Setup

library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.6.0
## ✔ ggplot2   4.0.0     ✔ tibble    3.3.0
## ✔ lubridate 1.9.4     ✔ tidyr     1.3.1
## ✔ purrr     1.2.0     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

library(moderndive)
library(infer)
library(DT)
load("OAW2309.Rdata")

Dummy Variables Model

Use the OAW2309 dataframe Create a linear regression model to predict the mean value of TMAX from the calendar month. Call this TMAX_mo_T.

Solution

TMAX_mo_T = lm(TMAX~mo,data=OAW2309)

Use summary() to examine the model.

Solution

summary(TMAX_mo_T)

## 
## Call:
## lm(formula = TMAX ~ mo, data = OAW2309)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -29.940  -5.033  -0.530   4.470  38.967 
## 
## Coefficients:
##             Estimate Std. Error t value Pr(>|t|)    
## (Intercept) 44.90791    0.14427 311.284   <2e-16 ***
## mo2          4.03164    0.20892  19.297   <2e-16 ***
## mo3          8.44918    0.20404  41.409   <2e-16 ***
## mo4         14.05624    0.20580  68.300   <2e-16 ***
## mo5         21.14569    0.20372 103.796   <2e-16 ***
## mo6         26.12542    0.20507 127.400   <2e-16 ***
## mo7         32.62203    0.20341 160.377   <2e-16 ***
## mo8         32.56430    0.20339 160.109   <2e-16 ***
## mo9         26.78366    0.20507 130.610   <2e-16 ***
## mo10        15.71011    0.20400  77.009   <2e-16 ***
## mo11         5.62339    0.20570  27.338   <2e-16 ***
## mo12        -0.06303    0.20404  -0.309    0.757    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 7.272 on 30063 degrees of freedom
## Multiple R-squared:  0.7198, Adjusted R-squared:  0.7197 
## F-statistic:  7019 on 11 and 30063 DF,  p-value: < 2.2e-16

Use the Improved Modern Dive Alternative

Use get_regression_table(). Compare with summary().

Solution

regression_table_T = get_regression_table(TMAX_mo_T)
str(regression_table_T)

## tibble [12 × 7] (S3: tbl_df/tbl/data.frame)
##  $ term     : chr [1:12] "intercept" "mo: 2" "mo: 3" "mo: 4" ...
##  $ estimate : num [1:12] 44.91 4.03 8.45 14.06 21.15 ...
##  $ std_error: num [1:12] 0.144 0.209 0.204 0.206 0.204 0.205 0.203 0.203 0.205 0.204 ...
##  $ statistic: num [1:12] 311.3 19.3 41.4 68.3 103.8 ...
##  $ p_value  : num [1:12] 0 0 0 0 0 0 0 0 0 0 ...
##  $ lower_ci : num [1:12] 44.62 3.62 8.05 13.65 20.75 ...
##  $ upper_ci : num [1:12] 45.19 4.44 8.85 14.46 21.55 ...

datatable(regression_table_T)

Obtain fitted and residuals dataframe.

Solution

fitted_and_residuals_T = get_regression_points(TMAX_mo_T)
str(fitted_and_residuals_T)

## tibble [30,075 × 5] (S3: tbl_df/tbl/data.frame)
##  $ ID      : int [1:30075] 1 2 3 4 5 6 7 8 9 10 ...
##  $ TMAX    : num [1:30075] 66 63 58 55 57 59 58 65 68 85 ...
##  $ mo      : Factor w/ 12 levels "1","2","3","4",..: 5 5 5 5 5 5 5 5 5 5 ...
##  $ TMAX_hat: num [1:30075] 66.1 66.1 66.1 66.1 66.1 ...
##  $ residual: num [1:30075] -0.054 -3.054 -8.054 -11.054 -9.054 ...
##  - attr(*, "terms")=Classes 'terms', 'formula'  language TMAX ~ mo
##   .. ..- attr(*, "variables")= language list(TMAX, mo)
##   .. ..- attr(*, "factors")= int [1:2, 1] 0 1
##   .. .. ..- attr(*, "dimnames")=List of 2
##   .. .. .. ..$ : chr [1:2] "TMAX" "mo"
##   .. .. .. ..$ : chr "mo"
##   .. ..- attr(*, "term.labels")= chr "mo"
##   .. ..- attr(*, "order")= int 1
##   .. ..- attr(*, "intercept")= int 1
##   .. ..- attr(*, "response")= int 1
##   .. ..- attr(*, ".Environment")=<environment: R_GlobalEnv> 
##   .. ..- attr(*, "predvars")= language list(TMAX, mo)
##   .. ..- attr(*, "dataClasses")= Named chr [1:2] "numeric" "factor"
##   .. .. ..- attr(*, "names")= chr [1:2] "TMAX" "mo"

knitr::kable(fitted_and_residuals_T)