Assignment 10B: Nobel Prize Data Analysis

Approach

Author

Patricio Romero

Published

November 19, 2026

1 Project Overview

The goal of this project is to explore Nobel Prize data using R and JSON.

The analysis will examine how Nobel Prizes have been awarded across different categories and time periods. It will also explore the geographic representation of Nobel Prize laureates.

The project will use data from the official Nobel Prize API. The data will be imported, cleaned, and transformed into a structured format for analysis and visualization.

The results will help identify patterns and changes in Nobel Prize awards over time.

2 Research Questions

This project will address the following four research questions:

  1. Which Nobel Prize categories have received the most awards over time?

  2. How has the number of Nobel Prize laureates changed across decades?

  3. Which countries are most frequently represented among Nobel Prize laureates?

  4. How do Nobel Prize patterns differ across categories and time periods?

These questions will help us explore historical trends, geographic representation, and differences between Nobel Prize categories.

3 Data Source

The data comes from the official Nobel Prize API in JSON format. For this Approach, I imported an initial sample of 100 award records. The full historical dataset and laureate birth countries will be examined in the Code Base.

Source: https://www.nobelprize.org/about/developer-zone-2/

3.1 Data Import

I used R and jsonlite to retrieve the award records. The tables below summarize the data without displaying long nested JSON objects.

Show code
api_url <- "https://api.nobelprize.org/2.1/nobelPrizes?limit=100"
nobel_json <- jsonlite::fromJSON(api_url, flatten = TRUE)
nobel_prizes <- nobel_json$nobelPrizes
stopifnot(is.data.frame(nobel_prizes), nrow(nobel_prizes) > 0)

# Keep original JSON records and create readable analysis variables.
nobel_clean <- nobel_prizes |>
  dplyr::transmute(
    `Award Year` = as.integer(awardYear),
    Category = category.en,
    `Award Date` = dateAwarded,
    `Prize Amount (SEK)` = as.numeric(prizeAmount),
    `Adjusted Prize Amount (SEK)` = as.numeric(prizeAmountAdjusted)
  )

stopifnot(nrow(nobel_clean) == nrow(nobel_prizes))

3.2 Dataset Overview

Show code
overview <- data.frame(
  Description = c("Award records", "Original API variables", "Selected analysis variables", "Data format", "Data source", "API version", "Sample scope"),
  Value = c(nrow(nobel_clean), ncol(nobel_prizes), ncol(nobel_clean), "JSON", "NobelPrize.org", "2.1", "First 100 award records")
)
format_table(overview, "Table 1. Dataset Overview")
Table 1. Dataset Overview
Description Value
Award records 100
Original API variables 13
Selected analysis variables 5
Data format JSON
Data source NobelPrize.org
API version 2.1
Sample scope First 100 award records

3.3 Variable Description

Show code
variable_table <- data.frame(
  Variable = names(nobel_clean),
  Type = vapply(nobel_clean, function(x) paste(class(x), collapse = ", "), character(1)),
  Description = c(
    "Year when the Nobel Prize was awarded",
    "Nobel Prize category in English",
    "Date when the prize was awarded",
    "Original prize amount in Swedish kronor",
    "Inflation-adjusted prize amount in Swedish kronor"
  ),
  Purpose = c(
    "Analyze historical trends",
    "Compare award categories",
    "Identify award dates",
    "Examine prize amounts",
    "Compare adjusted prize amounts"
  )
)
format_table(variable_table, "Table 2. Variable Description")
Table 2. Variable Description
Variable Type Description Purpose
Award Year integer Year when the Nobel Prize was awarded Analyze historical trends
Category character Nobel Prize category in English Compare award categories
Award Date character Date when the prize was awarded Identify award dates
Prize Amount (SEK) numeric Original prize amount in Swedish kronor Examine prize amounts
Adjusted Prize Amount (SEK) numeric Inflation-adjusted prize amount in Swedish kronor Compare adjusted prize amounts

3.4 Data Preview

The preview includes only readable award-level fields. Nested laureate information is not printed in this table.

Show code
preview <- head(nobel_clean[, c("Award Year", "Category", "Award Date", "Prize Amount (SEK)")], 6)
preview[["Prize Amount (SEK)"]] <- format(preview[["Prize Amount (SEK)"]], big.mark = ",", scientific = FALSE, trim = TRUE)
format_table(preview, "Table 3. Nobel Prize Data Preview")
Table 3. Nobel Prize Data Preview
Award Year Category Award Date Prize Amount (SEK)
1901 Chemistry 1901-11-12 150,782
1901 Literature 1901-11-14 150,782
1901 Peace 1901-12-10 150,782
1901 Physics 1901-11-12 150,782
1901 Physiology or Medicine 1901-10-30 150,782
1902 Chemistry 1902-11-11 141,847

4 Data Validation

Before the main analysis, I checked missing values and award counts by category in the imported sample. These results describe only the sample, not all historical awards.

4.1 Missing Values

Show code
missing <- vapply(nobel_clean, function(x) sum(is.na(x) | trimws(as.character(x)) == ""), integer(1))
missing_table <- data.frame(
  Variable = names(nobel_clean),
  `Missing Values` = as.integer(missing),
  `Percentage (%)` = round(100 * missing / nrow(nobel_clean), 2),
  check.names = FALSE
)
format_table(missing_table, "Table 4. Missing Values")
Table 4. Missing Values
Variable Missing Values Percentage (%)
Award Year 0 0
Category 0 0
Award Date 10 10
Prize Amount (SEK) 0 0
Adjusted Prize Amount (SEK) 0 0

4.2 Awards by Category

Show code
awards_table <- nobel_clean |>
  dplyr::count(Category, name = "Awards") |>
  dplyr::mutate(`Percentage (%)` = round(100 * Awards / sum(Awards), 2)) |>
  dplyr::arrange(dplyr::desc(Awards))
format_table(awards_table, "Table 5. Awards by Category")
Table 5. Awards by Category
Category Awards Percentage (%)
Chemistry 20 20
Literature 20 20
Peace 20 20
Physics 20 20
Physiology or Medicine 20 20

5 Original Data and Proposed Extension

The original API includes award-level information and nested laureate records. The Code Base will retrieve the complete available award data, organize laureate records separately, and use the laureate API to examine birth countries. This will help avoid confusing award counts with laureate counts.

6 Methodology

The analysis will use R to import and transform JSON data. I will validate missing values and duplicate records, group award years into decades, and create charts to answer the four research questions.

The planned visualizations are a category bar chart, a decade trend line, a top-10 birth-country bar chart, and a category-by-decade heatmap. Individual laureates and organizations will be handled separately for the geographic analysis.

6.1 Analytical Tools

Show code
tools_table <- data.frame(
  Package = c("jsonlite", "dplyr", "tidyr", "ggplot2", "knitr", "kableExtra"),
  Purpose = c("Import JSON", "Summarize data", "Transform nested data", "Create charts", "Create tables", "Style HTML tables")
)
format_table(tools_table, "Table 6. Analytical Tools")
Table 6. Analytical Tools
Package Purpose
jsonlite Import JSON
dplyr Summarize data
tidyr Transform nested data
ggplot2 Create charts
knitr Create tables
kableExtra Style HTML tables

7 Expected Results

This project is expected to identify patterns in Nobel Prize awards across categories, decades, and countries.

The analysis will help us understand:

  1. Which Nobel Prize categories have the highest number of awards.
  2. How the number of laureate award records has changed over time.
  3. Which birth countries are most frequently represented among individual laureates.
  4. How award patterns differ between categories and decades.

The results will be presented using summary tables and visualizations.

8 Limitations

This analysis has several limitations:

  • Some laureates may have missing birth country information.
  • Organizations do not have birth countries and will be excluded from geographic comparisons.
  • Historical country names and borders may have changed over time.
  • Some Nobel Prizes have multiple laureates, so award counts and laureate counts are different.
  • The dataset may not include every variable needed for additional comparisons.

These limitations will be considered when interpreting the results.

9 References

NobelPrize.org. (n.d.). Developer zone: Nobel Prize API.
https://www.nobelprize.org/about/developer-zone-2/

Posit. (n.d.). Quarto documentation.
https://quarto.org/docs/

Wickham, H., & Grolemund, G. (2017). R for Data Science. O’Reilly Media.
https://r4ds.hadley.nz/

10 Appendix: AI Assistance

ChatGPT was used to help understand the assignment requirements, organize the planned approach, improve English writing, and provide guidance for importing and processing JSON data in R.

I selected the Nobel Prize topic for this project and will run, review, and verify the data transformations, analysis, visualizations, and final conclusions during the Code Base stage.