Welcome to my project!I am exploring three fascinating data analysis methods: multiple linear regression, clustering, and classification. Our goal is to comprehend the relationships between various variables, spot hidden patterns in the data, and create models to forecast and organize data points. To get insightful information and make wise choices, we’ll employ statistical techniques and algorithms. Join me on this adventure where we turn data into knowledge. It’s going to be fun and rewarding! The dataset chosen is the “Concrete_data”, it concerns a series of factors that influence the strength of the concrete. Among the variables we have Cement, Blast Furnace Slag, Fly_Ash, Water, Superplasticizer, Coarse_Aggregate and Fine_Aggregate; these are all expressed per kg in m^3. Then we have the age of the concrete expressed in days and finally the strength expressed in Megapascals.
library(tidyverse)
## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──
## âś” ggplot2 3.4.2 âś” purrr 1.0.1
## âś” tibble 3.2.1 âś” dplyr 1.1.2
## âś” tidyr 1.3.0 âś” stringr 1.5.0
## âś” readr 2.1.3 âś” forcats 0.5.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## âś– dplyr::filter() masks stats::filter()
## âś– dplyr::lag() masks stats::lag()
library(caret)
## Caricamento del pacchetto richiesto: lattice
##
## Caricamento pacchetto: 'caret'
##
## Il seguente oggetto è mascherato da 'package:purrr':
##
## lift
library(datarium)
library(ggplot2)
library(ggpubr)
library(dplyr)
library(car)
## Caricamento del pacchetto richiesto: carData
##
## Caricamento pacchetto: 'car'
##
## Il seguente oggetto è mascherato da 'package:dplyr':
##
## recode
##
## Il seguente oggetto è mascherato da 'package:purrr':
##
## some
library(tseries)
## Registered S3 method overwritten by 'quantmod':
## method from
## as.zoo.data.frame zoo
library(MASS)
##
## Caricamento pacchetto: 'MASS'
##
## Il seguente oggetto è mascherato da 'package:dplyr':
##
## select
library(nortest)
library(lmtest)
## Caricamento del pacchetto richiesto: zoo
##
## Caricamento pacchetto: 'zoo'
##
## I seguenti oggetti sono mascherati da 'package:base':
##
## as.Date, as.Date.numeric
library(readxl)
data <- read_excel("~/Downloads/Concrete_Data.xls")
Once the dataset is loaded, I’m going to remove any missing data and rename the variables by simplifying the names. Then I summarize each variable and immediately remove any outliers in order to make my data more manageable and precise. For data variable I create many levels dividing they by trimester.
data <- na.omit(data)
title <- c("Cement", "Blast_Furnace_Slag","Fly_Ash","Water","Superplasticizer","Coarse_Aggregate","Fine_Aggregate","Day","Concrete_compressive_strength")
colnames(data) <- title
attach(data)
s <- summary(Cement)
iqr <- s[5] - s[2]
data <- subset(data, Cement > (s[2]-1.5*iqr) & Cement < (s[5]+1.5*iqr))
s <- summary(Blast_Furnace_Slag)
iqr <- s[5] - s[2]
data <- subset(data, Blast_Furnace_Slag > (s[2]-1.5*iqr) & Blast_Furnace_Slag < (s[5]+1.5*iqr))
s <- summary(Fly_Ash)
iqr <- s[5] - s[2]
data <- subset(data, Fly_Ash > (s[2]-1.5*iqr) & Fly_Ash < (s[5]+1.5*iqr))
s <- summary(Water)
iqr <- s[5] - s[2]
data <- subset(data, Water > (s[2]-1.5*iqr) & Water < (s[5]+1.5*iqr))
s <- summary(Superplasticizer)
iqr <- s[5] - s[2]
data <- subset(data, Superplasticizer > (s[2]-1.5*iqr) & Superplasticizer < (s[5]+1.5*iqr))
s <- summary(Coarse_Aggregate)
iqr <- s[5] - s[2]
data <- subset(data, Coarse_Aggregate > (s[2]-1.5*iqr) & Coarse_Aggregate < (s[5]+1.5*iqr))
s <- summary(Fine_Aggregate)
iqr <- s[5] - s[2]
data <- subset(data, Fine_Aggregate > (s[2]-1.5*iqr) & Fine_Aggregate < (s[5]+1.5*iqr))
s <- summary(Concrete_compressive_strength)
iqr <- s[5] - s[2]
data <- subset(data, Concrete_compressive_strength> (s[2]-1.5*iqr) & Concrete_compressive_strength< (s[5]+1.5*iqr))
data$Day <- cut(data$Day, breaks = c(0, 92 , 183, 274,366), labels = c("1st tm", "2nd tm","3dh tm", "4th tm"))
print(summary(data))
## Cement Blast_Furnace_Slag Fly_Ash Water
## Min. :102.0 Min. : 0.00 Min. : 0.0 Min. :127.0
## 1st Qu.:192.0 1st Qu.: 0.00 1st Qu.: 0.0 1st Qu.:166.6
## Median :269.4 Median : 20.00 Median : 0.0 Median :185.7
## Mean :279.1 Mean : 73.01 Mean : 54.6 Mean :182.4
## 3rd Qu.:349.0 3rd Qu.:143.25 3rd Qu.:118.3 3rd Qu.:192.0
## Max. :540.0 Max. :342.10 Max. :200.1 Max. :228.0
## Superplasticizer Coarse_Aggregate Fine_Aggregate Day
## Min. : 0.000 Min. : 801.0 Min. :594.0 1st tm:887
## 1st Qu.: 0.000 1st Qu.: 932.0 1st Qu.:732.0 2nd tm: 80
## Median : 6.350 Median : 968.0 Median :778.9 3dh tm: 13
## Mean : 5.877 Mean : 974.6 Mean :772.4 4th tm: 20
## 3rd Qu.:10.100 3rd Qu.:1029.4 3rd Qu.:822.0
## Max. :22.100 Max. :1145.0 Max. :945.0
## Concrete_compressive_strength
## Min. : 2.332
## 1st Qu.:23.522
## Median :33.871
## Mean :35.435
## 3rd Qu.:45.320
## Max. :79.400
Now I can draw my first model composed by all the variable! After using the function step I remove the less significative predictors
mod <- lm(formula = Concrete_compressive_strength ~ Cement + Blast_Furnace_Slag +
Fly_Ash + Water + Superplasticizer +(Coarse_Aggregate)+(Fine_Aggregate)+ Day, data = data)
summary(mod)
##
## Call:
## lm(formula = Concrete_compressive_strength ~ Cement + Blast_Furnace_Slag +
## Fly_Ash + Water + Superplasticizer + (Coarse_Aggregate) +
## (Fine_Aggregate) + Day, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -32.039 -7.722 0.248 7.093 30.527
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 47.287041 30.370684 1.557 0.119791
## Cement 0.101874 0.009385 10.855 < 2e-16 ***
## Blast_Furnace_Slag 0.077845 0.011222 6.937 7.24e-12 ***
## Fly_Ash 0.042121 0.013948 3.020 0.002594 **
## Water -0.206206 0.047721 -4.321 1.71e-05 ***
## Superplasticizer 0.388366 0.117129 3.316 0.000947 ***
## Coarse_Aggregate -0.010188 0.010538 -0.967 0.333855
## Fine_Aggregate -0.006457 0.012031 -0.537 0.591618
## Day2nd tm 17.300611 1.326283 13.044 < 2e-16 ***
## Day3dh tm 19.040241 3.220700 5.912 4.65e-09 ***
## Day4th tm 17.394575 2.581012 6.739 2.70e-11 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 11.09 on 989 degrees of freedom
## Multiple R-squared: 0.55, Adjusted R-squared: 0.5454
## F-statistic: 120.9 on 10 and 989 DF, p-value: < 2.2e-16
mod <- step(mod, direction = "back", trace = FALSE)
summary(mod)
##
## Call:
## lm(formula = Concrete_compressive_strength ~ Cement + Blast_Furnace_Slag +
## Fly_Ash + Water + Superplasticizer + Day, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -32.210 -7.690 0.382 7.222 30.365
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 23.711210 4.896404 4.843 1.49e-06 ***
## Cement 0.107307 0.004599 23.333 < 2e-16 ***
## Blast_Furnace_Slag 0.084589 0.005567 15.195 < 2e-16 ***
## Fly_Ash 0.049080 0.008870 5.533 4.02e-08 ***
## Water -0.173367 0.024591 -7.050 3.35e-12 ***
## Superplasticizer 0.438566 0.107631 4.075 4.98e-05 ***
## Day2nd tm 17.122950 1.315530 13.016 < 2e-16 ***
## Day3dh tm 18.900041 3.194811 5.916 4.54e-09 ***
## Day4th tm 17.477844 2.575442 6.786 1.98e-11 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 11.08 on 991 degrees of freedom
## Multiple R-squared: 0.5494, Adjusted R-squared: 0.5458
## F-statistic: 151 on 8 and 991 DF, p-value: < 2.2e-16
Since our Adjusted R^2 is not bad, we are going to check the assumption for MLR!
##1ST ASSUMPTION: model is linear in parameters
crPlots(mod)
We can accept first assumption and go on!
##2ND ASSUMPTION: mean of res =0 and res normally distribuited
mean(mod$residuals)
## [1] -7.935666e-17
shapiro.test(mod$residuals)
##
## Shapiro-Wilk normality test
##
## data: mod$residuals
## W = 0.99759, p-value = 0.1493
plot(mod)
Also the second assumption is respected. Let’s continue with third!
##3RD ASSUMPTION: homoscedasticity of residuals
ncvTest(mod)
## Non-constant Variance Score Test
## Variance formula: ~ fitted.values
## Chisquare = 46.91898, Df = 1, p = 7.3983e-12
plot(mod)
Looking to Scale-Location plot and computing the test we see that this
assumption is not respected and so we have two possible solution: 1) to
transform the response y in log(y) 2) to use WLS giving more weight to
high-quality data.
Let’s try with first solution
mod <- lm (log(Concrete_compressive_strength) ~ Cement + Blast_Furnace_Slag +
Fly_Ash + Water + Superplasticizer +(Coarse_Aggregate)+(Fine_Aggregate)+ Day, data = data)
summary(mod)
##
## Call:
## lm(formula = log(Concrete_compressive_strength) ~ Cement + Blast_Furnace_Slag +
## Fly_Ash + Water + Superplasticizer + (Coarse_Aggregate) +
## (Fine_Aggregate) + Day, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.86922 -0.24550 0.06362 0.26676 0.79980
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.1920653 1.0819926 3.874 0.000114 ***
## Cement 0.0031060 0.0003344 9.290 < 2e-16 ***
## Blast_Furnace_Slag 0.0021517 0.0003998 5.382 9.20e-08 ***
## Fly_Ash 0.0015683 0.0004969 3.156 0.001648 **
## Water -0.0060945 0.0017001 -3.585 0.000354 ***
## Superplasticizer 0.0129495 0.0041729 3.103 0.001968 **
## Coarse_Aggregate -0.0004519 0.0003754 -1.204 0.228947
## Fine_Aggregate -0.0005863 0.0004286 -1.368 0.171653
## Day2nd tm 0.5773685 0.0472504 12.219 < 2e-16 ***
## Day3dh tm 0.5416256 0.1147414 4.720 2.69e-06 ***
## Day4th tm 0.6070287 0.0919517 6.602 6.62e-11 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.395 on 989 degrees of freedom
## Multiple R-squared: 0.4883, Adjusted R-squared: 0.4831
## F-statistic: 94.38 on 10 and 989 DF, p-value: < 2.2e-16
mod <- step(mod, direction = "back", trace = FALSE)
summary(mod)
##
## Call:
## lm(formula = log(Concrete_compressive_strength) ~ Cement + Blast_Furnace_Slag +
## Fly_Ash + Water + Superplasticizer + Day, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.87606 -0.23825 0.05967 0.27725 0.82173
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.7620161 0.1745008 15.828 < 2e-16 ***
## Cement 0.0035048 0.0001639 21.384 < 2e-16 ***
## Blast_Furnace_Slag 0.0026254 0.0001984 13.233 < 2e-16 ***
## Fly_Ash 0.0020936 0.0003161 6.623 5.75e-11 ***
## Water -0.0041535 0.0008764 -4.739 2.46e-06 ***
## Superplasticizer 0.0143541 0.0038358 3.742 0.000193 ***
## Day2nd tm 0.5719942 0.0468836 12.200 < 2e-16 ***
## Day3dh tm 0.5534689 0.1138585 4.861 1.36e-06 ***
## Day4th tm 0.6144766 0.0917850 6.695 3.61e-11 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.3949 on 991 degrees of freedom
## Multiple R-squared: 0.4873, Adjusted R-squared: 0.4832
## F-statistic: 117.8 on 8 and 991 DF, p-value: < 2.2e-16
shapiro.test(mod$residuals)
##
## Shapiro-Wilk normality test
##
## data: mod$residuals
## W = 0.96463, p-value = 7.395e-15
ncvTest(mod)
## Non-constant Variance Score Test
## Variance formula: ~ fitted.values
## Chisquare = 90.43301, Df = 1, p = < 2.22e-16
In this case Adjusted R^2 decrease, the second assumption of normality is not respected and also the heteroscedasticity problem is not solved.
mod <- lm(formula = Concrete_compressive_strength ~ Cement + Blast_Furnace_Slag +
Fly_Ash + Water + Superplasticizer +(Coarse_Aggregate)+(Fine_Aggregate)+ Day, data = data)
summary(mod)
##
## Call:
## lm(formula = Concrete_compressive_strength ~ Cement + Blast_Furnace_Slag +
## Fly_Ash + Water + Superplasticizer + (Coarse_Aggregate) +
## (Fine_Aggregate) + Day, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -32.039 -7.722 0.248 7.093 30.527
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 47.287041 30.370684 1.557 0.119791
## Cement 0.101874 0.009385 10.855 < 2e-16 ***
## Blast_Furnace_Slag 0.077845 0.011222 6.937 7.24e-12 ***
## Fly_Ash 0.042121 0.013948 3.020 0.002594 **
## Water -0.206206 0.047721 -4.321 1.71e-05 ***
## Superplasticizer 0.388366 0.117129 3.316 0.000947 ***
## Coarse_Aggregate -0.010188 0.010538 -0.967 0.333855
## Fine_Aggregate -0.006457 0.012031 -0.537 0.591618
## Day2nd tm 17.300611 1.326283 13.044 < 2e-16 ***
## Day3dh tm 19.040241 3.220700 5.912 4.65e-09 ***
## Day4th tm 17.394575 2.581012 6.739 2.70e-11 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 11.09 on 989 degrees of freedom
## Multiple R-squared: 0.55, Adjusted R-squared: 0.5454
## F-statistic: 120.9 on 10 and 989 DF, p-value: < 2.2e-16
mod <- step(mod, direction = "back", trace = FALSE)
summary(mod)
##
## Call:
## lm(formula = Concrete_compressive_strength ~ Cement + Blast_Furnace_Slag +
## Fly_Ash + Water + Superplasticizer + Day, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -32.210 -7.690 0.382 7.222 30.365
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 23.711210 4.896404 4.843 1.49e-06 ***
## Cement 0.107307 0.004599 23.333 < 2e-16 ***
## Blast_Furnace_Slag 0.084589 0.005567 15.195 < 2e-16 ***
## Fly_Ash 0.049080 0.008870 5.533 4.02e-08 ***
## Water -0.173367 0.024591 -7.050 3.35e-12 ***
## Superplasticizer 0.438566 0.107631 4.075 4.98e-05 ***
## Day2nd tm 17.122950 1.315530 13.016 < 2e-16 ***
## Day3dh tm 18.900041 3.194811 5.916 4.54e-09 ***
## Day4th tm 17.477844 2.575442 6.786 1.98e-11 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 11.08 on 991 degrees of freedom
## Multiple R-squared: 0.5494, Adjusted R-squared: 0.5458
## F-statistic: 151 on 8 and 991 DF, p-value: < 2.2e-16
var_res <- var(mod$residuals)
vaaaar <- mod$residuals^2
wei <- 1 / vaaaar
mod <- lm(formula = Concrete_compressive_strength ~ Cement + Blast_Furnace_Slag +
Fly_Ash + Water + Superplasticizer +(Coarse_Aggregate)+(Fine_Aggregate)+ Day , data= data,weights = wei )
summary(mod)
##
## Call:
## lm(formula = Concrete_compressive_strength ~ Cement + Blast_Furnace_Slag +
## Fly_Ash + Water + Superplasticizer + (Coarse_Aggregate) +
## (Fine_Aggregate) + Day, data = data, weights = wei)
##
## Weighted Residuals:
## Min 1Q Median 3Q Max
## -1.3770 -1.0034 0.7660 0.9959 1.5557
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 21.5312410 1.9580765 10.996 <2e-16 ***
## Cement 0.1084350 0.0006957 155.863 <2e-16 ***
## Blast_Furnace_Slag 0.0854773 0.0009167 93.248 <2e-16 ***
## Fly_Ash 0.0506910 0.0010333 49.059 <2e-16 ***
## Water -0.1724649 0.0029707 -58.055 <2e-16 ***
## Superplasticizer 0.4268479 0.0079130 53.943 <2e-16 ***
## Coarse_Aggregate 0.0009451 0.0006976 1.355 0.176
## Fine_Aggregate 0.0009494 0.0008351 1.137 0.256
## Day2nd tm 17.1174366 0.0775949 220.600 <2e-16 ***
## Day3dh tm 19.5720740 0.8683476 22.539 <2e-16 ***
## Day4th tm 15.2766135 1.0690367 14.290 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.997 on 989 degrees of freedom
## Multiple R-squared: 0.998, Adjusted R-squared: 0.998
## F-statistic: 4.932e+04 on 10 and 989 DF, p-value: < 2.2e-16
mod <- step(mod, direction = "back", trace = FALSE)
summary(mod)
##
## Call:
## lm(formula = Concrete_compressive_strength ~ Cement + Blast_Furnace_Slag +
## Fly_Ash + Water + Superplasticizer + Day, data = data, weights = wei)
##
## Weighted Residuals:
## Min 1Q Median 3Q Max
## -1.2578 -1.0023 0.8486 0.9971 1.5620
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 23.9839343 0.3019447 79.43 <2e-16 ***
## Cement 0.1076676 0.0003625 296.98 <2e-16 ***
## Blast_Furnace_Slag 0.0845008 0.0005357 157.73 <2e-16 ***
## Fly_Ash 0.0495434 0.0005612 88.28 <2e-16 ***
## Water -0.1750144 0.0019273 -90.81 <2e-16 ***
## Superplasticizer 0.4268452 0.0072297 59.04 <2e-16 ***
## Day2nd tm 17.1641551 0.0677252 253.44 <2e-16 ***
## Day3dh tm 19.6400433 0.8645617 22.72 <2e-16 ***
## Day4th tm 15.2792149 1.0689409 14.29 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.9969 on 991 degrees of freedom
## Multiple R-squared: 0.998, Adjusted R-squared: 0.998
## F-statistic: 6.165e+04 on 8 and 991 DF, p-value: < 2.2e-16
shapiro.test(mod$residuals)
##
## Shapiro-Wilk normality test
##
## data: mod$residuals
## W = 0.99751, p-value = 0.1327
ncvTest(mod)
## Non-constant Variance Score Test
## Variance formula: ~ fitted.values
## Chisquare = 0.003391049, Df = 1, p = 0.95356
bptest(mod)
##
## studentized Breusch-Pagan test
##
## data: mod
## BP = 0.17428, df = 8, p-value = 1
Doing WLS I completely solve my problem of heteroscedasticity!
##4TH ASSUMPTION: no autocorrelation of res
acf(mod$residuals)
pacf(mod$residuals)
Since the assumption is not met, I will try to use a lag1 var.
lag_var <- lag(mod$residuals, 1)
lag_var <- c(lag_var)
mod<- lm(Concrete_compressive_strength ~ Cement + Blast_Furnace_Slag +
Fly_Ash + Water + Superplasticizer +(Coarse_Aggregate)+(Fine_Aggregate)+ Day +lag_var,data = data)
summary(mod)
##
## Call:
## lm(formula = Concrete_compressive_strength ~ Cement + Blast_Furnace_Slag +
## Fly_Ash + Water + Superplasticizer + (Coarse_Aggregate) +
## (Fine_Aggregate) + Day + lag_var, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -30.0980 -6.3084 0.5064 6.9420 30.0573
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 26.992790 28.175076 0.958 0.338278
## Cement 0.106846 0.008694 12.289 < 2e-16 ***
## Blast_Furnace_Slag 0.083508 0.010398 8.031 2.73e-15 ***
## Fly_Ash 0.048639 0.012920 3.765 0.000177 ***
## Water -0.178612 0.044294 -4.032 5.95e-05 ***
## Superplasticizer 0.358189 0.108618 3.298 0.001010 **
## Coarse_Aggregate -0.003248 0.009770 -0.332 0.739606
## Fine_Aggregate 0.002402 0.011165 0.215 0.829723
## Day2nd tm 13.693552 1.258863 10.878 < 2e-16 ***
## Day3dh tm 16.712954 2.986452 5.596 2.84e-08 ***
## Day4th tm 16.597471 2.389528 6.946 6.81e-12 ***
## lag_var 0.391566 0.030285 12.929 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 10.26 on 987 degrees of freedom
## (1 osservazione eliminata a causa di un valore mancante)
## Multiple R-squared: 0.6143, Adjusted R-squared: 0.61
## F-statistic: 142.9 on 11 and 987 DF, p-value: < 2.2e-16
mod <- step(mod, direction = "back", trace = FALSE)
summary(mod)
##
## Call:
## lm(formula = Concrete_compressive_strength ~ Cement + Blast_Furnace_Slag +
## Fly_Ash + Water + Superplasticizer + Day + lag_var, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -30.8261 -6.3801 0.5369 6.8164 29.9216
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 25.195095 4.535999 5.554 3.58e-08 ***
## Cement 0.106240 0.004269 24.889 < 2e-16 ***
## Blast_Furnace_Slag 0.083066 0.005154 16.118 < 2e-16 ***
## Fly_Ash 0.047642 0.008211 5.802 8.82e-09 ***
## Water -0.175379 0.022794 -7.694 3.44e-14 ***
## Superplasticizer 0.386294 0.099864 3.868 0.000117 ***
## Day2nd tm 13.601022 1.247486 10.903 < 2e-16 ***
## Day3dh tm 16.400306 2.962798 5.535 3.98e-08 ***
## Day4th tm 16.568511 2.384285 6.949 6.66e-12 ***
## lag_var 0.391386 0.030216 12.953 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 10.25 on 989 degrees of freedom
## (1 osservazione eliminata a causa di un valore mancante)
## Multiple R-squared: 0.6139, Adjusted R-squared: 0.6104
## F-statistic: 174.7 on 9 and 989 DF, p-value: < 2.2e-16
Box.test(mod$residuals)
##
## Box-Pierce test
##
## data: mod$residuals
## X-squared = 0.62339, df = 1, p-value = 0.4298
Lagging our residuals I solve my problem as we can se by box.test that is an alternative iv dwtest. I can not use dwtest since I used WLS.
##5TH ASSUMPTION: predictors and residuals are uncorrelated
I can check this by plotting every scatter plot composed by each predictors and residuals.
residuals<- c(mod$residuals,0)
plot(data$Cement,residuals)
plot(data$Blast_Furnace_Slag,residuals)
plot(data$Fly_Ash,residuals)
plot(data$Water,residuals)
plot(data$Superplasticizer,residuals)
Since there are not correlation and strange pattern we can accept this
assumption
##6TH ASSUMPTION: p>n It is verify since I have 1000 units and 9 predictors.
##7TH ASSUMPTION: absence of multicollinearity
library(corrplot)
## corrplot 0.92 loaded
corrplot(cor(data[,1:6]))
vif(mod)
## GVIF Df GVIF^(1/(2*Df))
## Cement 1.808814 1 1.344921
## Blast_Furnace_Slag 1.859940 1 1.363796
## Fly_Ash 2.614668 1 1.616994
## Water 1.976334 1 1.405821
## Superplasticizer 2.746763 1 1.657336
## Day 1.220118 3 1.033714
## lag_var 1.057494 1 1.028345
Since the vif is always less than 5 I can accept this assumption. So this is my final model.
mod<- lm(Concrete_compressive_strength ~ Cement + Blast_Furnace_Slag +
Fly_Ash + Water + Superplasticizer + Day +lag_var,data = data)
summary(mod)
##
## Call:
## lm(formula = Concrete_compressive_strength ~ Cement + Blast_Furnace_Slag +
## Fly_Ash + Water + Superplasticizer + Day + lag_var, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -30.8261 -6.3801 0.5369 6.8164 29.9216
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 25.195095 4.535999 5.554 3.58e-08 ***
## Cement 0.106240 0.004269 24.889 < 2e-16 ***
## Blast_Furnace_Slag 0.083066 0.005154 16.118 < 2e-16 ***
## Fly_Ash 0.047642 0.008211 5.802 8.82e-09 ***
## Water -0.175379 0.022794 -7.694 3.44e-14 ***
## Superplasticizer 0.386294 0.099864 3.868 0.000117 ***
## Day2nd tm 13.601022 1.247486 10.903 < 2e-16 ***
## Day3dh tm 16.400306 2.962798 5.535 3.98e-08 ***
## Day4th tm 16.568511 2.384285 6.949 6.66e-12 ***
## lag_var 0.391386 0.030216 12.953 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 10.25 on 989 degrees of freedom
## (1 osservazione eliminata a causa di un valore mancante)
## Multiple R-squared: 0.6139, Adjusted R-squared: 0.6104
## F-statistic: 174.7 on 9 and 989 DF, p-value: < 2.2e-16
mod <- step(mod, direction = "back", trace = FALSE)
summary(mod)
##
## Call:
## lm(formula = Concrete_compressive_strength ~ Cement + Blast_Furnace_Slag +
## Fly_Ash + Water + Superplasticizer + Day + lag_var, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -30.8261 -6.3801 0.5369 6.8164 29.9216
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 25.195095 4.535999 5.554 3.58e-08 ***
## Cement 0.106240 0.004269 24.889 < 2e-16 ***
## Blast_Furnace_Slag 0.083066 0.005154 16.118 < 2e-16 ***
## Fly_Ash 0.047642 0.008211 5.802 8.82e-09 ***
## Water -0.175379 0.022794 -7.694 3.44e-14 ***
## Superplasticizer 0.386294 0.099864 3.868 0.000117 ***
## Day2nd tm 13.601022 1.247486 10.903 < 2e-16 ***
## Day3dh tm 16.400306 2.962798 5.535 3.98e-08 ***
## Day4th tm 16.568511 2.384285 6.949 6.66e-12 ***
## lag_var 0.391386 0.030216 12.953 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 10.25 on 989 degrees of freedom
## (1 osservazione eliminata a causa di un valore mancante)
## Multiple R-squared: 0.6139, Adjusted R-squared: 0.6104
## F-statistic: 174.7 on 9 and 989 DF, p-value: < 2.2e-16