#library(readxl)
#Uploading the data
#ageandheight <- read_excel("AgeHeight.xl",sheet = "Hoja2")
#Creating the linear regression
#lmHeights = lm(height~age, data = AgeHeight)
#Review the results
#summary(lmHeights)
library(readxl)
AgeHeight <- read_excel("/Users/deveonwright/Downloads/AgeHeight.xlsx")
View(AgeHeight)
lm(formula = height~age,data = AgeHeight)
##
## Call:
## lm(formula = height ~ age, data = AgeHeight)
##
## Coefficients:
## (Intercept) age
## 64.928 0.635
lmHeight = lm(height~age, data = AgeHeight)
lmHeight2 = lm(height~age + no_siblings, data = AgeHeight)
summary(lmHeight)
##
## Call:
## lm(formula = height ~ age, data = AgeHeight)
##
## 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
summary(lmHeight2)
##
## Call:
## lm(formula = height ~ age + no_siblings, data = AgeHeight)
##
## 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)
library(psych)
## Warning: package 'psych' was built under R version 4.3.3
library(ggplot2)
## Warning: package 'ggplot2' was built under R version 4.3.2
##
## Attaching package: 'ggplot2'
## The following objects are masked from 'package:psych':
##
## %+%, alpha
insurance <- read_csv("/Users/deveonwright/Downloads/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)
head(insurance)
## # A tibble: 6 × 7
## age sex bmi children smoker region charges
## <dbl> <chr> <dbl> <dbl> <chr> <chr> <dbl>
## 1 19 female 27.9 0 yes southwest 16885.
## 2 18 male 33.8 1 no southeast 1726.
## 3 28 male 33 3 no southeast 4449.
## 4 33 male 22.7 0 no northwest 21984.
## 5 32 male 28.9 0 no northwest 3867.
## 6 31 female 25.7 0 no southeast 3757.
summary(insurance)
## age sex bmi children
## Min. :18.00 Length:1338 Min. :15.96 Min. :0.000
## 1st Qu.:27.00 Class :character 1st Qu.:26.30 1st Qu.:0.000
## Median :39.00 Mode :character 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
## smoker region charges
## Length:1338 Length:1338 Min. : 1122
## Class :character Class :character 1st Qu.: 4740
## Mode :character Mode :character Median : 9382
## Mean :13270
## 3rd Qu.:16640
## Max. :63770
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>
numeric_vars <- insurance[, sapply(insurance, is.numeric)]
cor(numeric_vars)
## 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
pairs(insurance[c("age", "bmi", "children", "charges")])
pairs.panels(insurance[c("age", "bmi", "children", "charges")])
model1 <- lm(charges ~ age, data = insurance)
summary(model1)
##
## Call:
## lm(formula = charges ~ age, data = insurance)
##
## Residuals:
## Min 1Q Median 3Q Max
## -8059 -6671 -5939 5440 47829
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3165.9 937.1 3.378 0.000751 ***
## age 257.7 22.5 11.453 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 11560 on 1336 degrees of freedom
## Multiple R-squared: 0.08941, Adjusted R-squared: 0.08872
## F-statistic: 131.2 on 1 and 1336 DF, p-value: < 2.2e-16
model2 <- lm(charges ~ ., data = insurance)
summary(model2)
##
## 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
plot(model2$residuals, main = "Residuals Plot", ylab = "Residuals", col = "blue")
# Add squared age and BMI indicator
insurance$age2 <- insurance$age^2
insurance$bmi30 <- ifelse(insurance$bmi >= 30, 1, 0)
# New model with interaction
model3 <- lm(charges ~ age + age2 + children + bmi + sex + bmi30 * smoker + region, data = insurance)
summary(model3)
##
## Call:
## lm(formula = charges ~ age + age2 + children + bmi + sex + bmi30 *
## smoker + region, data = insurance)
##
## Residuals:
## Min 1Q Median 3Q Max
## -17296.4 -1656.0 -1263.3 -722.1 24160.2
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 134.2509 1362.7511 0.099 0.921539
## age -32.6851 59.8242 -0.546 0.584915
## age2 3.7316 0.7463 5.000 6.50e-07 ***
## children 678.5612 105.8831 6.409 2.04e-10 ***
## bmi 120.0196 34.2660 3.503 0.000476 ***
## sexmale -496.8245 244.3659 -2.033 0.042240 *
## bmi30 -1000.1403 422.8402 -2.365 0.018159 *
## smokeryes 13404.6866 439.9491 30.469 < 2e-16 ***
## regionnorthwest -279.2038 349.2746 -0.799 0.424212
## regionsoutheast -828.5467 351.6352 -2.356 0.018604 *
## regionsouthwest -1222.6437 350.5285 -3.488 0.000503 ***
## bmi30:smokeryes 19810.7533 604.6567 32.764 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 4445 on 1326 degrees of freedom
## Multiple R-squared: 0.8664, Adjusted R-squared: 0.8653
## F-statistic: 781.7 on 11 and 1326 DF, p-value: < 2.2e-16