**Predicting the tire purchase

Project Objective

To develop a logistic regression model to predict the likelihood of a customer purchasing a tire again based on its Wet and Noise performance ratings

Question 1&2: develop the model & assess predictor significance

Step 1: install and load required libraries

###install.packages("readxl")
###install.packages("Hmisc")
###install.packages("pscl")

if(!require(pROC)) install.packages("pROC")

## Loading required package: pROC

## Type 'citation("pROC")' for a citation.

## 
## Attaching package: 'pROC'

## The following objects are masked from 'package:stats':
## 
##     cov, smooth, var

library(readxl)
library(Hmisc)

## 
## Attaching package: 'Hmisc'

## The following objects are masked from 'package:base':
## 
##     format.pval, units

library(pscl)

## Classes and Methods for R originally developed in the
## Political Science Computational Laboratory
## Department of Political Science
## Stanford University (2002-2015),
## by and under the direction of Simon Jackman.
## hurdle and zeroinfl functions by Achim Zeileis.

library(pROC) 

step 2: import and clean the data

tirerating_df <- read_excel("~/Downloads/RMarkdown/Class Exercise 15.xlsx")
tirerating_df

## # A tibble: 68 × 5
##    Tire                                        Wet Noise Buy_Again Purchase
##    <chr>                                     <dbl> <dbl>     <dbl>    <dbl>
##  1 BFGoodrich g-Force Super Sport A/S          8     7.2       6.1        0
##  2 BFGoodrich g-Force Super Sport A/S H&V      8     7.2       6.6        1
##  3 BFGoodrich g-Force T/A KDWS                 7.6   7.5       6.9        1
##  4 Bridgestone B381                            6.6   5.4       6.6        0
##  5 Bridgestone Insignia SE200                  5.8   6.3       4          0
##  6 Bridgestone Insignia SE200-02               6.3   5.7       4.5        0
##  7 Bridgestone Potenza G 019 Grid              7.7   5.2       5          0
##  8 Bridgestone Potenza RE92                    5     6.2       2.5        0
##  9 Bridgestone Potenza RE92A                   5.6   6.4       2.7        0
## 10 Bridgestone Potenza RE960AS Pole Position   8.8   8.5       8.1        1
## # ℹ 58 more rows

tr_df <- subset(tirerating_df, select = -c(Tire))

Step 3: summarize the data

summary(tr_df)

##       Wet            Noise         Buy_Again        Purchase     
##  Min.   :4.300   Min.   :3.600   Min.   :1.400   Min.   :0.0000  
##  1st Qu.:6.450   1st Qu.:6.000   1st Qu.:3.850   1st Qu.:0.0000  
##  Median :7.750   Median :7.100   Median :6.150   Median :0.0000  
##  Mean   :7.315   Mean   :6.903   Mean   :5.657   Mean   :0.4412  
##  3rd Qu.:8.225   3rd Qu.:7.925   3rd Qu.:7.400   3rd Qu.:1.0000  
##  Max.   :9.200   Max.   :8.900   Max.   :8.900   Max.   :1.0000

Step 4: feature selection( correlation analysis)

corr <- rcorr(as.matrix(tr_df))
corr

##            Wet Noise Buy_Again Purchase
## Wet       1.00  0.76      0.91     0.74
## Noise     0.76  1.00      0.83     0.72
## Buy_Again 0.91  0.83      1.00     0.83
## Purchase  0.74  0.72      0.83     1.00
## 
## n= 68 
## 
## 
## P
##           Wet Noise Buy_Again Purchase
## Wet            0     0         0      
## Noise      0         0         0      
## Buy_Again  0   0               0      
## Purchase   0   0     0

Step 5: build the logistic regression

model <- glm(Purchase ~ Wet + Noise, data = tr_df, family = binomial)
summary(model)

## 
## Call:
## glm(formula = Purchase ~ Wet + Noise, family = binomial, data = tr_df)
## 
## Coefficients:
##             Estimate Std. Error z value Pr(>|z|)   
## (Intercept) -39.4982    12.4779  -3.165  0.00155 **
## Wet           3.3745     1.2641   2.670  0.00760 **
## Noise         1.8163     0.8312   2.185  0.02887 * 
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## (Dispersion parameter for binomial family taken to be 1)
## 
##     Null deviance: 93.325  on 67  degrees of freedom
## Residual deviance: 27.530  on 65  degrees of freedom
## AIC: 33.53
## 
## Number of Fisher Scoring iterations: 8

Step 6: Pseudo-R-squared

pR2(model)

## fitting null model for pseudo-r2

##         llh     llhNull          G2    McFadden        r2ML        r2CU 
## -13.7649516 -46.6623284  65.7947536   0.7050093   0.6199946   0.8305269

###Question 4&5: predicting with new information

new_data1 <- data.frame(Wet = 8, Noise = 8) #buy again
new_data2 <- data.frame(Wet = 7, Noise = 7) # not buy again

prob1 <- predict(model, new_data1, type = "response") #probability that customers will buy again
prob1 *100 #88.37% that customers will buy again

##        1 
## 88.36964

prob2 <- predict(model, new_data2, type = "response") #probability that customers will not buy again
prob2 *100 #4.06% that customers will not buy again

##        1 
## 4.058753