R Notebook

Data getting

data_profe_2_tot <- 
  data_profe_2 %>% 
  filter(str_detect(metodo, "TOT"))

data_profe_2_umb <- 
  data_profe_2 %>% 
  filter(str_detect(metodo, "UMB"))

Pregunta 1 - test de normalidad

Prueba de normalidad

TOT por cada método

shapiro.test(data_profe_2_tot %>%
               filter(metodo %in% "ENmatResPreRec_FT_LSA_TOTAQE") %>%
               select(V5) %>% unlist()
)

    Shapiro-Wilk normality test

data:  data_profe_2_tot %>% filter(metodo %in% "ENmatResPreRec_FT_LSA_TOTAQE") %>% select(V5) %>% unlist()
W = 0.8808, p-value < 2.2e-16

shapiro.test(data_profe_2_tot %>%
               filter(metodo %in% "ENmatResPreRec_FT_vsm_TOTAQE") %>%
               select(V5) %>% unlist()
)

    Shapiro-Wilk normality test

data:  data_profe_2_tot %>% filter(metodo %in% "ENmatResPreRec_FT_vsm_TOTAQE") %>% select(V5) %>% unlist()
W = 0.87035, p-value < 2.2e-16

shapiro.test(data_profe_2_tot %>%
               filter(metodo %in% "ENmatResPreRec_FT_LSA_TOT") %>%
               select(V5) %>% unlist()
)

    Shapiro-Wilk normality test

data:  data_profe_2_tot %>% filter(metodo %in% "ENmatResPreRec_FT_LSA_TOT") %>% select(V5) %>% unlist()
W = 0.92058, p-value < 2.2e-16

shapiro.test(data_profe_2_tot %>%
               filter(metodo %in% "ENmatResPreRec_FT_vsm_TOT") %>%
               select(V5) %>% unlist()
)

    Shapiro-Wilk normality test

data:  data_profe_2_tot %>% filter(metodo %in% "ENmatResPreRec_FT_vsm_TOT") %>% select(V5) %>% unlist()
W = 0.90553, p-value < 2.2e-16

shapiro.test(data_profe_2_tot %>%
               filter(metodo %in% "ENmatResPreRec_MD_vsm_TOTAQE") %>%
               select(V5) %>% unlist()
)

    Shapiro-Wilk normality test

data:  data_profe_2_tot %>% filter(metodo %in% "ENmatResPreRec_MD_vsm_TOTAQE") %>% select(V5) %>% unlist()
W = 0.89218, p-value < 2.2e-16

shapiro.test(data_profe_2_tot %>%
               filter(metodo %in% "ENmatResPreRec_MD_LSA_TOT") %>%
               select(V5) %>% unlist()
)

    Shapiro-Wilk normality test

data:  data_profe_2_tot %>% filter(metodo %in% "ENmatResPreRec_MD_LSA_TOT") %>% select(V5) %>% unlist()
W = 0.86281, p-value < 2.2e-16

shapiro.test(data_profe_2_tot %>%
               filter(metodo %in% "ENmatResPreRec_MD_LSA_TOTAQE") %>%
               select(V5) %>% unlist()
)

    Shapiro-Wilk normality test

data:  data_profe_2_tot %>% filter(metodo %in% "ENmatResPreRec_MD_LSA_TOTAQE") %>% select(V5) %>% unlist()
W = 0.85785, p-value < 2.2e-16

shapiro.test(data_profe_2_tot %>%
               filter(metodo %in% "ENmatResPreRec_MD_vsm_TOT") %>%
               select(V5) %>% unlist()
)

    Shapiro-Wilk normality test

data:  data_profe_2_tot %>% filter(metodo %in% "ENmatResPreRec_MD_vsm_TOT") %>% select(V5) %>% unlist()
W = 0.86666, p-value < 2.2e-16

UMB por cada método

shapiro.test(data_profe_2_umb %>%
               filter(metodo %in% "ENmatResPreRec_FT_LSA_UMBAQE") %>%
               select(V5) %>% unlist()
)

    Shapiro-Wilk normality test

data:  data_profe_2_umb %>% filter(metodo %in% "ENmatResPreRec_FT_LSA_UMBAQE") %>% select(V5) %>% unlist()
W = 0.72948, p-value < 2.2e-16

shapiro.test(data_profe_2_umb %>%
               filter(metodo %in% "ENmatResPreRec_FT_vsm_UMBAQE") %>%
               select(V5) %>% unlist()
)

    Shapiro-Wilk normality test

data:  data_profe_2_umb %>% filter(metodo %in% "ENmatResPreRec_FT_vsm_UMBAQE") %>% select(V5) %>% unlist()
W = 0.79481, p-value < 2.2e-16

shapiro.test(data_profe_2_umb %>%
               filter(metodo %in% "ENmatResPreRec_FT_LSA_UMB") %>%
               select(V5) %>% unlist()
)

    Shapiro-Wilk normality test

data:  data_profe_2_umb %>% filter(metodo %in% "ENmatResPreRec_FT_LSA_UMB") %>% select(V5) %>% unlist()
W = 0.7876, p-value < 2.2e-16

shapiro.test(data_profe_2_umb %>%
               filter(metodo %in% "ENmatResPreRec_FT_vsm_UMB") %>%
               select(V5) %>% unlist()
)

    Shapiro-Wilk normality test

data:  data_profe_2_umb %>% filter(metodo %in% "ENmatResPreRec_FT_vsm_UMB") %>% select(V5) %>% unlist()
W = 0.78295, p-value < 2.2e-16

shapiro.test(data_profe_2_umb %>%
               filter(metodo %in% "ENmatResPreRec_MD_vsm_UMBAQE") %>%
               select(V5) %>% unlist()
)

    Shapiro-Wilk normality test

data:  data_profe_2_umb %>% filter(metodo %in% "ENmatResPreRec_MD_vsm_UMBAQE") %>% select(V5) %>% unlist()
W = 0.84792, p-value < 2.2e-16

shapiro.test(data_profe_2_umb %>%
               filter(metodo %in% "ENmatResPreRec_MD_LSA_UMB") %>%
               select(V5) %>% unlist()
)

    Shapiro-Wilk normality test

data:  data_profe_2_umb %>% filter(metodo %in% "ENmatResPreRec_MD_LSA_UMB") %>% select(V5) %>% unlist()
W = 0.70104, p-value < 2.2e-16

shapiro.test(data_profe_2_umb %>%
               filter(metodo %in% "ENmatResPreRec_MD_LSA_UMBAQE") %>%
               select(V5) %>% unlist()
)

    Shapiro-Wilk normality test

data:  data_profe_2_umb %>% filter(metodo %in% "ENmatResPreRec_MD_LSA_UMBAQE") %>% select(V5) %>% unlist()
W = 0.64439, p-value < 2.2e-16

shapiro.test(data_profe_2_umb %>%
               filter(metodo %in% "ENmatResPreRec_MD_vsm_UMB") %>%
               select(V5) %>% unlist()
)

    Shapiro-Wilk normality test

data:  data_profe_2_umb %>% filter(metodo %in% "ENmatResPreRec_MD_vsm_UMB") %>% select(V5) %>% unlist()
W = 0.67084, p-value < 2.2e-16

Pregunta 2 - diferencias entre medianas

diferencias entre medianas del número de palabras

kruskal.test(factor(V3) ~ V5, data_profe_2)

    Kruskal-Wallis rank sum test

data:  factor(V3) by V5
Kruskal-Wallis chi-squared = 106513, df = 37620, p-value < 2.2e-16

Pregunta 3 - chi cuadrado y grados de libertad

kruskal.test(metodo ~ V5, 
             data_profe_2 %>% 
               filter(V3 == 2,
                      V7 ==1,
                      str_detect(metodo, 
                                 "TOT")))

    Kruskal-Wallis rank sum test

data:  metodo by V5
Kruskal-Wallis chi-squared = 2499.8, df = 2362, p-value = 0.02407

kruskal.test(metodo ~ V5, 
             data_profe_2 %>% 
               filter(V3 == 2,
                      V7 ==1,
                      str_detect(metodo, 
                                 "UMB")))

    Kruskal-Wallis rank sum test

data:  metodo by V5
Kruskal-Wallis chi-squared = 683.42, df = 604, p-value = 0.01352