df <- read.csv("C:\\Users\\Emili\\OneDrive\\Desktop\\TEC\\Tec 6to Semestre Concentracion\\Modulo 2\\HousePriceData.csv")Usar file.choose()
str(df)## 'data.frame': 905 obs. of 10 variables:
## $ Observation : int 1 2 3 4 5 6 7 8 9 10 ...
## $ Dist_Taxi : int 9796 8294 11001 8301 10510 6665 13153 5882 7495 8233 ...
## $ Dist_Market : int 5250 8186 14399 11188 12629 5142 11869 9948 11589 7067 ...
## $ Dist_Hospital: int 10703 12694 16991 12289 13921 9972 17811 13315 13370 11400 ...
## $ Carpet : int 1659 1461 1340 1451 1770 1442 1542 1261 1090 1030 ...
## $ Builtup : int 1961 1752 1609 1748 2111 1733 1858 1507 1321 1235 ...
## $ Parking : chr "Open" "Not Provided" "Not Provided" "Covered" ...
## $ City_Category: chr "CAT B" "CAT B" "CAT A" "CAT B" ...
## $ Rainfall : int 530 210 720 620 450 760 1030 1020 680 1130 ...
## $ House_Price : int 6649000 3982000 5401000 5373000 4662000 4526000 7224000 3772000 4631000 4415000 ...summary(df)## Observation Dist_Taxi Dist_Market Dist_Hospital
## Min. : 1.0 Min. : 146 Min. : 1666 Min. : 3227
## 1st Qu.:237.0 1st Qu.: 6477 1st Qu.: 9367 1st Qu.:11302
## Median :469.0 Median : 8228 Median :11149 Median :13189
## Mean :468.4 Mean : 8235 Mean :11022 Mean :13091
## 3rd Qu.:700.0 3rd Qu.: 9939 3rd Qu.:12675 3rd Qu.:14855
## Max. :932.0 Max. :20662 Max. :20945 Max. :23294
##
## Carpet Builtup Parking City_Category
## Min. : 775 Min. : 932 Length:905 Length:905
## 1st Qu.: 1317 1st Qu.: 1579 Class :character Class :character
## Median : 1478 Median : 1774 Mode :character Mode :character
## Mean : 1511 Mean : 1794
## 3rd Qu.: 1654 3rd Qu.: 1985
## Max. :24300 Max. :12730
## NA's :7
## Rainfall House_Price
## Min. :-110.0 Min. : 1492000
## 1st Qu.: 600.0 1st Qu.: 4623000
## Median : 780.0 Median : 5860000
## Mean : 786.9 Mean : 6083992
## 3rd Qu.: 970.0 3rd Qu.: 7200000
## Max. :1560.0 Max. :150000000
## df <- df[-349, ]regresion <- lm(House_Price ~ Dist_Taxi + Dist_Market + Dist_Hospital + Carpet + factor(Parking) + factor(City_Category) + Rainfall, data=df)
summary(regresion)##
## Call:
## lm(formula = House_Price ~ Dist_Taxi + Dist_Market + Dist_Hospital +
## Carpet + factor(Parking) + factor(City_Category) + Rainfall,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4365818 -1143410 -40235 1148630 11949292
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -2.131e+06 3.994e+05 -5.335 1.22e-07 ***
## Dist_Taxi 5.910e+01 3.908e+01 1.512 0.13080
## Dist_Market 4.281e+01 3.031e+01 1.412 0.15818
## Dist_Hospital 1.759e+01 4.381e+01 0.401 0.68818
## Carpet 5.739e+03 7.587e+01 75.641 < 2e-16 ***
## factor(Parking)No Parking -5.484e+05 2.021e+05 -2.713 0.00679 **
## factor(Parking)Not Provided -3.133e+05 1.796e+05 -1.744 0.08150 .
## factor(Parking)Open -1.369e+05 1.641e+05 -0.834 0.40444
## factor(City_Category)CAT B -1.983e+06 1.399e+05 -14.176 < 2e-16 ***
## factor(City_Category)CAT C -2.980e+06 1.541e+05 -19.338 < 2e-16 ***
## Rainfall 1.585e+02 2.244e+02 0.707 0.48001
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1782000 on 886 degrees of freedom
## (7 observations deleted due to missingness)
## Multiple R-squared: 0.8797, Adjusted R-squared: 0.8783
## F-statistic: 647.8 on 10 and 886 DF, p-value: < 2.2e-16datos_nuevos <- data.frame(Dist_Taxi=9796, Dist_Market=5250, Dist_Hospital= 10703, Carpet= 1659, Parking="Open", City_Category="CAT B", Rainfall=530)
predict(regresion, datos_nuevos)## 1
## 6346536Al incluir todas la variables, el modelo es altamente significativo
con un poder explicativo del 94%.
“Builtup” y “Carpet” presentan indicios de multicolinealidad. Al remover
la primer variable, el modelo continua siendo altamente significativo
con un poder explicativo del 88%.
Las distancias a diferentes establecimientos y la lluvia no son tomados
en cuenta para definir el precio.
Todos las varaibles significativas para el modelo representan un efecto
negativo hacia el precio, a excepcion de “Carpet”, la cual logicamente
tiene un efecto positivo.