ESTADISTICA DESCRIPTIVA CON R

ESTADISTICA_DESCRIPTIVA_CON_R.R
Familia CF
Mon Mar 16 21:16:12 2015
#ESTADÍSTICA DESCRIPTIVA CON R
#Se seleccionaron 100 baterías aleatoriamente de un proceso de fabricación
#Y se llevó a cabo una prueba para determinar la duración de éstas.
#Los siguientes datos representan el tiempo de duración en horas
#para las 100 baterías:
datos<-c(165,175,143,177,176,152,159,161,182,148,180,172,171,156,174,165,176,156,152,165,172,170,148,149,158,167,
157,188,200,186,174,169,157,172,163,171,164,162,183,
161,188,173,198,188,175,165,195,180,174,173,189,199,
179,177,165,177,188,199,201,204,174,187,176,167,154,
187,179,188,199,185,170,172,173,193,192,190,189,197,
189,187,167,198,180,190,170,170,173,169,188,177,187,184,197,178,199,183,188,177,165,199)
n=length(datos) #contamos el número de datos
n
## [1] 100
datos=sort(datos) #ordena los datos de menor a mayor
datos
## [1] 143 148 148 149 152 152 154 156 156 157 157 158 159 161 161 162 163
## [18] 164 165 165 165 165 165 165 167 167 167 169 169 170 170 170 170 171
## [35] 171 172 172 172 172 173 173 173 173 174 174 174 174 175 175 176 176
## [52] 176 177 177 177 177 177 178179 179 180 180 180 182 183 183 184 185
## [69] 186 187 187 187 187 188 188 188 188 188 188 188 189 189 189 190 190
## [86] 192 193 195 197 197 198 198 199 199 199 199 199 200 201 204
R=range(datos) #la función range() da el valor menor y mayor en un conjunto de datos
R#las funciones max() y min() dan los valores máximo y minimos respectivamente
## [1] 143 204
#de un conjunto de datos
max(datos)#valor mayor
## [1] 204
min(datos) #valor menor
## [1] 143
#Para determinar el número aproximado de clases, se puede
#hacer uso de la Regla de Sturges, que en R viende determinada por la función
#nclass.Sturges():
nuclases=nclass.Sturges(datos) #número de clases
nuclases
## [1] 8
#hallamos la longitud de clase así:
L=(max(datos)-min(datos))/nuclases
L
## [1] 7.625
#como L=8.25 podemos aproximaral nÚmero entero mas cercano a L=8
L=8
#Para establecer las fronteras de cada clase, es necesario considerar la unidad más
#cercana con respecto a la cual se mide las observaciones. Por ejemplo, tomemos como
#limite inferior de la primera clase 142. Así, las ocho clases a considerar son:
limites=seq(142, 206, by=8) #puntos de corte para las clases
limites
## [1] 142 150 158 166 174 182 190 198 206#La función cut() asigna un intervalo cada valor del conjunto de datos de acuerdo a los
#limites establecidos anteriormente
clases= factor(cut(datos, limites)) #los limites para las clases
clases
## [1] (142,150] (142,150] (142,150] (142,150] (150,158] (150,158] (150,158]
## [8] (150,158] (150,158] (150,158] (150,158] (150,158] (158,166] (158,166]
## [15] (158,166] (158,166] (158,166](158,166] (158,166] (158,166] (158,166]
## [22] (158,166] (158,166] (158,166] (166,174] (166,174] (166,174] (166,174]
## [29] (166,174] (166,174] (166,174] (166,174] (166,174] (166,174] (166,174]
## [36] (166,174] (166,174] (166,174] (166,174] (166,174] (166,174] (166,174]
## [43] (166,174] (166,174] (166,174] (166,174] (166,174] (174,182] (174,182]
## [50] (174,182] (174,182] (174,182] (174,182](174,182] (174,182] (174,182]
## [57] (174,182] (174,182] (174,182] (174,182] (174,182] (174,182] (174,182]
## [64] (174,182] (182,190] (182,190] (182,190] (182,190] (182,190] (182,190]
## [71] (182,190] (182,190] (182,190] (182,190] (182,190] (182,190] (182,190]
## [78] (182,190] (182,190] (182,190] (182,190] (182,190] (182,190] (182,190]
## [85] (182,190] (190,198] (190,198] (190,198](190,198] (190,198] (190,198]
## [92] (190,198] (198,206] (198,206] (198,206] (198,206] (198,206] (198,206]
## [99] (198,206] (198,206]
## 8 Levels: (142,150] (150,158] (158,166] (166,174] (174,182] ... (198,206]
#Las clases con sus respectivas frecuencias
table(clases)
## clases
## (142,150] (150,158] (158,166] (166,174] (174,182] (182,190] (190,198]
## 4 8 12 23...