2024-03-17

Simple Linear Regression Formula: Simple

Here is a simple version of the SLR formula:

Simple Formula: \(\hat{y} = a + bx\)

This is the formula where:
\(\hat{y}\) is the dependent variable, dependent on the value of x changing
a is the constant determinant of \(\hat{y}\)
b is the amount in which x affects \(\hat{y}\) when calcualted
x is the independent variable that changes \(\hat{y}\) based on its value

The value of \(\hat{y}\) does not always reflect the true y values from the data provided, just a predictor of what the y value could be based on the data points provided.

These \(\hat{y}\) values can be used to calcualte the residuals which is the difference between the actual y value and the predicted \(\hat{y}\) value.

Simple Linear Regression Formula: Complex

Here is a more complex version of the SLR formula:

Complex Formula: \(\hat{y} = \beta_0 + (\beta_1\cdot x) + \varepsilon \hspace{1 cm}\)

This is the formula where:
\(\hat{y}\) is the dependent variable/ output of the linear regression
\(\beta_0\) is the y-intecept represented as a constant
\(\beta_1\) is the slope or the amount that x contributes to calculating \(\hat{y}\)
X is the independent variable
\(\varepsilon\) is the amount of error within the model

This is similar to the simple version of the formula, just with added vaiables for error and more defined terms that can be used to create multiple linear regression models when multiple variables are present when calculating \(\hat{y}\).

For n \(\beta\) terms, Multiple Linear Regression equations take n-1 beta terms to account for all of the variables considered when calculating \(\hat{y}\) plus the constant term \(\beta_0\).

Dataset iris

The dataset I will be using to model SLR is iris.

Here is the head of the dataset:

##   Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 1          5.1         3.5          1.4         0.2  setosa
## 2          4.9         3.0          1.4         0.2  setosa
## 3          4.7         3.2          1.3         0.2  setosa
## 4          4.6         3.1          1.5         0.2  setosa
## 5          5.0         3.6          1.4         0.2  setosa
## 6          5.4         3.9          1.7         0.4  setosa

Plotly Before Plot (Graph)

Here is the Plotly plot of the data to see the points before creating the SLR line:

Graphing SLR of Petal Width vs Petal Length

In this example, we can see the line created from the \(\hat{y}\) values in the SLR equation when considering petal width and height.

Graphing SLR of Sepal Width vs Sepal Length

In this example, we can see the line created from the \(\hat{y}\) values in the SLR equation sepal width and height.

Programming used to create SLR Graphs

Here is how you create a Single Regression Line graph using ggplot

# Here is the head of the data
head(iris)
##   Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 1          5.1         3.5          1.4         0.2  setosa
## 2          4.9         3.0          1.4         0.2  setosa
## 3          4.7         3.2          1.3         0.2  setosa
## 4          4.6         3.1          1.5         0.2  setosa
## 5          5.0         3.6          1.4         0.2  setosa
## 6          5.4         3.9          1.7         0.4  setosa
# Here is a summary of the data
summary(iris)
##   Sepal.Length    Sepal.Width     Petal.Length    Petal.Width   
##  Min.   :4.300   Min.   :2.000   Min.   :1.000   Min.   :0.100  
##  1st Qu.:5.100   1st Qu.:2.800   1st Qu.:1.600   1st Qu.:0.300  
##  Median :5.800   Median :3.000   Median :4.350   Median :1.300  
##  Mean   :5.843   Mean   :3.057   Mean   :3.758   Mean   :1.199  
##  3rd Qu.:6.400   3rd Qu.:3.300   3rd Qu.:5.100   3rd Qu.:1.800  
##  Max.   :7.900   Max.   :4.400   Max.   :6.900   Max.   :2.500  
##        Species  
##  setosa    :50  
##  versicolor:50  
##  virginica :50  
##                 
##                 
## 
# Here is how you graph a ggplot of the SLR:
ggplot(data = iris, aes(x = Sepal.Width, y = Sepal.Length)) + geom_point(color = "coral") +
    geom_smooth(method = "lm", se = FALSE) + ggtitle("Plot of Sepal Length by Width") +
    xlab("Sepal Width") + ylab("Sepal Length")

gg_plot plots the graph’s data and is needed to start the process
Xlab, Ylab, and ggtitle are all labels
geom_point plots the points on the graph
gg_smooth plots the Single Regression Line onto the graph

Thank You!

Simple Linear Regression is a powerful tool in statistics that can be implement in many facets of data analysis. It can also be expanded upon in many ways such as Multiple Linear Regression.

For more information on Single Linear Regression, please visit these websites:

https://online.stat.psu.edu/stat462/node/91/

https://www.ncl.ac.uk/webtemplate/ask-assets/external/maths-resources/statistics/regression-and-correlation/simple-linear-regression.html

https://online.stat.psu.edu/stat501/lesson/1/1.1