This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.
When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:
summary(cars)
## speed dist
## Min. : 4.0 Min. : 2.00
## 1st Qu.:12.0 1st Qu.: 26.00
## Median :15.0 Median : 36.00
## Mean :15.4 Mean : 42.98
## 3rd Qu.:19.0 3rd Qu.: 56.00
## Max. :25.0 Max. :120.00
You can also embed plots, for example:
Note that the echo = FALSE parameter was added to the
code chunk to prevent printing of the R code that generated the
plot.
insurance <- read.csv("C:/Users/Home/Downloads/insurance.csv", stringsAsFactors=TRUE)
# Set the CRAN mirror
options(repos = "https://cloud.r-project.org/")
# Install the "psych" package
install.packages("psych")
## Installing package into 'C:/Users/Home/AppData/Local/R/win-library/4.3'
## (as 'lib' is unspecified)
## package 'psych' successfully unpacked and MD5 sums checked
##
## The downloaded binary packages are in
## C:\Users\Home\AppData\Local\Temp\RtmpovLYEV\downloaded_packages
library(psych)
## Warning: package 'psych' was built under R version 4.3.3
View(insurance)
#in this data set we are trying see the relation between the attribute
str(insurance)# to see the structure of the data set
## 'data.frame': 1338 obs. of 7 variables:
## $ age : int 19 18 28 33 32 31 46 37 37 60 ...
## $ sex : Factor w/ 2 levels "female","male": 1 2 2 2 2 1 1 1 2 1 ...
## $ bmi : num 27.9 33.8 33 22.7 28.9 ...
## $ children: int 0 1 3 0 0 0 1 3 2 0 ...
## $ smoker : Factor w/ 2 levels "no","yes": 2 1 1 1 1 1 1 1 1 1 ...
## $ region : Factor w/ 4 levels "northeast","northwest",..: 4 3 3 2 2 3 3 2 1 2 ...
## $ charges : num 16885 1726 4449 21984 3867 ...
summary(insurance) # note that mean and median is quite far ,this means
## age sex bmi children smoker
## Min. :18.00 female:662 Min. :15.96 Min. :0.000 no :1064
## 1st Qu.:27.00 male :676 1st Qu.:26.30 1st Qu.:0.000 yes: 274
## Median :39.00 Median :30.40 Median :1.000
## Mean :39.21 Mean :30.66 Mean :1.095
## 3rd Qu.:51.00 3rd Qu.:34.69 3rd Qu.:2.000
## Max. :64.00 Max. :53.13 Max. :5.000
## region charges
## northeast:324 Min. : 1122
## northwest:325 1st Qu.: 4740
## southeast:364 Median : 9382
## southwest:325 Mean :13270
## 3rd Qu.:16640
## Max. :63770
#from each other
hist(insurance$charges)
table(insurance$region)
##
## northeast northwest southeast southwest
## 324 325 364 325
prop.table(table(insurance$region))
##
## northeast northwest southeast southwest
## 0.2421525 0.2428999 0.2720478 0.2428999
table(insurance$sex)
##
## female male
## 662 676
prop.table(table(insurance$sex))
##
## female male
## 0.4947683 0.5052317
table(insurance$smoker)
##
## no yes
## 1064 274
prop.table(table(insurance$smoker))
##
## no yes
## 0.7952167 0.2047833
pairs(insurance[c('age','bmi','children', 'charges')])
pairs.panels(insurance[c('age','bmi','children', 'charges')])
ins_model<-lm(charges~ age+ children + bmi + sex+smoker+region,data=insurance)
ins_model<-lm(charges~.,data=insurance)
ins_model
##
## Call:
## lm(formula = charges ~ ., data = insurance)
##
## Coefficients:
## (Intercept) age sexmale bmi
## -11938.5 256.9 -131.3 339.2
## children smokeryes regionnorthwest regionsoutheast
## 475.5 23848.5 -353.0 -1035.0
## regionsouthwest
## -960.1
summary(ins_model)
##
## Call:
## lm(formula = charges ~ ., data = insurance)
##
## Residuals:
## Min 1Q Median 3Q Max
## -11304.9 -2848.1 -982.1 1393.9 29992.8
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -11938.5 987.8 -12.086 < 2e-16 ***
## age 256.9 11.9 21.587 < 2e-16 ***
## sexmale -131.3 332.9 -0.394 0.693348
## bmi 339.2 28.6 11.860 < 2e-16 ***
## children 475.5 137.8 3.451 0.000577 ***
## smokeryes 23848.5 413.1 57.723 < 2e-16 ***
## regionnorthwest -353.0 476.3 -0.741 0.458769
## regionsoutheast -1035.0 478.7 -2.162 0.030782 *
## regionsouthwest -960.0 477.9 -2.009 0.044765 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 6062 on 1329 degrees of freedom
## Multiple R-squared: 0.7509, Adjusted R-squared: 0.7494
## F-statistic: 500.8 on 8 and 1329 DF, p-value: < 2.2e-16
insurance$bmi30<-ifelse(insurance$bmi>=30,1,0)
insurance$bmi30
## [1] 0 1 1 0 0 0 1 0 0 0 0 0 1 1 1 0 1 0 1 1 1 1 1 1 0 0 0 1 0 1 1 0 0 0 1 0 1
## [38] 0 1 1 0 1 0 1 1 1 1 1 0 1 1 1 0 1 0 1 1 1 0 1 0 1 0 0 0 0 1 0 1 0 0 0 0 1
## [75] 0 1 0 1 1 1 0 1 1 1 1 0 1 0 0 0 1 0 0 1 1 1 1 1 0 0 1 0 1 0 0 0 0 1 0 1 1
## [112] 0 1 1 1 0 1 0 0 0 1 0 0 1 1 0 0 1 0 1 0 0 1 0 0 0 1 0 1 1 0 1 0 0 0 1 1 1
## [149] 1 0 0 0 1 0 0 1 0 0 1 0 0 1 1 0 0 0 1 1 1 0 1 1 0 1 1 1 0 0 0 1 0 1 0 0 1
## [186] 1 0 1 1 1 1 0 0 0 1 1 1 0 0 1 1 1 0 1 0 0 0 0 1 1 1 1 0 0 1 1 0 0 0 0 1 1
## [223] 1 1 0 1 1 1 1 0 1 0 0 0 0 0 0 1 0 1 1 0 0 1 0 1 1 1 0 0 0 1 1 1 1 0 1 1 0
## [260] 1 0 0 0 1 1 1 0 1 1 0 0 1 1 0 0 0 0 0 1 0 0 1 0 1 1 0 1 0 1 0 1 0 1 0 0 0
## [297] 0 0 1 0 0 0 1 1 1 1 0 1 1 1 0 0 1 1 1 1 1 1 0 1 0 0 1 1 0 1 0 1 1 1 1 0 1
## [334] 0 1 1 0 0 1 0 0 1 0 1 1 0 1 1 0 0 0 0 0 1 1 0 1 0 1 0 1 1 0 0 0 1 1 0 1 1
## [371] 0 0 1 1 1 0 0 1 1 1 0 1 1 1 0 1 1 0 0 1 1 1 1 1 1 0 1 1 0 1 0 1 1 1 0 1 0
## [408] 0 0 1 0 0 0 0 1 1 1 0 1 0 1 1 1 1 1 0 0 0 0 1 1 0 0 1 0 1 1 0 1 0 1 1 1 1
## [445] 0 1 0 0 0 1 0 0 0 0 1 1 1 1 1 1 1 1 1 0 0 0 0 1 0 0 1 1 0 1 0 0 0 1 1 1 1
## [482] 1 1 1 1 1 0 0 1 1 1 0 0 1 0 0 0 0 0 1 1 0 0 1 0 1 1 0 0 0 1 1 0 1 0 1 1 1
## [519] 1 1 0 1 1 1 0 1 1 0 1 0 1 1 0 1 1 0 1 1 0 1 1 1 1 1 1 0 1 1 0 1 1 0 0 1 1
## [556] 0 1 1 1 1 0 1 1 1 1 1 1 1 1 1 0 1 1 1 1 0 0 1 1 0 0 1 1 0 0 0 0 1 1 1 0 0
## [593] 1 0 1 1 0 1 1 1 1 1 0 1 0 1 0 0 0 1 0 1 1 0 1 1 0 0 1 1 1 1 0 1 0 0 0 1 1
## [630] 1 1 0 1 0 1 1 0 1 0 1 1 0 1 1 1 1 0 0 0 1 1 1 1 1 1 0 1 1 1 0 1 0 1 1 0 1
## [667] 0 1 1 0 1 1 0 1 1 0 1 1 1 0 0 0 1 0 0 0 0 1 0 1 0 1 1 0 1 1 1 1 1 1 1 1 1
## [704] 0 0 1 1 0 1 0 1 0 1 1 0 0 0 0 1 1 1 1 1 1 0 1 0 0 1 1 0 0 1 0 1 1 1 0 1 1
## [741] 0 0 1 0 0 1 0 0 1 1 0 0 1 0 1 0 0 0 1 1 1 1 0 0 0 1 1 0 1 0 1 0 1 0 1 1 1
## [778] 1 1 0 0 1 1 0 0 0 1 1 0 0 1 0 0 0 1 0 1 0 1 0 0 1 0 1 0 1 1 1 1 0 1 1 0 0
## [815] 1 1 0 1 0 1 1 0 1 0 0 1 1 0 1 0 1 0 0 1 1 1 1 0 0 1 1 0 1 0 1 1 1 1 0 1 1
## [852] 1 1 0 0 0 1 0 1 0 1 0 1 0 0 0 1 1 0 0 1 0 0 1 0 0 0 1 0 0 1 0 0 1 0 0 0 1
## [889] 1 1 0 0 0 1 1 1 0 0 1 0 0 1 0 1 1 0 1 1 1 0 0 1 0 0 0 1 0 0 0 1 0 1 1 1 0
## [926] 1 0 0 1 1 1 1 0 1 1 0 0 0 0 0 0 1 1 0 1 1 1 1 1 0 0 1 0 1 0 1 1 0 1 1 1 0
## [963] 1 0 1 0 0 0 0 1 0 0 0 1 1 0 1 0 1 0 0 0 0 1 1 0 1 0 1 0 0 0 1 0 0 0 1 1 1
## [1000] 0 0 1 0 0 0 1 0 0 0 0 0 0 1 1 0 0 0 1 1 1 1 1 1 0 1 1 0 0 1 0 0 1 0 0 1 0
## [1037] 1 1 0 0 0 0 1 0 1 0 0 1 0 1 1 0 0 0 0 0 0 1 1 1 1 0 1 0 0 0 1 1 0 1 1 1 1
## [1074] 0 0 0 1 0 1 1 0 0 0 1 1 0 0 1 1 0 1 0 1 1 1 1 1 1 1 1 0 0 1 1 0 1 0 0 1 0
## [1111] 1 1 0 0 0 1 0 1 1 0 1 1 1 1 1 0 0 1 1 0 0 1 1 0 1 0 0 0 1 1 1 1 0 1 1 1 1
## [1148] 1 0 1 1 1 1 1 0 0 1 0 1 1 1 1 1 0 0 0 1 0 1 1 0 0 1 0 1 0 0 0 1 0 1 0 1 0
## [1185] 0 0 1 1 0 0 1 0 1 1 0 0 1 1 0 0 0 1 1 1 0 0 1 1 0 1 1 1 0 1 1 1 0 1 1 1 0
## [1222] 0 0 0 0 1 0 1 1 1 1 0 0 0 0 1 0 0 0 1 1 1 0 1 1 0 0 0 1 1 0 0 0 0 0 1 1 0
## [1259] 1 0 0 1 0 0 1 0 1 1 1 0 1 1 0 0 0 0 1 0 0 0 1 0 0 1 1 0 0 0 1 1 0 1 0 0 0
## [1296] 0 0 0 0 0 1 1 0 0 0 0 0 0 1 1 0 0 1 1 0 0 0 1 1 0 1 0 1 1 0 1 1 1 0 1 0 1
## [1333] 1 1 1 1 0 0
ins_model2<-lm(charges~ age+age+children+bmi+sex+bmi30*smoker + region, data=insurance)