R Markdown

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:

library(readxl)
## Warning: package 'readxl' was built under R version 4.3.3
ageandheight <- read_excel("C:/GGTUAN/DREAMS/Yankee/TSU/MSc_TSU/Spring_2024/CS-583 Data Minning/Project_Data/AgeHeight.xlsx", sheet="Hoja")
ageandheight
## # A tibble: 12 × 3
##      age height no_siblings
##    <dbl>  <dbl>       <dbl>
##  1    18   76.1           1
##  2    19   77             2
##  3    20   78.1           3
##  4    21   78.2           2
##  5    22   78.8           0
##  6    23   79.7           1
##  7    24   79.9           5
##  8    25   81.1           0
##  9    26   81.2           1
## 10    27   81.8           4
## 11    28   82.8           1
## 12    29   83.5           5
lmheight <- lm(height ~ age, data=ageandheight)

summary(lmheight)
## 
## Call:
## lm(formula = height ~ age, data = ageandheight)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -0.27238 -0.24248 -0.02762  0.16014  0.47238 
## 
## Coefficients:
##             Estimate Std. Error t value Pr(>|t|)    
## (Intercept)  64.9283     0.5084  127.71  < 2e-16 ***
## age           0.6350     0.0214   29.66 4.43e-11 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 0.256 on 10 degrees of freedom
## Multiple R-squared:  0.9888, Adjusted R-squared:  0.9876 
## F-statistic:   880 on 1 and 10 DF,  p-value: 4.428e-11
lmheight2 <- lm(height ~ age + no_siblings, data=ageandheight)
summary(lmheight2)
## 
## Call:
## lm(formula = height ~ age + no_siblings, data = ageandheight)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -0.26297 -0.22462 -0.02021  0.16102  0.49752 
## 
## Coefficients:
##             Estimate Std. Error t value Pr(>|t|)    
## (Intercept) 64.90554    0.53526 121.260 8.96e-16 ***
## age          0.63751    0.02340  27.249 5.85e-10 ***
## no_siblings -0.01772    0.04735  -0.374    0.717    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 0.2677 on 9 degrees of freedom
## Multiple R-squared:  0.9889, Adjusted R-squared:  0.9865 
## F-statistic: 402.2 on 2 and 9 DF,  p-value: 1.576e-09
library(readr)
insurance <- read_csv("C:/GGTUAN/DREAMS/Yankee/TSU/MSc_TSU/Spring_2024/CS-583 Data Minning/Project_Data/insurance.csv")
## Rows: 1338 Columns: 7
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (3): sex, smoker, region
## dbl (4): age, bmi, children, charges
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
View(insurance)

insurance2 <- read.csv("C:/GGTUAN/DREAMS/Yankee/TSU/MSc_TSU/Spring_2024/CS-583 Data Minning/Project_Data/insurance.csv", stringsAsFactors=TRUE)
View(insurance2)
str(insurance)
## spc_tbl_ [1,338 × 7] (S3: spec_tbl_df/tbl_df/tbl/data.frame)
##  $ age     : num [1:1338] 19 18 28 33 32 31 46 37 37 60 ...
##  $ sex     : chr [1:1338] "female" "male" "male" "male" ...
##  $ bmi     : num [1:1338] 27.9 33.8 33 22.7 28.9 ...
##  $ children: num [1:1338] 0 1 3 0 0 0 1 3 2 0 ...
##  $ smoker  : chr [1:1338] "yes" "no" "no" "no" ...
##  $ region  : chr [1:1338] "southwest" "southeast" "southeast" "northwest" ...
##  $ charges : num [1:1338] 16885 1726 4449 21984 3867 ...
##  - attr(*, "spec")=
##   .. cols(
##   ..   age = col_double(),
##   ..   sex = col_character(),
##   ..   bmi = col_double(),
##   ..   children = col_double(),
##   ..   smoker = col_character(),
##   ..   region = col_character(),
##   ..   charges = col_double()
##   .. )
##  - attr(*, "problems")=<externalptr>
str(insurance2)
## '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(insurance2)
##       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
hist(insurance2$charges)

table(insurance2$region)
## 
## northeast northwest southeast southwest 
##       324       325       364       325
prop.table(table(insurance2$region))
## 
## northeast northwest southeast southwest 
## 0.2421525 0.2428999 0.2720478 0.2428999
table(insurance2$sex)
## 
## female   male 
##    662    676
prop.table(table(insurance2$sex))
## 
##    female      male 
## 0.4947683 0.5052317
table(insurance2$smoker)
## 
##   no  yes 
## 1064  274
prop.table(table(insurance2$smoker))
## 
##        no       yes 
## 0.7952167 0.2047833
cor(insurance2[c('age', 'bmi', 'children', 'charges')])
##                age       bmi   children    charges
## age      1.0000000 0.1092719 0.04246900 0.29900819
## bmi      0.1092719 1.0000000 0.01275890 0.19834097
## children 0.0424690 0.0127589 1.00000000 0.06799823
## charges  0.2990082 0.1983410 0.06799823 1.00000000
#insurance2.cor = cor(insurance2)
#corrplot(cor(insurance2[c('age', 'bmi', 'children', 'charges')]))

pairs(insurance2[c('age', 'bmi', 'children', 'charges')])

library(psych)
pairs.panels(insurance2[c('age', 'bmi', 'children', 'charges')])

ins_model  <- lm(charges ~ age +children +bmi +sex +smoker +region , data=insurance2)
ins_model2   <- lm(charges ~ . ,  data=insurance2)
ins_model2
## 
## Call:
## lm(formula = charges ~ ., data = insurance2)
## 
## 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 ~ age + children + bmi + sex + smoker + 
##     region, data = insurance2)
## 
## 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 ***
## children           475.5      137.8   3.451 0.000577 ***
## bmi                339.2       28.6  11.860  < 2e-16 ***
## sexmale           -131.3      332.9  -0.394 0.693348    
## 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