [1] 0.9413208

#Cálculo del Wn y su p value

n <- nrow(tabla_SW)

mu <- 0.0038915*log(n)^3 - 0.083751*log(n)^2 - 0.31082*log(n) - 1.5861
sigma <- exp(0.0030302*log(n)^2 - 0.082676*log(n) - 0.4803)

Wn <- (log(1 - W) - mu) / sigma

print(Wn)

## [1] 3.241867

p_value_SW <- pnorm(Wn, lower.tail = FALSE)

print(p_value_SW)

## [1] 0.0005937472

library(fastGraph)

shadeDist(Wn,
          ddist = "dnorm",
          lower.tail = FALSE,
          sub = paste("Wn:", round(Wn, 3),
                      " p-value:", round(p_value_SW, 5)))

En este caso, dado que el p-value = 0.0005937 < 0.05, se rechaza la hipótesis nula de normalidad. Por lo tanto, los residuos no siguen una distribución normal, es decir, no se cumple que 𝜀∼𝑁(0,𝜎2)ε∼N(0,σ2).

Usando la librería stats (precargada al iniciar R)

salida_SW <- shapiro.test(resid(modelo_estimado))

print(salida_SW)

## 
##  Shapiro-Wilk normality test
## 
## data:  resid(modelo_estimado)
## W = 0.94132, p-value = 0.0005937

Mismos resultados que en el cálculo manual.

Importante, a partir de esta salida se puede calcular el Wn si se llegará a necesitar:

salida_SW <- shapiro.test(resid(modelo_estimado))

Wn_salida <- qnorm(salida_SW$p.value, lower.tail = FALSE)

print(Wn_salida)

## [1] 3.241867