The Iberian Lynx (Lynx pardinus) is a species first discovered by Temminck in 1827 [Fosse; et al. 2024]; it is a small carnivore with a patchy distribution of sites across Spain and Portugal [IUCN Red List; 2023]. With a diet consisting of primarily the European rabbit (Oryctolagus cuniculus); a species now considered endangered [IUCN Red List; 2019]; it is a delicate balance for conservationists to properly conserve both predators and prey.
The lynx is currently classified as vulnerable within the IUCN Red List [2023]; but this wasn’t always the case. In 2001, their status was classified as Endangered [IUCN; 2024]. This is estimated to be due to a lack of prey, habitat loss, and persecution from humans [IUCN, 2024]. Conservationists have been working to increase the numbers of prey, protect and restore the forest and scrubland habitats utilized by the lynx, and work on repairing their relationships with humans [IUCN, 2024]. Other issues such as the virus outbreaks, disease transfers from domestic cats (Felis catus), and lack of genetic diversity are issues being worked on by geneticists [IUCN, 2024]
Therefore, the data is implied to be a part of the conservation efforts undertaken by conservationists to protect the Iberian lynx. One question could be “How have the populations of Iberian Lynx (Lynx pardinus) changed between the 19th and 20th centuries?”, alternatively this could be a study on the European rabbit conservation and showing how the lynx populations have been impacted by the conservation efforts undertaken to protect them.
Our questions are:
How have the populations of Iberian Lynx (Lynx pardinus) changed between the 19th and 20th centuries?
Are different environmental factors between site A and site B impacting on the conservation of the Iberian Lynx (Lynx pardinus)?
Proposed Analysis:
The dataset contains the following columns:
id: Identifier for each entry.
lynx: Numerical values representing lynx population/count data.
century: Categorical, representing two unique values: 19 and 20.
Since we have a categorical predictor variable (“century”) with two groups, and a quantitative outcome variable (“lynx”), the appropriate statistical test would be a T-test to compare the means of lynx populations between the 19th and 20th centuries.
The following r code chunk installs and loads the various packages used to analysing the lynx data set.
library(kableExtra) # loads the kableExtra package
library(tidyverse) # loads the tidyverse package for ggplot functions
library("magrittr") # loads the magrittr package, which provides functions that helps make code more readable
library(knitr) # loads the knitr package, for dynamic report generationThe lynx data set has been altered to make it easier to work with for subsequent analysis (the letter preceeding the numbers for each study site ID has been removed). The altered lynx data set is loaded and a table is created.
library(readr)
Lynx_Data_set_altered <- read_csv("C:/Users/tamsi/Downloads/Lynx Data set_altered.csv")
View(Lynx_Data_set_altered)data("lynx_Data_set_altered") # loads the altered lynx data set
as_tibble(Lynx_Data_set_altered) # creates a tibble, which basically is a dataframe# A tibble: 70 × 3
id lynx century
<dbl> <dbl> <dbl>
1 1 3311 19
2 2 6721 19
3 3 4254 19
4 4 687 19
5 5 255 19
6 6 473 19
7 7 358 19
8 8 784 19
9 9 1594 19
10 10 1676 19
# ℹ 60 more rowsThe following r code chunk facilitates the calculation of the sum of the number of lynxes grouped by study site and century of capture. All missing values recorded as ‘NA’ are removed. The resulting output adopts a wider format from a longer one. Finally, a new column named ‘sum_lynx’ is created with the sum of row values.
lynx_summary <- Lynx_Data_set_altered %>% # altered lynx data set is assigned to lynx_summary
group_by(id, century) %>% # data set is grouped by ID and century
summarize(total_lynx = sum(lynx, na.rm = TRUE), .groups = 'drop') %>% # sum of number of lynxes is computed as total_lynx, with missing data values coded as 'NA' removed and result ungrouped
spread(century, total_lynx, fill = 0) %>% # spreads the key-value pair across multiple columns into a wider format
mutate(sum_lynx = rowSums(select(., -id), na.rm = TRUE)) # sum of row values calculated and assigned a new columnThe following r code chunk creates a table with the sum of each row for both the 19th and 20th centuries.
lynx_summary |> # specifies data to be used for subsequent operations
kable() %>% # converts dataframes and matrices into well-formatted tables
kable_classic_2(full_width = F) # manipulates table styles, with full width set to false| id | 19 | 20 | sum_lynx |
|---|---|---|---|
| 1 | 3311 | 387 | 3698 |
| 2 | 6721 | 758 | 7479 |
| 3 | 4254 | 1307 | 5561 |
| 4 | 687 | 3465 | 4152 |
| 5 | 255 | 6991 | 7246 |
| 6 | 473 | 6313 | 6786 |
| 7 | 358 | 3794 | 4152 |
| 8 | 784 | 1836 | 2620 |
| 9 | 1594 | 345 | 1939 |
| 10 | 1676 | 382 | 2058 |
| 11 | 2251 | 808 | 3059 |
| 12 | 1426 | 1388 | 2814 |
| 13 | 756 | 2713 | 3469 |
| 14 | 299 | 3800 | 4099 |
| 15 | 201 | 3091 | 3292 |
| 16 | 229 | 2985 | 3214 |
| 17 | 469 | 3790 | 4259 |
| 18 | 736 | 674 | 1410 |
| 19 | 2042 | 81 | 2123 |
| 20 | 2811 | 80 | 2891 |
| 21 | 4431 | 108 | 4539 |
| 22 | 2511 | 229 | 2740 |
| 23 | 389 | 399 | 788 |
| 24 | 73 | 1132 | 1205 |
| 25 | 39 | 2432 | 2471 |
| 26 | 49 | 3574 | 3623 |
| 27 | 59 | 2935 | 2994 |
| 28 | 188 | 1537 | 1725 |
| 29 | 377 | 529 | 906 |
| 30 | 1292 | 485 | 1777 |
| 31 | 4031 | 662 | 4693 |
| 32 | 3495 | 1000 | 4495 |
| 33 | 587 | 1590 | 2177 |
| 34 | 105 | 2657 | 2762 |
| 35 | 153 | 3396 | 3549 |
The following r code chunk facilitates the calculation of the sum of the number of lynxes grouped by study site . All missing values recorded as ‘NA’ are removed.
lynx_summary <- Lynx_Data_set_altered %>% # altered lynx data set assigned to 'lynx_summary'
group_by(id) %>% # data grouped by id
summarize(total_lynx = sum(lynx, na.rm = TRUE), .groups = 'drop') # sum of number of lynxes calculated, with missing values coded as 'NA' removed and result ungroupedThe following r code chunk creates a table with the sum of each row.
lynx_summary |> # specifies data for subsequent operations
kable() %>% # converts dataframes and matrices into well-formatted tables
kable_classic_2(full_width = F) # manipulates table styles, with full width set to false| id | total_lynx |
|---|---|
| 1 | 3698 |
| 2 | 7479 |
| 3 | 5561 |
| 4 | 4152 |
| 5 | 7246 |
| 6 | 6786 |
| 7 | 4152 |
| 8 | 2620 |
| 9 | 1939 |
| 10 | 2058 |
| 11 | 3059 |
| 12 | 2814 |
| 13 | 3469 |
| 14 | 4099 |
| 15 | 3292 |
| 16 | 3214 |
| 17 | 4259 |
| 18 | 1410 |
| 19 | 2123 |
| 20 | 2891 |
| 21 | 4539 |
| 22 | 2740 |
| 23 | 788 |
| 24 | 1205 |
| 25 | 2471 |
| 26 | 3623 |
| 27 | 2994 |
| 28 | 1725 |
| 29 | 906 |
| 30 | 1777 |
| 31 | 4693 |
| 32 | 4495 |
| 33 | 2177 |
| 34 | 2762 |
| 35 | 3549 |
The following r code chunk facilitates the calculation of the sum of the number of lynxes grouped by study site . All missing values recorded as ‘NA’ are removed.
lynx_summary <- Lynx_Data_set_altered %>% # altered lynx data set assigned to 'lynx_summary'
group_by(id) %>% # data grouped by id
summarize(total_lynx = sum(lynx, na.rm = TRUE), .groups = 'drop') # sum of number of lynxes calculated, with missing values coded as 'NA' removed and result ungroupedThe following r code chunk creates a table with the sum of each row for the 19th century.
lynx_summary |> # specifies data for subsequent operations
kable() %>% # converts dataframes and matrices into well-formatted tables
kable_classic_2(full_width = F) # manipulates table styles, with full width set to false| id | total_lynx |
|---|---|
| 1 | 3698 |
| 2 | 7479 |
| 3 | 5561 |
| 4 | 4152 |
| 5 | 7246 |
| 6 | 6786 |
| 7 | 4152 |
| 8 | 2620 |
| 9 | 1939 |
| 10 | 2058 |
| 11 | 3059 |
| 12 | 2814 |
| 13 | 3469 |
| 14 | 4099 |
| 15 | 3292 |
| 16 | 3214 |
| 17 | 4259 |
| 18 | 1410 |
| 19 | 2123 |
| 20 | 2891 |
| 21 | 4539 |
| 22 | 2740 |
| 23 | 788 |
| 24 | 1205 |
| 25 | 2471 |
| 26 | 3623 |
| 27 | 2994 |
| 28 | 1725 |
| 29 | 906 |
| 30 | 1777 |
| 31 | 4693 |
| 32 | 4495 |
| 33 | 2177 |
| 34 | 2762 |
| 35 | 3549 |
The following r code chunk facilitates the calculation of the mean of the number of lynxes grouped by century. All missing values recorded as ‘NA’ are removed.
lynx_mean_summary <- Lynx_Data_set_altered %>% # altered lynx data set assigned to 'lynx_mean_summary'
group_by(century) %>% # data grouped by century
summarize(mean_lynx = mean(lynx, na.rm = TRUE), .groups = 'drop') # mean of number of lynxes calculated, with missing values coded as 'NA' removed and result ungroupedThe following r code chunk creates a table with the mean of lynx numbers for each century.
lynx_mean_summary %>% # specifies data for subsequent operations
kable() %>% # converts dataframes and matrices into well-formatted tables
kable_classic_2(full_width = F) # manipulates table styles, with full width set to false| century | mean_lynx |
|---|---|
| 19 | 1403.200 |
| 20 | 1932.943 |
The following r code chunk facilitates the calculation of the total number of lynxes grouped by century. All missing values recorded as ‘NA’ are removed.
lynx_by_century <- Lynx_Data_set_altered %>% # specifies data for subsequent operations
group_by(century) %>% # data grouped by century
summarize(total_lynx = sum(lynx, na.rm = TRUE), .groups = 'drop') # total number of lynxes calculated, with missing values coded as 'NA' removed and result ungroupedThe following chunk of r code helps generate a bar graph of the total number of lynxes captured in each century
ggplot(lynx_by_century, aes(x = century, y = total_lynx)) + # ggplot functions are used to generate graphics, with data set specified, x- and y-variables assigned accordingly
geom_bar(stat = "identity", fill = "purple") + # generates a bar graph, with sum of values for variable used instead of counts, fill colour manually set to purple
labs(title = "Total Lynx Counts by Century", # title of graph specified
x = "Century", # label of a-axis assigned accordingly
y = "Total Lynx Count") + # label of y-axis assigned accordingly
theme_dark() # theme set to darkThe following r code chunk facilitates the calculation of the total number of lynxes grouped by study site id. All missing values recorded as ‘NA’ are removed.
lynx_by_id <- Lynx_Data_set_altered %>% # specifies data for subsequent operations
group_by(id) %>% # data grouped by id
summarize(total_lynx = sum(lynx, na.rm = TRUE), .groups = 'drop') # total number of lynxes calculated, with missing values coded as 'NA' removed and result ungroupedggplot(lynx_by_id, aes(x = reorder(id, total_lynx), y = total_lynx)) + # ggplot functions are used to generate graphics, with data set specified, x- and y-variables assigned accordingly and values reordered according to specified order
geom_bar(stat = "identity", fill = "purple") + # generates a bar graph, with sum of values for variable used instead of counts, fill colour manually set to purple
labs(title = "Total Lynx Counts by ID", # title of graph specified
x = "ID", # label of x-axis assigned accordingly
y = "Total Lynx Count") + # label of y-axis assigned accordingly
theme_dark() + # theme set to dark
coord_flip() # Flips the axes for better readability 
Fosse; et al. 2024. The lynxes (Lynx pardinus/spelaeus, Lynx lynx) from the Middle Pleistocene to the Holocene in southern France: a paleontological and taphonomical overview. [online]. HAL Open Science: Fosse; et al. Available at: The lynxes (Lynx pardinus/spelaeus, Lynx lynx) from the Middle Pleistocene to the Holocene in southern France: a paleontological and taphonomical overview. [Date accessed: 28th October 2024].
IUCN Red List, 2019. European Rabbit [online]. IUCN Red List. Available at: Oryctolagus cuniculus (European Rabbit) [Date accessed: 27th October 2024].
IUCN Red List, 2023. Iberian Lynx [online]. IUCN Red List. Available at: Lynx pardinus (Iberian Lynx) [Date accessed: 27th October 2024].
IUCN, 2024. Iberian lynx rebounding thanks to conservation action - IUCN Red List [online]. Press Released: IUCN. Available at: Iberian lynx rebounding thanks to conservation action - IUCN Red List - Press release | IUCN [Date accessed: 28th October 2024].