Advertisement · 728 × 90

Posts by Steven Ponce

Area chart showing the share of the world population living in extreme poverty from 1820 to 2018. A shaded band across the top of the chart marks the historical pre-modern baseline of 75–90%, indicating that extreme poverty was the default human condition before industrialization. The line holds near 79% through the 19th century, declines gradually to 46% by 1980, then drops sharply to 8.6% by 2018, with the post-1980 decline shown in a darker fill to emphasize the acceleration.

Area chart showing the share of the world population living in extreme poverty from 1820 to 2018. A shaded band across the top of the chart marks the historical pre-modern baseline of 75–90%, indicating that extreme poverty was the default human condition before industrialization. The line holds near 79% through the 19th century, declines gradually to 46% by 1980, then drops sharply to 8.6% by 2018, with the post-1980 decline shown in a darker fill to emphasize the acceleration.

📊 #30DayChartChallenge 2026 – day 21
.
Timeseries | Historical
.
🔗 : stevenponce.netlify.app/data_visuali...
.
#rstats | #r4ds | #dataviz | #ggplot2

12 hours ago 5 2 0 0

Exactly the point — that quadrant is empty by design. In this dataset, high AI exposure and high pay don’t coexist. The upper-right is a ghost quadrant, which is what makes the pattern so stark

19 hours ago 1 0 0 0
A three-panel data visualization titled "AI Automation Risk Is a Low-Wage Problem." The top panel shows two horizontal bars comparing average annual wages: high AI risk jobs average $43K, while low AI risk jobs average $103K, a $60K gap. The bottom-left scatter plot shows AI automation risk score on the x-axis and annual wage on the y-axis, with bubble size representing the number of workers employed. Jobs are clustered into two groups: low-risk occupations in the upper-left (safe and well-paid) and high-risk occupations in the lower-right (exposed and underpaid), with labeled callouts for Dentists, Engineers, Advertising and Marketing Managers, Payroll and Timekeeping Clerks, and Tellers. The bottom-right horizontal bar chart shows worker concentration among high-risk occupations sorted by employment, revealing that Shipping, Receiving, and Inventory Clerks (858K workers) and Tellers (339K) account for the largest share of AI exposure. Data source: AI Exposure Index, aiexposure.org.

A three-panel data visualization titled "AI Automation Risk Is a Low-Wage Problem." The top panel shows two horizontal bars comparing average annual wages: high AI risk jobs average $43K, while low AI risk jobs average $103K, a $60K gap. The bottom-left scatter plot shows AI automation risk score on the x-axis and annual wage on the y-axis, with bubble size representing the number of workers employed. Jobs are clustered into two groups: low-risk occupations in the upper-left (safe and well-paid) and high-risk occupations in the lower-right (exposed and underpaid), with labeled callouts for Dentists, Engineers, Advertising and Marketing Managers, Payroll and Timekeeping Clerks, and Tellers. The bottom-right horizontal bar chart shows worker concentration among high-risk occupations sorted by employment, revealing that Shipping, Receiving, and Inventory Clerks (858K workers) and Tellers (339K) account for the largest share of AI exposure. Data source: AI Exposure Index, aiexposure.org.

📊 #MakeoverMonday – 2026 W16 | AI Risk Rankings
.
🔗: stevenponce.netlify.app/data_visuali...
.
#rstats | #DataFam | #dataviz | #ggplot2

21 hours ago 3 0 1 0
Three-panel stacked line chart showing independent indicators of planetary change from 1960 to 2024, all trending upward in parallel. Top panel: atmospheric CO₂ concentration rises from 317 ppm to 425 ppm, crossing the 400 ppm threshold in 2013. Middle panel: global mean temperature anomaly (relative to 1951–1980 baseline) climbs from near 0°C to +1.2°C, first exceeding +1°C in 2016. Bottom panel: global mean sea level rises approximately 149 mm (15 cm) above the 1960 baseline. All three signals move in the same direction across six decades, illustrating the convergent trajectory of climate change indicators. Data sources: NOAA GML (CO₂), NASA GISS (temperature), CSIRO Church & White, and NOAA LSA (sea level).

Three-panel stacked line chart showing independent indicators of planetary change from 1960 to 2024, all trending upward in parallel. Top panel: atmospheric CO₂ concentration rises from 317 ppm to 425 ppm, crossing the 400 ppm threshold in 2013. Middle panel: global mean temperature anomaly (relative to 1951–1980 baseline) climbs from near 0°C to +1.2°C, first exceeding +1°C in 2016. Bottom panel: global mean sea level rises approximately 149 mm (15 cm) above the 1960 baseline. All three signals move in the same direction across six decades, illustrating the convergent trajectory of climate change indicators. Data sources: NOAA GML (CO₂), NASA GISS (temperature), CSIRO Church & White, and NOAA LSA (sea level).

📊 #30DayChartChallenge 2026 – day 20
.
Timeseries | Evolution
.
🔗 : stevenponce.netlify.app/data_visuali...
.
#rstats | #r4ds | #dataviz | #ggplot2

1 day ago 6 2 0 0
Line chart showing the levelized cost of electricity (LCOE) for four power sources from 2010 to 2024 in 2024 USD per kilowatt-hour. Solar PV begins at $0.42/kWh in 2010 and falls 90% to $0.043/kWh by 2024, the steepest decline of any technology. Onshore wind drops 69% from $0.11 to $0.034/kWh. Offshore wind declines from $0.19 to $0.079/kWh. Fossil fuels remain relatively flat near $0.09/kWh throughout, spiking to $0.14/kWh in 2022 before retreating. Two vertical dotted lines mark cost-parity crossover points: onshore wind becomes cost-competitive with fossil fuels in 2013, solar in 2017. By 2024, both solar and onshore wind generate electricity more cheaply than any fossil fuel alternative. Data source: IRENA Renewable Power Generation Costs reports.

Line chart showing the levelized cost of electricity (LCOE) for four power sources from 2010 to 2024 in 2024 USD per kilowatt-hour. Solar PV begins at $0.42/kWh in 2010 and falls 90% to $0.043/kWh by 2024, the steepest decline of any technology. Onshore wind drops 69% from $0.11 to $0.034/kWh. Offshore wind declines from $0.19 to $0.079/kWh. Fossil fuels remain relatively flat near $0.09/kWh throughout, spiking to $0.14/kWh in 2022 before retreating. Two vertical dotted lines mark cost-parity crossover points: onshore wind becomes cost-competitive with fossil fuels in 2013, solar in 2017. By 2024, both solar and onshore wind generate electricity more cheaply than any fossil fuel alternative. Data source: IRENA Renewable Power Generation Costs reports.

📊 #30DayChartChallenge 2026 – day 19
.
Timeseries | Evolution
.
🔗 : stevenponce.netlify.app/data_visuali...
.
#rstats | #r4ds | #dataviz | #ggplot2

2 days ago 11 1 0 0

Interesting hypothesis

3 days ago 0 0 0 0

Thank you morgan

3 days ago 1 0 0 0
A two-panel data visualization. The left panel is a scatter plot showing government health spending versus out-of-pocket payments as a percentage of current health expenditure for 195 countries in 2023. Countries with lower government spending cluster in the upper-left with high out-of-pocket burden, highlighted in burgundy. Countries with high government spending cluster in the lower-right with low out-of-pocket burden, highlighted in steel blue. A dashed diagonal reference line and a dotted 40% hardship threshold line provide analytical anchors. The right panel shows global median trends from 2000 to 2023: government spending (blue) rising steadily, out-of-pocket payments (burgundy) declining. A shaded band marks COVID-19 years. Together, the panels show where governments spend less, households spend more — and that this pattern has slowly improved globally over two decades.

A two-panel data visualization. The left panel is a scatter plot showing government health spending versus out-of-pocket payments as a percentage of current health expenditure for 195 countries in 2023. Countries with lower government spending cluster in the upper-left with high out-of-pocket burden, highlighted in burgundy. Countries with high government spending cluster in the lower-right with low out-of-pocket burden, highlighted in steel blue. A dashed diagonal reference line and a dotted 40% hardship threshold line provide analytical anchors. The right panel shows global median trends from 2000 to 2023: government spending (blue) rising steadily, out-of-pocket payments (burgundy) declining. A shaded band marks COVID-19 years. Together, the panels show where governments spend less, households spend more — and that this pattern has slowly improved globally over two decades.

📊 #TidyTuesday – 2026 W16 | Global Health Spending
.
🔗: stevenponce.netlify.app/data_visuali...
.
#rstats | #r4ds | #dataviz | #ggplot2

3 days ago 8 1 0 0
A dumbbell chart comparing under-five and neonatal mortality rates across four regions (Sub-Saharan Africa, World, South Asia, Latin America & Caribbean) between 1990 (open circle) and 2023 (filled circle). Both panels show sharp declines, but the neonatal panel reveals slower progress — illustrated by shorter dumbbells relative to starting values. A callout notes that neonatal deaths rose from 39% to 47% of all under-five deaths globally between 1990 and 2023, signaling a concentration of child mortality risk in the first 28 days of life. Rates are per 1,000 live births.

A dumbbell chart comparing under-five and neonatal mortality rates across four regions (Sub-Saharan Africa, World, South Asia, Latin America & Caribbean) between 1990 (open circle) and 2023 (filled circle). Both panels show sharp declines, but the neonatal panel reveals slower progress — illustrated by shorter dumbbells relative to starting values. A callout notes that neonatal deaths rose from 39% to 47% of all under-five deaths globally between 1990 and 2023, signaling a concentration of child mortality risk in the first 28 days of life. Rates are per 1,000 live births.

📊 #30DayChartChallenge 2026 – day 18
.
Relationships | Data Day — UNICEF
.
🔗 : stevenponce.netlify.app/data_visuali...
.
#rstats | #r4ds | #dataviz | #ggplot2

3 days ago 9 3 2 0
Advertisement
A two-part data visualization titled "The Holiday-Volatility Paradox." The left side shows four scatter plots arranged in a 2×2 grid, each showing the relationship between the average number of holidays per month (x-axis) and the coefficient of variation in air traffic (y-axis) for Small, Medium, Large, and Very Large markets. A red linear trend line in the Small Market panel shows a positive correlation (r = +0.48), while blue trend lines in the Medium (r = −0.22), Large (r = −0.17), and Very Large (r = −0.07) panels show negative correlations. A dashed reference line marks the industry median volatility. The right side shows a summary slope chart titled "The Sign Flip," plotting the four correlation values across market sizes and built in R/ggplot2 as a remake of TidyTuesday 2024 Week 52.

A two-part data visualization titled "The Holiday-Volatility Paradox." The left side shows four scatter plots arranged in a 2×2 grid, each showing the relationship between the average number of holidays per month (x-axis) and the coefficient of variation in air traffic (y-axis) for Small, Medium, Large, and Very Large markets. A red linear trend line in the Small Market panel shows a positive correlation (r = +0.48), while blue trend lines in the Medium (r = −0.22), Large (r = −0.17), and Very Large (r = −0.07) panels show negative correlations. A dashed reference line marks the industry median volatility. The right side shows a summary slope chart titled "The Sign Flip," plotting the four correlation values across market sizes and built in R/ggplot2 as a remake of TidyTuesday 2024 Week 52.

📊 #30DayChartChallenge 2026 – day 17
.
Relationships | Remake
.
🔗 : stevenponce.netlify.app/data_visuali...
.
#rstats | #r4ds | #dataviz | #ggplot2

4 days ago 6 2 0 0
Line chart showing indexed U.S. trends in leaded gasoline use (red) and violent crime rates (dark) from 1941 to 2010, both normalized to peak = 100. Leaded gasoline peaked around 1970 and declined sharply after the EPA regulation began in 1973. Violent crime peaks around 1991 — approximately 22 years later — then falls steadily. A shaded band and arrow highlight the lag window between the two peaks, illustrating the hypothesis that early-life lead exposure shaped the U.S. crime wave two decades later.

Line chart showing indexed U.S. trends in leaded gasoline use (red) and violent crime rates (dark) from 1941 to 2010, both normalized to peak = 100. Leaded gasoline peaked around 1970 and declined sharply after the EPA regulation began in 1973. Violent crime peaks around 1991 — approximately 22 years later — then falls steadily. A shaded band and arrow highlight the lag window between the two peaks, illustrating the hypothesis that early-life lead exposure shaped the U.S. crime wave two decades later.

📊 #30DayChartChallenge 2026 – day 16
.
Relationships | Causation
.
🔗 : stevenponce.netlify.app/data_visuali...
.
#rstats | #r4ds | #dataviz | #ggplot2

5 days ago 6 0 0 0
A 2×2 grid of scatter plots showing fossil fuels' share of electricity versus GDP per capita (log scale) in 2022, faceted by World Bank income group. Each panel includes a linear trend line with confidence band and a Pearson r annotation. Low-income countries show no relationship (r = −0.08); lower-middle-income countries show a moderate positive correlation (r = 0.50); upper-middle-income countries show a weak positive trend (r = 0.24); high-income countries show virtually no relationship (r = 0.05). Selected countries are labeled: DR Congo and Ethiopia (low income), Nigeria and India (lower middle), China and Brazil (upper middle), Saudi Arabia and Norway (high income). The overall pattern reveals that fossil dependence rises with income through the middle-income stages, then breaks down at high income — where energy policy choices, not wealth alone, determine the electricity mix.

A 2×2 grid of scatter plots showing fossil fuels' share of electricity versus GDP per capita (log scale) in 2022, faceted by World Bank income group. Each panel includes a linear trend line with confidence band and a Pearson r annotation. Low-income countries show no relationship (r = −0.08); lower-middle-income countries show a moderate positive correlation (r = 0.50); upper-middle-income countries show a weak positive trend (r = 0.24); high-income countries show virtually no relationship (r = 0.05). Selected countries are labeled: DR Congo and Ethiopia (low income), Nigeria and India (lower middle), China and Brazil (upper middle), Saudi Arabia and Norway (high income). The overall pattern reveals that fossil dependence rises with income through the middle-income stages, then breaks down at high income — where energy policy choices, not wealth alone, determine the electricity mix.

📊 #30DayChartChallenge 2026 – day 15
.
Relationships | Correlation
.
🔗 : stevenponce.netlify.app/data_visuali...
.
#rstats | #r4ds | #dataviz | #ggplot2

6 days ago 9 0 0 0
An alluvial (Sankey-style) chart titled "Global Trade Connects Regions Through a Few Dominant Product Flows." The left axis shows five world regions — Asia, Europe, the Americas, Africa, and Oceania — ordered from the largest to the smallest exporter. Flows connect each region to one of three product groups on the right: Agriculture (green), Fuels & Mining (copper), and Manufacturing (burgundy). Asia and Europe generate the widest flows, with manufactured goods — shown in deep burgundy — dominating exports across every region. Fuels & Mining flows are most prominent from the Americas and Africa. Agriculture flows are thin across all regions. Data represent average annual merchandise exports from 2019 to 2023, sourced from the WTO Statistics Portal.

An alluvial (Sankey-style) chart titled "Global Trade Connects Regions Through a Few Dominant Product Flows." The left axis shows five world regions — Asia, Europe, the Americas, Africa, and Oceania — ordered from the largest to the smallest exporter. Flows connect each region to one of three product groups on the right: Agriculture (green), Fuels & Mining (copper), and Manufacturing (burgundy). Asia and Europe generate the widest flows, with manufactured goods — shown in deep burgundy — dominating exports across every region. Fuels & Mining flows are most prominent from the Americas and Africa. Agriculture flows are thin across all regions. Data represent average annual merchandise exports from 2019 to 2023, sourced from the WTO Statistics Portal.

📊 #30DayChartChallenge 2026 – day 14
.
Relationships | Trade
.
🔗 : stevenponce.netlify.app/data_visuali...
.
#rstats | #r4ds | #dataviz | #ggplot2

1 week ago 7 1 0 0
A scatter plot comparing seven major tech companies by hiring rate (y-axis) and layoff rate (x-axis), both expressed as a percentage of the current workforce. A dashed diagonal line marks the net growth threshold where hiring equals layoffs. Companies above the line — NVIDIA, Apple, and Google are net expanders, shown in teal. Companies below — Microsoft, Meta, Amazon, and Tesla — are net contractors, shown in burgundy. NVIDIA stands apart in the upper left with the highest hiring rate and zero layoffs. Microsoft anchors the lower right with the highest layoff rate despite active recruiting.

A scatter plot comparing seven major tech companies by hiring rate (y-axis) and layoff rate (x-axis), both expressed as a percentage of the current workforce. A dashed diagonal line marks the net growth threshold where hiring equals layoffs. Companies above the line — NVIDIA, Apple, and Google are net expanders, shown in teal. Companies below — Microsoft, Meta, Amazon, and Tesla — are net contractors, shown in burgundy. NVIDIA stands apart in the upper left with the highest hiring rate and zero layoffs. Microsoft anchors the lower right with the highest layoff rate despite active recruiting.

📊 #MakeoverMonday – 2026 W15 | Big Tech Hiring
.
🔗: stevenponce.netlify.app/data_visuali...
.
#rstats | #DataFam | #dataviz | #ggplot2

1 week ago 2 0 0 0
A vertical node-arrow diagram titled "One Intervention, System-Wide Impact." Five trophic levels cascade top to bottom: Wolves (apex predator, index 0 to 100), Elk (herbivore, 100 to 40), Willows (vegetation, 20 to 80), Beavers (engineer, 5 to 25), and Rivers (landscape, 30 to 70). A red arrow connects Wolves to Elk, labeled "elk population declined, movement patterns shifted." Three green arrows follow, each labeled with a recovery effect: overgrazing was reduced and vegetation recovered; willow thickets expanded and beaver habitat was restored; beaver dams increased, and rivers stabilized. An intervention callout marks 1995 as the year wolves were reintroduced to Yellowstone. A result box at the bottom reads: Rivers stabilized, Biodiversity increased, Ecosystem resilience restored. Data source: Ripple and Beschta (2012); values are directional indices, not absolute counts.

A vertical node-arrow diagram titled "One Intervention, System-Wide Impact." Five trophic levels cascade top to bottom: Wolves (apex predator, index 0 to 100), Elk (herbivore, 100 to 40), Willows (vegetation, 20 to 80), Beavers (engineer, 5 to 25), and Rivers (landscape, 30 to 70). A red arrow connects Wolves to Elk, labeled "elk population declined, movement patterns shifted." Three green arrows follow, each labeled with a recovery effect: overgrazing was reduced and vegetation recovered; willow thickets expanded and beaver habitat was restored; beaver dams increased, and rivers stabilized. An intervention callout marks 1995 as the year wolves were reintroduced to Yellowstone. A result box at the bottom reads: Rivers stabilized, Biodiversity increased, Ecosystem resilience restored. Data source: Ripple and Beschta (2012); values are directional indices, not absolute counts.

📊 #30DayChartChallenge 2026 – day 13
.
Relationships | Ecosystems
.
🔗 : stevenponce.netlify.app/data_visuali...
.
#rstats | #r4ds | #dataviz | #ggplot2

1 week ago 6 1 0 0
Ordered dot plot titled "Distance from Normal." Each dot represents one country, positioned horizontally by its deviation from the global median electricity carbon intensity of 482 gCO₂/kWh. The distribution is right-skewed: most countries cluster near zero, while a small group of coal-dependent systems — led by Turkmenistan (+825), Uzbekistan (+639), and Falkland Islands (+518) — extends far into the right tail. Two countries with hydro-heavy grids, Nepal and Lesotho, anchor the left tail near −460 gCO₂/kWh. Data from Our World in Data Energy Dataset (Ember / Energy Institute).

Ordered dot plot titled "Distance from Normal." Each dot represents one country, positioned horizontally by its deviation from the global median electricity carbon intensity of 482 gCO₂/kWh. The distribution is right-skewed: most countries cluster near zero, while a small group of coal-dependent systems — led by Turkmenistan (+825), Uzbekistan (+639), and Falkland Islands (+518) — extends far into the right tail. Two countries with hydro-heavy grids, Nepal and Lesotho, anchor the left tail near −460 gCO₂/kWh. Data from Our World in Data Energy Dataset (Ember / Energy Institute).

📊 #30DayChartChallenge 2026 – day 12
.
Distributions | Theme Day — FlowingData
.
🔗 : stevenponce.netlify.app/data_visuali...
.
#rstats | #r4ds | #dataviz | #ggplot2

1 week ago 7 1 0 0
Two-panel data visualization titled "Rough Seas Suppress Feeding — They Don't Enhance It." Panel A is a heatmap showing survey effort by wind condition (Beaufort scale, binned Calm to Gale+) and sea state (SS1–SS6). Observation density peaks at slight-to-moderate seas with light-to-moderate winds, shown in deep navy. Panel B is a dot plot with Wilson 95% confidence intervals showing seabird feeding rates by sea state. Feeding peaks at 11.9% under calm, rippled conditions (SS1) and declines steadily through rough (SS5, ~4%) and very rough seas (SS6, ~2%). A dashed reference line marks the peak feeding rate. Data from Te Papa Tongarewa, Museum of New Zealand, 1969–1990.

Two-panel data visualization titled "Rough Seas Suppress Feeding — They Don't Enhance It." Panel A is a heatmap showing survey effort by wind condition (Beaufort scale, binned Calm to Gale+) and sea state (SS1–SS6). Observation density peaks at slight-to-moderate seas with light-to-moderate winds, shown in deep navy. Panel B is a dot plot with Wilson 95% confidence intervals showing seabird feeding rates by sea state. Feeding peaks at 11.9% under calm, rippled conditions (SS1) and declines steadily through rough (SS5, ~4%) and very rough seas (SS6, ~2%). A dashed reference line marks the peak feeding rate. Data from Te Papa Tongarewa, Museum of New Zealand, 1969–1990.

📊 #TidyTuesday – 2026 W15 | Bird Sightings at Sea
.
🔗: stevenponce.netlify.app/data_visuali...
.
#rstats | #r4ds | #dataviz | #ggplot2

1 week ago 6 1 0 0
A survival curve chart titled "Different Failure Modes, Different Timelines." Five Kaplan-Meier-style curves show how five machine failure modes — Random Failure, Heat Stress, Power Failure, Wear-Out, and Overstrain — behave differently as accumulated tool wear increases in a synthetic milling machine. All curves remain near 100% survival probability through approximately 185 minutes of tool wear, then diverge sharply in the wear-out zone. Random Failure stays closest to 100%, while Overstrain drops most steeply, reaching near 0% by 250 minutes. A shaded region marks the wear-out zone where failures concentrate.

A survival curve chart titled "Different Failure Modes, Different Timelines." Five Kaplan-Meier-style curves show how five machine failure modes — Random Failure, Heat Stress, Power Failure, Wear-Out, and Overstrain — behave differently as accumulated tool wear increases in a synthetic milling machine. All curves remain near 100% survival probability through approximately 185 minutes of tool wear, then diverge sharply in the wear-out zone. Random Failure stays closest to 100%, while Overstrain drops most steeply, reaching near 0% by 250 minutes. A shaded region marks the wear-out zone where failures concentrate.

📊 #30DayChartChallenge 2026 – day 11
.
Distributions | Physical
.
🔗 : stevenponce.netlify.app/data_visuali...
.
#rstats | #r4ds | #dataviz | #ggplot2

1 week ago 5 1 0 0
Half-eye distribution chart comparing return on investment (ROI) for Horror and Crime films (1980–2020, US box office, log scale). Horror films (n=254) show a wide, right-skewed distribution with a median ROI of 2x and a long tail of extreme outliers — including Paranormal Activity (2007), which returned 12,889x on a $15,000 budget. Crime films (n=400) cluster tightly near break-even with a median ROI of 0.3x and few breakout returns. The chart shows that Horror is Hollywood's highest-variance genre, while Crime is its least volatile.

Half-eye distribution chart comparing return on investment (ROI) for Horror and Crime films (1980–2020, US box office, log scale). Horror films (n=254) show a wide, right-skewed distribution with a median ROI of 2x and a long tail of extreme outliers — including Paranormal Activity (2007), which returned 12,889x on a $15,000 budget. Crime films (n=400) cluster tightly near break-even with a median ROI of 0.3x and few breakout returns. The chart shows that Horror is Hollywood's highest-variance genre, while Crime is its least volatile.

📊 #30DayChartChallenge 2026 – day 10
.
Distributions | Pop Culture
.
🔗 : stevenponce.netlify.app/data_visuali...
.
#rstats | #r4ds | #dataviz | #ggplot2

1 week ago 5 1 0 0
Advertisement
Horizontal stacked bar chart comparing the global distribution of population across four daily income thresholds in 2000 and 2022, adjusted for purchasing power parity. In 2000, 36% of the world lived on less than $3 per day and 38% on $3–$10; by 2022, extreme poverty fell to 11% while the $10–$30 bracket saw the largest growth, rising from 13% to 27%. Those above $30 per day nearly doubled from 13% to 18%.

Horizontal stacked bar chart comparing the global distribution of population across four daily income thresholds in 2000 and 2022, adjusted for purchasing power parity. In 2000, 36% of the world lived on less than $3 per day and 38% on $3–$10; by 2022, extreme poverty fell to 11% while the $10–$30 bracket saw the largest growth, rising from 13% to 27%. Those above $30 per day nearly doubled from 13% to 18%.

📊 #30DayChartChallenge 2026 – day 09
.
Distributions | Wealth
.
🔗 : stevenponce.netlify.app/data_visuali...
.
#rstats | #r4ds | #dataviz | #ggplot2

1 week ago 4 1 0 0
Circular chart showing the weekly distribution of U.S. flu activity across the 52-week year. A gray band represents the typical seasonal range from 2015–16 to 2019–20, with activity concentrated near January and February at the top of the clock face and near zero during summer months at the bottom. A small cyan ring near the center shows the 2020–21 season, when flu nearly disappeared due to COVID-19 pandemic measures.

Circular chart showing the weekly distribution of U.S. flu activity across the 52-week year. A gray band represents the typical seasonal range from 2015–16 to 2019–20, with activity concentrated near January and February at the top of the clock face and near zero during summer months at the bottom. A small cyan ring near the center shows the 2020–21 season, when flu nearly disappeared due to COVID-19 pandemic measures.

📊 #30DayChartChallenge 2026 – day 08
.
Distributions | Circular
.
🔗 : stevenponce.netlify.app/data_visuali...
.
#rstats | #r4ds | #dataviz | #ggplot2

1 week ago 13 1 1 0
A three-panel chart showing the distribution of renewable electricity share across countries in 2022 at three scales. Panel 1 is a histogram of the global distribution, revealing a bimodal shape with many countries clustered near 0–20% and another group near 100%, with a median of roughly 32%. Panel 2 shows half-eye density plots by World Bank income group — Low, Lower-middle, Upper-middle, and High — all with similar medians around 28–36%, but notably different spreads and shapes. Panel 3 zooms in on Upper-middle income countries as a dot plot, where individual-country variation is stark: South Africa sits near 0%, China and Turkey near 25–30%, and Brazil and Paraguay near 80–100%.

A three-panel chart showing the distribution of renewable electricity share across countries in 2022 at three scales. Panel 1 is a histogram of the global distribution, revealing a bimodal shape with many countries clustered near 0–20% and another group near 100%, with a median of roughly 32%. Panel 2 shows half-eye density plots by World Bank income group — Low, Lower-middle, Upper-middle, and High — all with similar medians around 28–36%, but notably different spreads and shapes. Panel 3 zooms in on Upper-middle income countries as a dot plot, where individual-country variation is stark: South Africa sits near 0%, China and Turkey near 25–30%, and Brazil and Paraguay near 80–100%.

📊 #30DayChartChallenge 2026 – day 07
.
Distributions | Multiscale
.
🔗 : stevenponce.netlify.app/data_visuali...
.
#rstats | #r4ds | #dataviz | #ggplot2

2 weeks ago 13 3 0 0
A gap chart showing U.S. and Saudi Arabia oil production in terawatt-hours from 1965 to 2024. The area between the two lines is shaded in two colors: warm gray before 2009, labeled "Production tracked closely," and steel blue after 2009, labeled "U.S. pulls ahead." A dashed vertical line marks the inflection point of the 2009 shale boom. The U.S. line ends at 10k TWh in 2024; Saudi Arabia at 5.9k TWh. An annotation notes that U.S. output is approximately 1.7 times that of Saudi Arabia. The chart illustrates a structural shift from decades of competitive parity to clear U.S. dominance following the shale revolution.

A gap chart showing U.S. and Saudi Arabia oil production in terawatt-hours from 1965 to 2024. The area between the two lines is shaded in two colors: warm gray before 2009, labeled "Production tracked closely," and steel blue after 2009, labeled "U.S. pulls ahead." A dashed vertical line marks the inflection point of the 2009 shale boom. The U.S. line ends at 10k TWh in 2024; Saudi Arabia at 5.9k TWh. An annotation notes that U.S. output is approximately 1.7 times that of Saudi Arabia. The chart illustrates a structural shift from decades of competitive parity to clear U.S. dominance following the shale revolution.

📊 #MakeoverMonday – 2026 W14 | Global Oil Production
.
🔗: stevenponce.netlify.app/data_visuali...
.
#rstats | #DataFam | #dataviz | #ggplot2

2 weeks ago 5 0 0 0
An arrow chart showing the 10 biggest improvements and 10 biggest declines in RSF Press Freedom rankings between 2015 and 2025. Blue arrows point leftward — from a higher 2015 rank to a lower 2025 rank — indicating improvement in press freedom. Burgundy arrows point to the right, indicating decline. Top improvers include Gambia (+93 places), Montenegro, and North Macedonia. The biggest decliners include Nicaragua (−98 places), El Salvador, and Hong Kong. The x-axis runs from rank 1 (most free) on the left to rank 180 (least free) on the right. A gray dot marks each country's 2015 starting rank.

An arrow chart showing the 10 biggest improvements and 10 biggest declines in RSF Press Freedom rankings between 2015 and 2025. Blue arrows point leftward — from a higher 2015 rank to a lower 2025 rank — indicating improvement in press freedom. Burgundy arrows point to the right, indicating decline. Top improvers include Gambia (+93 places), Montenegro, and North Macedonia. The biggest decliners include Nicaragua (−98 places), El Salvador, and Hong Kong. The x-axis runs from rank 1 (most free) on the left to rank 180 (least free) on the right. A gray dot marks each country's 2015 starting rank.

📊 #30DayChartChallenge 2026 – day 06
.
Comparisons | Data Day — Reporters Without Borders
.
🔗 : stevenponce.netlify.app/data_visuali...
.
#rstats | #r4ds | #dataviz | #ggplot2

2 weeks ago 9 1 0 0
Barcode strip plot showing the carbon intensity of electricity (gCO₂ per kWh, 2020–2023 average) for countries grouped by World Bank income classification. Each vertical tick represents one country. A taupe band marks the middle 50% (IQR) and a white-filled dot marks the group median. Groups are sorted from lowest to highest median: High income (250 g), Low income (256 g), Upper middle income (454 g), and Lower middle income (481 g). A dashed vertical line marks the global median. Notable outliers include Norway and Poland (High income), Ethiopia and Syria (Low income), Albania and Turkmenistan (Upper middle income), and Nepal and Uzbekistan (Lower middle income). Within-group variation is wide across all four groups, often rivaling differences between groups.

Barcode strip plot showing the carbon intensity of electricity (gCO₂ per kWh, 2020–2023 average) for countries grouped by World Bank income classification. Each vertical tick represents one country. A taupe band marks the middle 50% (IQR) and a white-filled dot marks the group median. Groups are sorted from lowest to highest median: High income (250 g), Low income (256 g), Upper middle income (454 g), and Lower middle income (481 g). A dashed vertical line marks the global median. Notable outliers include Norway and Poland (High income), Ethiopia and Syria (Low income), Albania and Turkmenistan (Upper middle income), and Nepal and Uzbekistan (Lower middle income). Within-group variation is wide across all four groups, often rivaling differences between groups.

📊 #30DayChartChallenge 2026 – day 05
.
Comparisons | Experimental
.
🔗 : stevenponce.netlify.app/data_visuali...
.
#rstats | #r4ds | #dataviz | #ggplot2

2 weeks ago 14 1 0 0
A two-panel data visualization titled "Repair Isn't the Problem — The System Is." The left panel is a scatter plot showing product categories by median repairability score (x-axis, 1–10) versus percentage successfully repaired (y-axis, 0–100%). A shaded amber region marks the "system constraint" zone — categories rated easy to fix (score ≥6) but repaired less than 50% of the time. Two rust-colored points, Computer Equipment/Phones and Display and Sound Equipment, fall in this zone near the 50% threshold. Slate-colored points for Textiles and Tools Non-Electric sit above 85% success despite similar repairability scores. The right panel is a horizontal bar chart showing the share of recorded failure reasons. "Spare parts unavailable" dominates at 65% (rust bar), followed by "Failure unidentified" at 26% and "Insufficient time" at 9% (gray bars). Together, the panels show that repair failure is driven by systemic constraints — primarily missing parts — rather than by volunteer skill or product difficulty. Data source: Repair Monitor (repaircafes.org).

A two-panel data visualization titled "Repair Isn't the Problem — The System Is." The left panel is a scatter plot showing product categories by median repairability score (x-axis, 1–10) versus percentage successfully repaired (y-axis, 0–100%). A shaded amber region marks the "system constraint" zone — categories rated easy to fix (score ≥6) but repaired less than 50% of the time. Two rust-colored points, Computer Equipment/Phones and Display and Sound Equipment, fall in this zone near the 50% threshold. Slate-colored points for Textiles and Tools Non-Electric sit above 85% success despite similar repairability scores. The right panel is a horizontal bar chart showing the share of recorded failure reasons. "Spare parts unavailable" dominates at 65% (rust bar), followed by "Failure unidentified" at 26% and "Insufficient time" at 9% (gray bars). Together, the panels show that repair failure is driven by systemic constraints — primarily missing parts — rather than by volunteer skill or product difficulty. Data source: Repair Monitor (repaircafes.org).

📊 #TidyTuesday – 2026 W14 | Repair Cafes Worldwide
.
🔗: stevenponce.netlify.app/data_visuali...
.
#rstats | #r4ds | #dataviz | #ggplot2

2 weeks ago 6 0 1 0
Slope chart showing carbon intensity of electricity generation (gCO₂/kWh) for 20 countries, comparing 2020 to 2024. Three countries are highlighted in green as the largest absolute improvers: Chile (−172 g), Poland (−126 g), and Australia (−88 g). A dashed blue line marks the 100 gCO₂/kWh clean grid benchmark. France, Sweden, Norway, and Brazil already fall below this threshold in both years. All other countries are shown in gray and show modest or no improvement over the period.

Slope chart showing carbon intensity of electricity generation (gCO₂/kWh) for 20 countries, comparing 2020 to 2024. Three countries are highlighted in green as the largest absolute improvers: Chile (−172 g), Poland (−126 g), and Australia (−88 g). A dashed blue line marks the 100 gCO₂/kWh clean grid benchmark. France, Sweden, Norway, and Brazil already fall below this threshold in both years. All other countries are shown in gray and show modest or no improvement over the period.

📊 #30DayChartChallenge 2026 – day 04
.
Comparisons | Slope
.
🔗 : stevenponce.netlify.app/data_visuali...
.
#rstats | #r4ds | #dataviz | #ggplot2

2 weeks ago 8 2 0 0

Thanks Gilles! Used ggmosaic in R for the chart grammar, with a manual geom_text() layer built from pre-computed tile centroids for the labels. Everything else is ggplot2 + ggtext.

2 weeks ago 0 0 0 0
The mosaic chart shows the electricity generation mix by World Bank income group in 2022. Tile width represents each group's share of global output; tile height shows the energy source mix within that group. Upper-middle-income countries — dominated by China — produce the largest share of global electricity at roughly 48%, with fossil fuels accounting for 31% of global output alone. A dashed vertical line marks the boundary between upper-middle and high-income countries, where the energy mix meaningfully diversifies. High-income countries account for about 39% of global production, with notable shares in wind, solar, hydro, and nuclear. Lower-middle-income countries produce around 12%, still heavily fossil-dependent. Low-income nations collectively produce less than 1% of global electricity and are annotated. Data source: Our World in Data, Energy Institute Statistical Review of World Energy.

The mosaic chart shows the electricity generation mix by World Bank income group in 2022. Tile width represents each group's share of global output; tile height shows the energy source mix within that group. Upper-middle-income countries — dominated by China — produce the largest share of global electricity at roughly 48%, with fossil fuels accounting for 31% of global output alone. A dashed vertical line marks the boundary between upper-middle and high-income countries, where the energy mix meaningfully diversifies. High-income countries account for about 39% of global production, with notable shares in wind, solar, hydro, and nuclear. Lower-middle-income countries produce around 12%, still heavily fossil-dependent. Low-income nations collectively produce less than 1% of global electricity and are annotated. Data source: Our World in Data, Energy Institute Statistical Review of World Energy.

📊 #30DayChartChallenge 2026 – day 03
.
Comparisons | Mosaic
.
🔗 : stevenponce.netlify.app/data_visuali...
.
#rstats | #r4ds | #dataviz | #ggplot2

2 weeks ago 15 1 1 0
Advertisement

Great point — the contribution side is real and important context. This chart is a spending snapshot only; a taxes-paid vs. benefits-received breakdown would tell a fuller story.

2 weeks ago 1 0 1 0