Cost of food in the United States increased 3.10 percent in September of 2025 over the same month in the previous year. This dataset provides the latest reported value for - United States Food Inflation - plus previous releases, historical high and low, short-term forecast and long-term prediction, economic calendar, survey consensus and news.

For a quick summary of the case study, please click "US Economy Powerpoint" and download the Powerpoint.

This dataset was inspired by rising prices for essential goods, the abnormally high inflation rate in March of 7.9 percent of this year, and the 30 trillion-dollar debt that we have. I was extremely curious to see how sustainable this is for the average American and if wages are increasing at the same rate to help combat this inflation. This is not politically driven in the slightest nor was this made to put the blame on Americans. This dataset was inspired by rising prices for essential goods and the abnormally high inflation rate in March of 7.9 percent of this year. I was extremely curious to see how sustainable this is for the average American and if wages are increasing at the same rate to help combat this inflation. This is not politically driven in the slightest nor was this made to put the blame on Americans. All of the datasets were obtained from third party sources websites such as https://dqydj.com/household-income-by-year/ and https://www.usinflationcalculator.com/inflation/historical-inflation-rates/ and only excluding https://fred.stlouisfed.org/series/ASPUS, which is first-party data.

This dataset was inspired by rising prices for essential goods and the abnormally high inflation rate in March of 7.9 percent of this year. I was extremely curious to see how sustainable this is for the average American and if wages are increasing at the same rate to help combat this inflation. This is not politically driven in the slightest nor was this made to put the blame on Americans. This dataset was inspired by rising prices for essential goods and the abnormally high inflation rate in March of 7.9 percent of this year. I was extremely curious to see how sustainable this is for the average American and if wages are increasing at the same rate to help combat this inflation. This is not politically driven in the slightest nor was this made to put the blame on Americans. All of the datasets were obtained from third party sources websites such as https://dqydj.com/household-income-by-year/ and https://www.usinflationcalculator.com/inflation/historical-inflation-rates/ and only excluding https://fred.stlouisfed.org/series/ASPUS, which is first-party data.

I labeled all of the datasets to be self-explanatory based off of the title of the datasets. The US Economy Notebook has most of the code that I used as well as the four of the six phases of data analysis. The last two phases are in the US Economy Powerpoint. The "US Historical Inflation Rates" dataset could have also been labeled "The Inflation Of The US Dollar Month By Month". Lastly, the Average Sales of Houses in Jan is just a filtered version of "Average Sales of Houses in the US" dataset.

Consumer Price Index CPI in the United States increased to 324.80 points in September from 323.98 points in August of 2025. This dataset provides the latest reported value for - United States Consumer Price Index (CPI) - plus previous releases, historical high and low, short-term forecast and long-term prediction, economic calendar, survey consensus and news.

This dataset provides estimated average retail prices for more than 150 fruits and vegetables by year.

The source of the header image is Scott Webb on Unsplash.

OVERVIEW

The United States Department of Agriculture's Economic Research Service (ERS) estimated average prices for over 150 commonly consumed fruits and vegetables, using 2013, 2016, 2020, and 2022 retail sales data from Circana. Circana obtained this data from a selection of retail establishments across the U.S., including grocery stores, supermarkets, convenience stores, drug stores, and liquor stores.

See ers.usda.gov for additional documentation.

LIMITATIONS & SOURCES OF ERROR

• Coding inconsistencies and market dynamics make this dataset unsuitable for inferring price trends over time.
• The sample of U.S. retail establishments from which Circana collected data may not be representative of the entire population.
• Estimates of a product’s inedible portion and weight change from cooking are based on samples of products. Actual amounts will differ for specific products bought by a household (e.g., the actual size of the inedible core of an apple varies between fruits).

Inflation Rate in the United States increased to 3 percent in September from 2.90 percent in August of 2025. This dataset provides - United States Inflation Rate - actual values, historical data, forecast, chart, statistics, economic calendar and news.

Context

The US Bureau of Labor Statistics monitors and collects day-to-day information about the market price of raw inputs and finished goods, and publishes regularized statistical assays of this data. The Consumer Price Index and the Producer Price Index are its two most famous products. The former tracks the aggregate dollar price of consumer goods in the United States (things like onions, shovels, and smartphones); the latter (this dataset) tracks the cost of raw inputs to the industries producing those goods (things like raw steel, bulk leather, and processed chemicals).

The US federal government uses this dataset to track inflation. While in the short term the raw dollar value of producer inputs may be volatile, in the long term it will always go up due to inflation --- the slowly decreasing buying power of the US dollar.

Content

This dataset consists of a packet of files, each one tracking regularized cost of inputs for certain industries. The data is tracked-month to month with an index out of 100.

Acknowledgements

This data is published online by the US Bureau of Labor Statistics.

Inspiration

• How does the Producer Price Index compare against the Consumer Price Index?
• What have the largest spikes in input costs been, historically? Can you determine why they occurred?
• What is the overall price index trend amongst US producers?

Core consumer prices in the United States increased 3 percent in September of 2025 over the same month in the previous year. This dataset provides - United States Core Inflation Rate - actual values, historical data, forecast, chart, statistics, economic calendar and news.

This dataset is comprised of data submitted to HCAI by prescription drug manufacturers for wholesale acquisition cost (WAC) increases that exceed the statutorily-mandated WAC increase threshold of an increase of more than 16% above the WAC of the drug product on December 31 of the calendar year three years prior to the current calendar year. This threshold applies to prescription drug products with a WAC greater than $40 for a course of therapy. Required WAC increase reports are to be submitted to HCAI within a month after the end of the quarter in which the WAC increase went into effect. Please see the statute and regulations for additional information regarding reporting thresholds and report due dates.

Key data elements in this dataset include the National Drug Code (NDC) maintained by the FDA, narrative descriptions of the reasons for the increase in WAC, and the five-year history of WAC increases for the NDC. A WAC Increase Report consists of 27 data elements that have been divided into two separate Excel data sets: Prescription Drug WAC Increase and Prescription Drug WAC Increase – 5 Year History. The datasets include manufacturer WAC Increase Reports received since January 1, 2019. The Prescription Drugs WAC Increase dataset consists of the information submitted by prescription drug manufacturers that pertains to the current WAC increase of a given report, including the amount of the current increase, the WAC after increase, and the effective date of the increase. The Prescription Drugs WAC Increase – 5 Year History dataset consists of the information submitted by prescription drug manufacturers for the data elements that comprise the 5-year history of WAC increases of a given report, including the amount of each increase and their effective dates.

There are two types of WAC Increase datasets below: Monthly and Annual. The Monthly datasets include the data in completed reports submitted by manufacturers for calendar year 2025, as of November 7, 2025. The Annual datasets include data in completed reports submitted by manufacturers for the specified year. The datasets may include reports that do not meet the specified minimum thresholds for reporting.

The Quick Guide explaining how to link the information in each data set to form complete reports is here: https://hcai.ca.gov/wp-content/uploads/2024/03/QuickGuide_LinkingTheDatasets.pdf

The program regulations are available here: https://hcai.ca.gov/wp-content/uploads/2024/03/CTRx-Regulations-Text.pdf

The data format and file specifications are available here: https://hcai.ca.gov/wp-content/uploads/2024/03/Format-and-File-Specifications-version-2.0-ada.pdf

DATA NOTES: Due to recent changes in Excel, it is not recommended that you save these files to .csv format. If you do, when importing back into Excel the leading zeros in the NDC number column will be dropped. If you need to save it into a different format other than .xlsx it must be .txt

Submitted reports that are still under review by HCAI are not included in these files.

DATA UPDATES: Drug manufacturers may submit WAC Increase reports to HCAI for price increases from previous quarters. CTRx staff update the posted datasets monthly for current year data and as needed for previous years. Please check the 'Data last updated' date on each dataset page to ensure you are viewing the most current data.

Due to regulatory changes that went into effect April 1, 2024, reports submitted prior to April 1, 2024, will include the data field "Unit Sales Volume in US" and reports submitted on or after April 1, 2024, will instead include "Total Volume of Gross Sales in US Dollars".

This dataset includes various economic indicators such as stock market performance, inflation rates, GDP, interest rates, employment data, and housing index, all of which are crucial for understanding the state of the economy. By analysing this dataset, one can gain insights into the causes and effects of past recessions in the US, which can inform investment decisions and policy-making.

There are 20 columns and 343 rows spanning 1990-04 to 2022-10

The columns are:

1. Price: Price column refers to the S&P 500 lot price over the years. The S&P 500 is a stock market index that measures the performance of 500 large companies listed on stock exchanges in the United States. This variable represents the value of the S&P 500 index from 1980 to present. Industrial Production: This variable measures the output of industrial establishments in the manufacturing, mining, and utilities sectors. It reflects the overall health of the manufacturing industry, which is a key component of the US economy.

2. INDPRO: Industrial production measures the output of the manufacturing, mining, and utility sectors of the economy. It provides insights into the overall health of the economy, as a decline in industrial production can indicate a slowdown in economic activity. This data can be used by policymakers and investors to assess the state of the economy and make informed decisions.

3. CPI: CPI stands for Consumer Price Index, which measures the change in the prices of a basket of goods and services that consumers purchase. CPI inflation represents the rate at which the prices of goods and services in the economy are increasing.

4. Treasure Bill rate (3 month to 30 Years): Treasury bills (T-bills) are short-term debt securities issued by the US government. This variable represents the interest rates on T-bills with maturities ranging from 3 months to 30 years. It reflects the cost of borrowing money for the government and provides an indication of the overall level of interest rates in the economy.

5. GDP: GDP stands for Gross Domestic Product, which is the value of all goods and services produced in a country. This dataset is taking into account only the Nominal GDP values. Nominal GDP represents the total value of goods and services produced in the US economy without accounting for inflation.

6. Rate: The Federal Funds Rate is the interest rate at which depository institutions lend reserve balances to other depository institutions overnight. It is set by the Federal Reserve and is used as a tool to regulate the money supply in the economy.

7. BBK_Index: The BBKI are maintained and produced by the Indiana Business Research Center at the Kelley School of Business at Indiana University. The BBK Coincident and Leading Indexes and Monthly GDP Growth for the U.S. are constructed from a collapsed dynamic factor analysis of a panel of 490 monthly measures of real economic activity and quarterly real GDP growth. The BBK Leading Index is the leading subcomponent of the cycle measured in standard deviation units from trend real GDP growth.

8. Housing Index: This variable represents the value of the housing market in the US. It is calculated based on the prices of homes sold in the market and provides an indication of the overall health of the housing market.

9. Recession binary column: This variable is a binary indicator that takes a value of 1 when the US economy is in a recession and 0 otherwise. It is based on the official business cycle dates provided by the National Bureau of Economic Research.

U.S. Economic and Financial Dataset

Dataset Description

This dataset combines historical U.S. economic and financial indicators, spanning the last 50 years, to facilitate time series analysis and uncover patterns in macroeconomic trends. It is designed for exploring relationships between interest rates, inflation, economic growth, stock market performance, and industrial production.

Key Features

• Frequency: Monthly
• Time Period: Last 50 years from Nov-24
• Sources:
  • Federal Reserve Economic Data (FRED)
  • Yahoo Finance

Dataset Feature Description

1. Interest Rate (Interest_Rate):

   • The effective federal funds rate, representing the interest rate at which depository institutions trade federal funds overnight.

2. Inflation (Inflation):

   • The Consumer Price Index for All Urban Consumers, an indicator of inflation trends.

3. GDP (GDP):

   • Real GDP measures the inflation-adjusted value of goods and services produced in the U.S.

4. Unemployment Rate (Unemployment):

   • The percentage of the labor force that is unemployed and actively seeking work.

5. Stock Market Performance (S&P500):

   • Monthly average of the adjusted close price, representing stock market trends.

6. Industrial Production (Ind_Prod):

   • A measure of real output in the industrial sector, including manufacturing, mining, and utilities.

Dataset Statistics

1. Total Entries: 599
2. Columns: 6
3. Memory usage: 37.54 kB
4. Data types: float64

Feature Overview

• Columns:
  • Interest_Rate: Monthly Federal Funds Rate (%)
  • Inflation: CPI (All Urban Consumers, Index)
  • GDP: Real GDP (Billions of Chained 2012 Dollars)
  • Unemployment: Unemployment Rate (%)
  • Ind_Prod: Industrial Production Index (2017=100)
  • S&P500: Monthly Average of S&P 500 Adjusted Close Prices

Executive Summary

This project explores the interconnected dynamics of key macroeconomic indicators and financial market trends over the past 50 years, leveraging data from the Federal Reserve Economic Data (FRED) and Yahoo Finance. The dataset integrates critical variables such as the Federal Funds Rate, Inflation (CPI), Real GDP, Unemployment Rate, Industrial Production, and the S&P 500 Index, providing a holistic view of the U.S. economy and financial markets.

The analysis focuses on uncovering relationships between these variables through time-series visualization, correlation analysis, and trend decomposition. Key findings are included in the Insights section. This project serves as a robust resource for understanding long-term economic trends, policy impacts, and market behavior. It is particularly valuable for students, researchers, policymakers, and financial analysts seeking to connect macroeconomic theory with real-world data.

Potential Use Cases

• Economic Analysis: Examine relationships between interest rates, inflation, GDP, and unemployment.
• Stock Market Prediction: Study how macroeconomic indicators influence stock market trends.
• Time Series Modeling: Perform ARIMA, VAR, or other models to forecast economic trends.
• Cyclic Pattern Analysis: Identify how economic shocks and recoveries impact key indicators.

Snap of Power Analysis

https://github.com/user-attachments/assets/1b40e0ca-7d2e-4fbc-8cfd-df3f09e4fdb8">

To ensure sufficient power, the dataset covers last 50 years of monthly data i.e., around 600 entries.

Key Insights derived through EDA, time-series visualization, correlation analysis, and trend decomposition

• Interest Rate and Inflation Dynamics: The interest Rate and inflation exhibit an inverse relationship, especially during periods of aggressive monetary tightening by the Federal Reserve.
• Economic Growth and Market Performance: GDP growth and the S&P 500 Index show a positive correlation, reflecting how market performance often aligns with overall economic health.
• Labor Market and Industrial Output: Unemployment and industrial production demonstrate a strong inverse relationship. Higher industrial output is typically associated with lower unemployment
• Market Behavior During Economic Shocks: The S&P 500 experienced sharp declines during significant crises, such as the 2008 financial crash and the COVID-19 pandemic in 2020. These events also triggered increased unemployment and contractions in GDP, highlighting the interplay between markets and the broader economy.
• Correlation Highlights: S&P 500 and GDP have a strong positive correlation. Interest rates negatively correlate with GDP and inflation, reflecting monetary policy impacts. Unemployment is negatively correlated with industrial production but positively correlated with interest rates.

Link to GitHub Repo

https:/...

The USDA, Economic Research Service (ERS) Food Price Outlook (FPO) provides data on food prices and forecasts annual food price changes up to 18 months in the future. On a monthly basis, ERS forecasts the annual percentage change in food prices for the current year and, beginning in July each year, for the following year. These forecasts are primarily based on the U.S. Department of Labor, Bureau of Labor Statistics’ (BLS) Consumer Price Index (CPI) and Producer Price Index (PPI) data.

This dataset contains the following records from the Food Price Outlook: 1. Changes in Consumer Price Indexes, 2020 through 2023 2. Annual percent changes in selected Consumer Price Indexes, 1974 through 2021

The data examines the historical change in the Consumer Price Index (CPI) for food in the United States. The CPI measures the average change over time in the prices paid by urban consumers for a representative market basket of consumer goods and services. This includes different categories of food such as meat and dairy products, fruits and vegetables, as well as the overall cost of Food at home compared to Food away from home. The CPI for food measures the changes in the retail prices of food items only.

For more information on this dataset visit: ers.usda.gov

Graph and download economic data for Inflation, consumer prices for the United States (FPCPITOTLZGUSA) from 1960 to 2024 about consumer, CPI, inflation, price index, indexes, price, and USA.

US Electricity Prices and Sales by State, Sector, and Year

https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F8734253%2Fdba0dac3571f37e79f2891a6ffd80d5c%2Fus%20electric%20flag.png?generation=1712518711362350&alt=media" alt=""> This comprehensive dataset offers a detailed look at the United States electricity market, providing valuable insights into prices, sales, and revenue across various states, sectors, and years. With data spanning from 2001 onwards to 2024, this dataset is a powerful tool for analyzing the complex dynamics of the US electricity market and understanding how it has evolved over time.

The dataset includes eight key variables: | Column Name | Description | |-------|-------| | year | The year of the observation | | month | The month of the observation | | stateDescription | The name of the state | | sectorName | The sector of the electricity market (residential, commercial, industrial, other, or all sectors) | | customers | The number of customers (missing for some observations) | | price | The average price of electricity per kilowatt-hour (kWh) in cents | | revenue | The total revenue generated from electricity sales in millions of dollars | | sales | The total electricity sales in millions of kilowatt-hours (kWh) |

By providing such granular data, this dataset enables users to conduct in-depth analyses of electricity market trends, comparing prices and consumption patterns across different states and sectors, and examining the impact of seasonality on demand and prices.

One of the primary applications of this dataset is in forecasting future electricity prices and sales based on historical trends. By leveraging the extensive time series data available, researchers and analysts can develop sophisticated models to predict how prices and demand may change in the coming years, taking into account factors such as economic growth, population shifts, and policy changes. This predictive power is invaluable for policymakers, energy companies, and investors looking to make informed decisions in the rapidly evolving electricity market.

Another key use case for this dataset is in investigating the complex relationships between electricity prices, sales volumes, and revenue. By combining the price, sales, and revenue data, users can explore how changes in prices impact consumer behavior and utility company bottom lines. This analysis can shed light on important questions such as the price elasticity of electricity demand, the effectiveness of energy efficiency programs, and the potential impact of new technologies like renewable energy and energy storage on the market.

Beyond its immediate applications in the energy sector, this dataset also has broader implications for understanding the US economy and society as a whole. Electricity is a critical input for businesses and households across the country, and changes in electricity prices and consumption can have far-reaching effects on economic growth, competitiveness, and quality of life. By providing such a rich and detailed portrait of the US electricity market, this dataset opens up new avenues for research and insights that can inform public policy, business strategy, and academic inquiry.

I hope you all enjoy using this dataset and find it useful! 🤗

This dataset consolidates data from 1960 to 2012, offering a detailed perspective on fertilizer consumption in the United States. It covers plant nutrients, major selected products, mixed fertilizers, secondary nutrients, and micronutrients. Explore the share of crop areas receiving fertilizer and fertilizer use per acre for key crops like corn, cotton, soybeans, and wheat in major producing states. The dataset also includes fertilizer farm prices and indices of wholesale fertilizer prices, providing a comprehensive resource for researchers, policymakers, and stakeholders interested in understanding fertilizer trends, crop dynamics, and pricing indices in the U.S. agricultural landscape. Fertilizer price data are available up to 2013.

Graph and download economic data for Median Sales Price of Houses Sold for the United States (MSPUS) from Q1 1963 to Q2 2025 about sales, median, housing, and USA.

This dataset, compiled by NREL using data from ABB, the Velocity Suite (http://energymarketintel.com/) and the U.S. Energy Information Administration dataset 861 (http://www.eia.gov/electricity/data/eia861/), provides average residential, commercial and industrial electricity rates with likely zip codes for both investor owned utilities (IOU) and non-investor owned utilities. Note: the files include average rates for each utility (not average rates per zip code), but not the detailed rate structure data found in the OpenEI U.S. Utility Rate Database (https://openei.org/apps/USURDB/).

President Trump's proposals to impose universal tariffs as well as tariffs on Chinese, Canadian, and Mexican imports would considerably increase the average tariff rate. It's estimated that, if put into effect, the average tariff rate including dutiable imports would reach almost 18 percent, up from two percent in 2024. Tariff rates are higher when dutiable imports are included because they refer only to goods that are actually subject to tariffs, rather than all imports. This skews the average tariff rate upward because it excludes duty-free goods. Trump's proposal for a universal 10 percent tariff on all imports would impose a flat tax on all imports, rather than just dutiable goods. This would result in a sharp increase in the overall tariff burden because previously duty-free goods would be taxed.

Producer Prices in the United States increased to 149.78 points in September from 149.32 points in August of 2025. This dataset provides the latest reported value for - United States Producer Prices - plus previous releases, historical high and low, short-term forecast and long-term prediction, economic calendar, survey consensus and news.

About this dataset

Context

The dataset presents the distribution of median household income among distinct age brackets of householders in Price. Based on the latest 2019-2023 5-Year Estimates from the American Community Survey, it displays how income varies among householders of different ages in Price. It showcases how household incomes typically rise as the head of the household gets older. The dataset can be utilized to gain insights into age-based household income trends and explore the variations in incomes across households.

Key observations: Insights from 2023

In terms of income distribution across age cohorts, in Price, householders within the 25 to 44 years age group have the highest median household income at $59,052, followed by those in the 45 to 64 years age group with an income of $51,968. Meanwhile householders within the 65 years and over age group report the second lowest median household income of $30,972. Notably, householders within the under 25 years age group, had the lowest median household income at $27,850.

Content

When available, the data consists of estimates from the U.S. Census Bureau American Community Survey (ACS) 2019-2023 5-Year Estimates. All incomes have been adjusting for inflation and are presented in 2023-inflation-adjusted dollars.

Age groups classifications include:

• Under 25 years
• 25 to 44 years
• 45 to 64 years
• 65 years and over

Variables / Data Columns

• Age Of The Head Of Household: This column presents the age of the head of household
• Median Household Income: Median household income, in 2023 inflation-adjusted dollars for the specific age group

Good to know

Margin of Error

Data in the dataset are based on the estimates and are subject to sampling variability and thus a margin of error. Neilsberg Research recommends using caution when presening these estimates in your research.

Custom data

If you do need custom data for any of your research project, report or presentation, you can contact our research staff at research@neilsberg.com for a feasibility of a custom tabulation on a fee-for-service basis.

Inspiration

Neilsberg Research Team curates, analyze and publishes demographics and economic data from a variety of public and proprietary sources, each of which often includes multiple surveys and programs. The large majority of Neilsberg Research aggregated datasets and insights is made available for free download at https://www.neilsberg.com/research/.

Recommended for further research

This dataset is a part of the main dataset for Price median household income by age. You can refer the same here

Description

Subscriptions to economics journals at US libraries, for the year 2000.

Usage

data("Journals")

Format

A data frame containing 180 observations on 10 variables.

title

Journal title.

publisher

factor with publisher name.

society

factor. Is the journal published by a scholarly society?

price

Library subscription price.

pages

Number of pages.

charpp

Characters per page.

citations

Total number of citations.

foundingyear

Year journal was founded.

subs

Number of library subscriptions.

field

factor with field description.

Details

Data on 180 economic journals, collected in particular for analyzing journal pricing. See also https://econ.ucsb.edu/~tedb/Journals/jpricing.html for general information on this topic as well as a more up-to-date version of the data set. This version is taken from Stock and Watson (2007).

The data as obtained from the online complements for Stock and Watson (2007) contained two journals with title “World Development”. One of these (observation 80) seemed to be an error and was changed to “The World Economy”.

Source

Online complements to Stock and Watson (2007).

References

Bergstrom, T. (2001). Free Labor for Costly Journals? Journal of Economic Perspectives, 15, 183–198.

Stock, J.H. and Watson, M.W. (2007). Introduction to Econometrics, 2nd ed. Boston: Addison Wesley.

Examples

data and transformed variables

data("Journals") journals <- Journals[, c("subs", "price")] journals$citeprice <- Journals$price/Journals$citations journals$age <- 2000 - Journals$foundingyear journals$chars <- Journals$charpp*Journals$pages/10^6

Stock and Watson (2007)

Figure 8.9 (a) and (b)

plot(subs ~ citeprice, data = journals, pch = 19) plot(log(subs) ~ log(citeprice), data = journals, pch = 19) fm1 <- lm(log(subs) ~ log(citeprice), data = journals) abline(fm1)

Table 8.2, use HC1 for comparability with Stata

fm2 <- lm(subs ~ citeprice + age + chars, data = log(journals)) fm3 <- lm(subs ~ citeprice + I(citeprice^2) + I(citeprice^3) + age + I(age * citeprice) + chars, data = log(journals)) fm4 <- lm(subs ~ citeprice + age + I(age * citeprice) + chars, data = log(journals)) coeftest(fm1, vcov = vcovHC(fm1, type = "HC1")) coeftest(fm2, vcov = vcovHC(fm2, type = "HC1")) coeftest(fm3, vcov = vcovHC(fm3, type = "HC1")) coeftest(fm4, vcov = vcovHC(fm4, type = "HC1")) waldtest(fm3, fm4, vcov = vcovHC(fm3, type = "HC1"))

changes with respect to age

library("strucchange")

Nyblom-Hansen test

scus <- gefp(subs ~ citeprice, data = log(journals), fit = lm, order.by = ~ age) plot(scus, functional = meanL2BB)

estimate breakpoint(s)

journals <- journals[order(journals$age),] bp <- breakpoints(subs ~ citeprice, data = log(journals), h = 20) plot(bp) bp.age <- journals$age[bp$breakpoints]

visualization

plot(subs ~ citeprice, data = log(journals), pch = 19, col = (age > log(bp.age)) + 1) abline(coef(bp)[1,], col = 1) abline(coef(bp)[2,], col = 2) legend("bottomleft", legend = c("age > 18", "age < 18"), lty = 1, col = 2:1, bty = "n")