Penguin Flipper Length and Body Mass
Jackeline Gamez
October 16, 2026
Introduction
Penguins come in different sizes, and their flipper lengths might be related to how much they weigh. By looking at these two measurements, we can see if penguins with longer flippers also tend to weigh more. Since there are different types of penguins, I will also compare the species to see if the relationship is different.
This project looks at the question: Is there a relationship
between a penguin’s flipper length and its body mass, and does this
relationship change depending on the species? I will use the
Palmer Penguins dataset from the palmerpenguins R package.
The data were collected by Dr. Kristen Gorman and the Palmer Station
research program in Antarctica. I will focus on three variables:
flipper_length_mm, which is the length of a penguin’s
flippers in millimeters; body_mass_g, which is the
penguin’s weight in grams; and species, which tells us what
type of penguin it is: Adelie, Chinstrap, or Gentoo (Horst, Hill, &
Gorman, 2020).
Data Analysis
First, I will look at the dataset and check if any information is missing. I will remove rows that are missing any of the three variables I need. Then, I will calculate summary statistics for each penguin species and make a scatter plot to show the relationship between flipper length and body mass. Each species will have its own color, and the graph will include a trend line for each species. Finally, I will use a linear regression model to study how flipper length and species are related to body mass. These steps will help me understand the patterns in the data, but they will not prove that flipper length causes a penguin to weigh more or less.
1. Load the dataset and inspect it
# Load the dataset from the palmerpenguins package
data("penguins", package = "palmerpenguins")
# Preview the data and check its structure
head(penguins)str(penguins)## tibble [344 × 8] (S3: tbl_df/tbl/data.frame)
## $ species : Factor w/ 3 levels "Adelie","Chinstrap",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ island : Factor w/ 3 levels "Biscoe","Dream",..: 3 3 3 3 3 3 3 3 3 3 ...
## $ bill_length_mm : num [1:344] 39.1 39.5 40.3 NA 36.7 39.3 38.9 39.2 34.1 42 ...
## $ bill_depth_mm : num [1:344] 18.7 17.4 18 NA 19.3 20.6 17.8 19.6 18.1 20.2 ...
## $ flipper_length_mm: int [1:344] 181 186 195 NA 193 190 181 195 193 190 ...
## $ body_mass_g : int [1:344] 3750 3800 3250 NA 3450 3650 3625 4675 3475 4250 ...
## $ sex : Factor w/ 2 levels "female","male": 2 1 1 NA 1 2 1 2 NA NA ...
## $ year : int [1:344] 2007 2007 2007 2007 2007 2007 2007 2007 2007 2007 ...dim(penguins)## [1] 344 8The first rows provide a preview of the observations,
str() shows the variables and their data types, and
dim() reports the number of rows and columns.
2. Check missing values and clean the data
# Count missing values in the variables used for this project
colSums(is.na(penguins[, c("flipper_length_mm", "body_mass_g", "species")]))## flipper_length_mm body_mass_g species
## 2 2 0# Keep the three relevant columns and remove rows with missing values
penguins_clean <- penguins |>
dplyr::select(species, flipper_length_mm, body_mass_g) |>
dplyr::filter(
!is.na(species),
!is.na(flipper_length_mm),
!is.na(body_mass_g)
)
# Check the cleaned dataset
dim(penguins_clean)## [1] 342 3summary(penguins_clean)## species flipper_length_mm body_mass_g
## Adelie :151 Min. :172.0 Min. :2700
## Chinstrap: 68 1st Qu.:190.0 1st Qu.:3550
## Gentoo :123 Median :197.0 Median :4050
## Mean :200.9 Mean :4202
## 3rd Qu.:213.0 3rd Qu.:4750
## Max. :231.0 Max. :6300This step keeps only the information needed for my research question and removes any rows with missing information. The summary helps me see the lowest, highest, and average values in the data.
3. Summarize measurements by species
species_summary <- penguins_clean |>
dplyr::group_by(species) |>
dplyr::summarise(
penguin_count = dplyr::n(),
mean_flipper_length_mm = mean(flipper_length_mm),
mean_body_mass_g = mean(body_mass_g),
median_body_mass_g = median(body_mass_g),
.groups = "drop"
)
knitr::kable(
species_summary,
digits = 2,
caption = "Flipper length and body mass summary by penguin species"
)| species | penguin_count | mean_flipper_length_mm | mean_body_mass_g | median_body_mass_g |
|---|---|---|---|---|
| Adelie | 151 | 189.95 | 3700.66 | 3700 |
| Chinstrap | 68 | 195.82 | 3733.09 | 3700 |
| Gentoo | 123 | 217.19 | 5076.02 | 5000 |
This table shows how many penguins are in each species and compares their average flipper length and body weight. It also shows the middle body weight for each species to help us understand their sizes.
4. Visualize the relationship
library(ggplot2)
ggplot(
penguins_clean,
aes(x = flipper_length_mm, y = body_mass_g, color = species)
) +
geom_point(alpha = 0.75, size = 2) +
geom_smooth(method = "lm", se = FALSE) +
labs(
title = "Penguin Flipper Length and Body Mass",
subtitle = "Points and fitted linear trends are shown by species",
x = "Flipper length (millimeters)",
y = "Body mass (grams)",
color = "Species"
) +
theme_minimal()
Each point on the graph represents one penguin. The different colors show the three penguin species, and the lines show the patterns in the data. These lines help us see if penguins with longer flippers also tend to weigh more within each species.
5. Fit a linear regression model
model <- lm(body_mass_g ~ flipper_length_mm * species, data = penguins_clean)
summary(model)##
## Call:
## lm(formula = body_mass_g ~ flipper_length_mm * species, data = penguins_clean)
##
## Residuals:
## Min 1Q Median 3Q Max
## -911.18 -251.93 -31.77 197.82 1144.81
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -2535.837 879.468 -2.883 0.00419 **
## flipper_length_mm 32.832 4.627 7.095 7.69e-12 ***
## speciesChinstrap -501.359 1523.459 -0.329 0.74229
## speciesGentoo -4251.444 1427.332 -2.979 0.00311 **
## flipper_length_mm:speciesChinstrap 1.742 7.856 0.222 0.82467
## flipper_length_mm:speciesGentoo 21.791 6.941 3.139 0.00184 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 370.6 on 336 degrees of freedom
## Multiple R-squared: 0.7896, Adjusted R-squared: 0.7864
## F-statistic: 252.2 on 5 and 336 DF, p-value: < 2.2e-16This model looks at flipper length, penguin species, and how they are related to body weight. It helps us see if the relationship between flipper length and weight is different for each species. The results give us numbers that we can compare with the table and graph. However, this does not prove that longer flippers cause penguins to weigh more.
Conclusion and Future Directions
Conclusion and Future Directions
After looking at the results, I found that penguins with longer flippers tend to weigh more. The table shows that Gentoo penguins have the longest flippers and weigh the most on average. Adelie and Chinstrap penguins have shorter flippers and weigh less. The graph and model also show that flipper length and body weight are related. However, the relationship is not exactly the same for every species. Gentoo penguins show a stronger relationship than Adelie penguins, while Adelie and Chinstrap penguins have similar patterns. This helps answer my research question because it shows that flipper length is related to body weight, but the relationship can depend on the species.
One limitation of my project is that I only studied flipper length, body weight, and species. The dataset also includes information about whether penguins are male or female, which island they were found on, and their bill measurements. These things might also be related to their body weight. In the future, I could study these other factors to learn more about penguin sizes. I could also compare other penguin datasets to see if the results are similar. My findings only describe the penguins in this dataset, so they might not be the same for all penguins.
References
Horst, A. M., Hill, A. P., & Gorman, K. B. (2020). palmerpenguins: Palmer Archipelago (Antarctica) penguin data. https://github.com/allisonhorst/palmerpenguins
Palmer Penguins project website: https://allisonhorst.github.io/palmerpenguins/