The Analitica
package provides essential tools for:
It is suitable for researchers, educators, and analysts seeking quick and interpretable workflows.
Use descripYG()
to explore a numeric variable,
optionally grouped by a categorical variable:
#> n Mean Median SD Kurtosis Skewness CV Min Max P25
#> 1 474 34419.57 28875 17075.66 8.30863 2.117877 0.4961033 15750 135000 24000
#> P75 IQR Fence_Low Fence_High
#> 1 36937.5 12937.5 4593.75 56343.75
descripYG(d_e, vd = Sueldo_actual, vi = labor)
#> Picking joint bandwidth of 2460
#> Group n Mean Median SD Kurtosis Skewness CV Min
#> 1 1 363 27838.54 26550 7567.995 10.850828 1.8973062 0.27185316 15750
#> 2 2 27 30938.89 30750 2114.616 5.795226 -0.3472238 0.06834817 24300
#> 3 3 84 63977.80 60500 18244.776 4.913269 1.1597365 0.28517355 34410
#> Max P25 P75 IQR
#> 1 80000 22800.00 31200.00 8400
#> 2 35250 30150.00 30975.00 825
#> 3 135000 51956.25 71281.25 19325
You can assess variance assumptions using manual implementations:
Levene.Test(Sueldo_actual ~ labor, data = d_e)
#> $Statistic
#> [1] 36.089
#>
#> $df
#> df_between df_within
#> 2 471
#>
#> $p_value
#> [1] 0
#>
#> $Significance
#> [1] "***"
#>
#> $Decision
#> [1] "Heteroscedastic"
#>
#> $Method
#> [1] "Levene (median)"
#>
#> attr(,"class")
#> [1] "homocedasticidad"
BartlettTest(Sueldo_actual ~ labor, data = d_e)
#> $Statistic
#> [1] 194.6489
#>
#> $df
#> [1] 2
#>
#> $p_value
#> [1] 0
#>
#> $Significance
#> [1] "***"
#>
#> $Decision
#> [1] "Heterocedastic"
#>
#> $Method
#> [1] "Bartlett"
#>
#> attr(,"class")
#> [1] "homocedasticidad"
FKTest(Sueldo_actual ~ labor, data = d_e)
#> $Statistic
#> [1] 88.2881
#>
#> $df
#> [1] 2
#>
#> $p_value
#> [1] 0
#>
#> $Significance
#> [1] "***"
#>
#> $Decision
#> [1] "Heteroscedastic"
#>
#> $Method
#> [1] "Fligner-Killeen"
#>
#> attr(,"class")
#> [1] "homocedasticidad"
Detect univariate outliers with Grubbs’ test:
res <- grubbs_outliers(d_e, Sueldo_actual)
head(res[res$outL == TRUE, ])
#> ID Sexo FechaNAc educacion labor Sueldo_actual Sueldo_inicial antigüedad
#> 18 18 h 20/03/1986 16 3 103750 27510 97
#> 29 29 h 28/01/1964 19 3 135000 79980 96
#> 32 32 h 28/01/1984 19 3 110625 45000 96
#> 34 34 h 02/02/1969 19 3 92000 39990 96
#> 103 103 h 17/03/1989 19 3 97000 35010 91
#> 106 106 h 04/08/1962 19 3 91250 29490 91
#> experiencia minoria outL
#> 18 70 0 TRUE
#> 29 199 0 TRUE
#> 32 120 0 TRUE
#> 34 175 0 TRUE
#> 103 68 0 TRUE
#> 106 23 0 TRUE
Fit an ANOVA model and apply post hoc tests:
mod <- aov(Sueldo_actual ~ as.factor(labor), data = d_e)
resultado <- GHTest(mod)
summary(resultado)
#> =====================================
#> Multiple Comparison Method Summary
#> =====================================
#> Method used: Games-Howell
#>
#> >> Group means:
#> 1 2 3
#> 27838.54 30938.89 63977.80
#>
#> >> Order of means (from highest to lowest):
#> [1] "3" "2" "1"
#>
#> >> Pairwise comparisons:
#> Comparacion Diferencia t_value gl p_value Significancia
#> 1 1 - 2 3100.349 5.4518 93.07 0 ***
#> 11 1 - 3 36139.258 17.8034 89.71 0 ***
#> 2 2 - 3 33038.909 16.2606 89.58 0 ***
plot(resultado)
Other methods include TukeyTest()
,
ScheffeTest()
, DuncanTest()
,
SNKTest()
, T2Test()
, and
T3Test()
.
When assumptions are violated, try:
g1 <- d_e$Sueldo_actual[d_e$labor == 1]
g2 <- d_e$Sueldo_actual[d_e$labor == 2]
MWTest(g1, g2)
#> $Resultados
#> Comparacion Diferencia Valor_Critico p_value Significancia
#> Grupo2 Grupo1 - Grupo2 3100.349 NA 1e-04 ***
#>
#> $Promedios
#> Grupo1 Grupo2
#> 27838.54 30938.89
#>
#> $Orden_Medias
#> [1] "Grupo2" "Grupo1"
#>
#> $Metodo
#> [1] "Mann-Whitney U (two.sided, manual)"
#>
#> attr(,"class")
#> [1] "comparacion" "mannwhitney"
BMTest(g1, g2)
#> $Resultados
#> Comparacion Diferencia df SE t_critical p_value p_hat
#> Grupo1 Grupo1 - Grupo2 -3100.349 64.98 9.7586 1.9971 0 0.7297
#> Significancia
#> Grupo1 ***
#>
#> $Promedios
#> Grupo1 Grupo2
#> 27838.54 30938.89
#>
#> $df
#> [1] 64.98189
#>
#> $Orden_Medias
#> [1] "Grupo2" "Grupo1"
#>
#> $Metodo
#> [1] "Brunner-Munzel (two.sided)"
#>
#> $p_hat
#> [1] 0.7296704
#>
#> attr(,"class")
#> [1] "comparacion" "brunnermunzel"
BMpTest(g1, g2)
#> $Resultados
#> Comparacion Diferencia Valor_Critico p_value p_hat Significancia
#> Grupo2 Grupo1 - Grupo2 3100.349 NA 0 0.7297 *
#>
#> $Promedios
#> Grupo1 Grupo2
#> 27838.54 30938.89
#>
#> $Orden_Medias
#> [1] "Grupo2" "Grupo1"
#>
#> $Metodo
#> [1] "Brunner-Munzel (perm, two.sided)"
#>
#> attr(,"class")
#> [1] "comparacion" "brunnermunzel_perm"
Analitica
integrates descriptive analysis with robust
comparison methods for applied data exploration.
For detailed documentation, see ?Analitica
or
function-specific help pages like ?GHTest
or
?descripYG
.