Module 8. Assignment

-

    For this week's lab, I used R's built-in mtcars dataset to look into how weight and horsepower of a car affect its gas mileage (MPG). I did both association and regression studies, and both showed strong negative relationships: cars that are larger and more powerful get worse gas mileage.

I used ggplot2 to make a scatter plot with a regression line and a segmented comparison that puts both factors next to each other. With Facets, it was easy to compare two relationships without all the extra stuff. Few told me to use bland colors, little ink, and clear labels, which made it easy to read and understand the falling trends.


R code 

mtcars

# Use cor() to compute correlation matrices.

cor_matrix <- cor(mtcars[, c("mpg", "wt", "hp", "disp")])
round(cor_matrix, 2)

m_mpg_wt <- lm(mpg ~ wt, data = mtcars)
summary(m_mpg_wt)

library(ggplot2)
library(tidyr)

ggplot(mtcars, aes(x = wt, y = mpg)) +
  geom_point(color = "steelblue", size = 3) +            # scatter
  stat_smooth(method = "lm", color = "red", se = TRUE) + # regression line
  labs(title = "MPG vs Weight",
       x = "Weight (1000 lbs)",
       y = "Miles per Gallon (MPG)") +
  theme_minimal()


mtcars_long <- mtcars |>
  dplyr::select(mpg, wt, hp) |>
  pivot_longer(cols = c(wt, hp), names_to = "variable", values_to = "value")

ggplot(mtcars_long, aes(x = value, y = mpg)) +
  geom_point(color = "darkorange", size = 2) +
  stat_smooth(method = "lm", color = "red", se = TRUE) +
  facet_wrap(~ variable, scales = "free_x") +
  labs(title = "MPG Compared to Weight and Horsepower",
       x = "Predictor Value",
       y = "Miles per Gallon (MPG)") +
  theme_bw()








What patterns or relationships did you observe?
 I was surprised by how clearly the results showed trends since this was the first time I had used R to do correlation and regression.  I saw that the MPG went down as the car's weight or horsepower went up.  It was easy to see that because both of the red regression lines went down, showing a strong negative link.

How did your use of grid layout or facets enhance interpretation?
 The facet structure really helped me get a better sense of the similarity.  Instead of putting everything on one chart, it was easier to look at two easy plots next to each other.  The fact that each panel showed how a different variable affected MPG made it a lot easier for me to understand at first.

In your opinion, how do Few’s recommendations help or hinder your design choices?
 Few's advice to keep images clean and simple really did help a lot.  Since I'm still learning, my graphs looked better and were easier to understand when I used fewer colors and a clear background.  It also helped me keep my mind on the facts instead of getting sidetracked by the details of the design

Comments

Post a Comment

Popular posts from this blog

LIS 4317 Final Project – Diamonds Analysis

-
Image
Diamonds constitute one of the most extensively examined datasets in R due to their numerous quality attributes that affect valuation. For this undertaking, I employed the diamonds dataset from the ggplot2 package to investigate the relationship between carat (weight), cut quality, and clarity in relation to diamond prices. This dataset provided an opportunity to apply and demonstrate proficiency in distribution analysis, comparative evaluation, and multivariate visualization methods acquired during LIS 4317. Overview of the Dataset The diamonds dataset comprises 53,940 observations and ten variables, thereby satisfying the project's criterion of a minimum of fifty rows and five to twenty variables. Key variables encompass: Cost – Price of diamond in United States dollars Carat – the mass of the diamond Reduce — reduction in quality levels (Fair, Good, Very Good, Premium, Ideal) Color – the process of color grading Clarity – Evaluation of transparency and lucidity I ...
Read more

Visualizing Distributions in R

-
Image
  The goal for this week was to make a distribution visualization in R and think about how well it worked. I used the usual mtcars dataset that comes with R for this purpose. This multidimensional figure makes it evident that there is a negative correlation: as the weight of the automobile goes up, the MPG goes down. The grid also reveals that automobiles with 4, 6, and 8 cylinders are grouped together. This design follows the advice of Stephen Few and Nathan Yau, who say that tiny multiples with aligned axes are better for straightforward comparison than a single, overloaded chart. I completely agree with Few's criticism that conventional ways of visualizing data, including layering graphs, might hide the underlying structure of a dataset. This way of breaking the facts into a grid makes the tale more clearer and more honest. R-code # Load the ggplot2 library library(ggplot2) # Create a density plot ggplot(mtcars, aes(x = mpg)) + geom_density(fill = "skyblue", ...
Read more

Module 5. Part-to-Whole and Ranking Analysis

-
Image
  I used a dataset that is split into groups (T, S, R, Q, and Other) for this lesson so I could see how each part fits in with the whole. It was easy for me to choose because the numbers make it clear how the different groups are different. There are three different stories in the donut charts: The total numbers are shown in X.1. "Other" is much bigger than the others. In terms of rank, the average position shows that "Other" is way ahead of the others, with the others being close behind. Time shows how long each group takes, and we can see that one group takes most of the time. Visuals that show the relationship between parts and wholes are a quick way to show who has the biggest share. They look good on a blog and are easy to read. But it's harder to see the little changes between the slices, so a bar chart would be better some of the time. In general, I like how this chart makes the imbalance clear while also letting me know the boundaries when I...
Read more