People per tax return and Days of 90°F or hotter

Where People per tax return is higher, Days of 90°F or hotter tends to be higher. The link is weak: +0.38 across 3,089 counties, on a scale from −1 (opposite) to +1 (in step). That figure compares places with the same population density, income and education, so those differences can't explain it. It holds inside states too. Measured separately within each of 39 states, the middle value of the link is +0.10.

Holds after adjusting

Every place, plotted

One dot for each place reporting both measures. Hover over or tap a dot to see its name and values. The thin line is the straight line that best fits the dots. The bold line, shown for counties, is the link after adjusting for density, income and education. A dot far from the lines is a place that does not follow the pattern.

Loading every place…

What each measure is

People per tax return

People covered per tax return: household size as the tax system sees it.

IRS Statistics of Income · IRS SOI N2 / N1

Days of 90°F or hotter

The number of days in the year when the high temperature reached 90°F or more. The high is the average over the county of NOAA's daily map of weather station readings, made of squares about 3 miles wide. So a county with hot valleys and cool mountains counts fewer days than its hottest town. A state's figure is the average of its counties, each weighted by its land area. Lower 48 states only, from 1951.

NOAA NCEI nClimGrid-Daily · NOAA NCEI nClimGrid-Daily v1.0.0 county averages (prcp/tmax/tmin, scaled), hot_days; states, counties averaged by land area

Highest and lowest

Where each measure is highest and lowest among the places reporting both (2023), with the other measure beside it. This is shown for every size of place where both are published. Metro-area values are added up from their counties. A measure that cannot be added up across counties, such as a middle value (median), has no metro figure. Counts are shown per 1,000 residents, since raw totals would only list the largest places. Cities and towns and ZIP codes are shown where the Census survey or the CDC publishes them; most other sources stop at the county. They are shown for places of 5,000 residents or more, and only where the survey’s margin of error is small enough for the figure to be usable. The CDC publishes its health estimates for cities in a version adjusted for age, so places with older or younger people can be compared fairly, but not for ZIP codes.

Counties

By people per tax return

	People per tax return	Days of 90°F or hotter
Highest
Jefferson County, ID	2	22
Gaines County, TX	2	109
Buffalo County, SD	2	26
Sterling County, TX	2	118
Juab County, UT	2	40
Lowest
New York County, NY	1	10
Suffolk County, MA	1	1
Pitkin County, CO	2	0
San Juan County, CO	2	0
District of Columbia, DC	2	20

By days of 90°F or hotter

	People per tax return	Days of 90°F or hotter
Highest
Starr County, TX	2	196
Zapata County, TX	2	192
Hidalgo County, TX	2	189
Brooks County, TX	2	187
Jim Hogg County, TX	2	186
Lowest
Teller County, CO	2	0
Summit County, CO	2	0
San Juan County, CO	2	0
Saguache County, CO	2	0
Routt County, CO	2	0

States

By people per tax return

	People per tax return	Days of 90°F or hotter
Highest
Utah	2	28.1
Idaho	2	10.3
Oklahoma	2	80.1
Texas	2	118
Arkansas	2	63.5
Lowest
Rhode Island	2	0.396
Vermont	2	0.566
Massachusetts	2	3.43
Maine	2	1.16
New Hampshire	2	1.69

By days of 90°F or hotter

	People per tax return	Days of 90°F or hotter
Highest
Texas	2	118
Louisiana	2	114
Florida	2	105
Arizona	2	90.2
Mississippi	2	89
Lowest
Rhode Island	2	0.396
Vermont	2	0.566
New York	2	0.947
Maine	2	1.16
New Hampshire	2	1.69

Metro areas

By people per tax return

	People per tax return	Days of 90°F or hotter
Highest
Andrews, TX	2	115
Provo-Orem-Lehi, UT	2	29.2
Vernal, UT	2	16
Eagle Pass, TX	2	163
Blackfoot, ID	2	12
Lowest
Nantucket, MA	2	0
Breckenridge, CO	2	0
Vineyard Haven, MA	2	0
Barnstable Town, MA	2	0
Taos, NM	2	0

By days of 90°F or hotter

	People per tax return	Days of 90°F or hotter
Highest
Rio Grande City-Roma, TX	2	196
Zapata, TX	2	192
McAllen-Edinburg-Mission, TX	2	189
Alice, TX	2	178
Yuma, AZ	2	176
Lowest
Youngstown-Warren, OH	2	0
Wooster, OH	2	0
Wheeling, WV-OH	2	0
Waynesville, NC	2	0
Watertown-Fort Drum, NY	2	0

Counties furthest from the pattern

Compared with the straight line that best fits all 3,108 counties: the five with far more days of 90°F or hotter than their people per tax return would suggest, and the five with far less.

	People per tax return	Days of 90°F or hotter
Above the line
Kenedy County, TX	2	158
Maricopa County, AZ	2	168
La Paz County, AZ	2	165
Brooks County, TX	2	187
Jim Hogg County, TX	2	186
Below the line
Morgan County, UT	2	0
Franklin County, ID	2	6
Duchesne County, UT	2	0
Sanpete County, UT	2	3
Rich County, UT	2	0

Two series, one county

Both measures over time for a county you pick. The two charts are stacked, so they share only the years along the bottom. You can pick from the thirty largest counties reporting both. This panel covers 2010–2024, and a measure published only once shows as a single dot.

Loading…

Every version of the link

Each row measures the same link, from −1 to +1, in a different way. If the rows mostly agree, the link does not depend on one choice of method.

Before adjusting for anything	+0.389	3,089 counties reporting both
After adjusting for density, income and education	+0.383	the part of the link that is not just how urban, rich and educated a place is
Also adjusting for population size	+0.385	size taken out as well as density
Also comparing only within each state	+0.087	each county is compared only with others in its own state, so this is no longer a comparison between states
Also holding winter sunshine equal	+0.206	compares counties that get the same sunlight in winter as well. If this is much weaker, part of the link is a difference between sunny and grey regions (more)
Giving bigger counties more weight	+0.355	the adjusted link for the average resident rather than the average county. With this weighting, the data counts for about 284 equally weighted counties
Middle value inside single states	+0.097	the link worked out inside each of 39 states with at least 20 counties reporting
Using ranks, after adjusting	+0.453	uses each county’s rank, not its value, so a few extreme counties cannot create the link

How much to believe it

Could it be chance?

The p-value is the chance of seeing a link this strong if there were really none. A value of 0.05 or less means the link is unlikely to be chance. Very small values are written in short form: 3.1e-16 means 0.00000000000000031, and the bigger the number after “e-”, the smaller the value. Treating every county as a separate case gives p = 1.8e-108. But counties in the same state tend to resemble each other, so the better figure allows for that: p = 0.002. The site tested 32,131 pairs, and testing so many turns up some flukes. The q-value allows for that too. For this pair it is 2.0e-107.

Do nearby places look alike?

Moran’s I measures how much nearby places look alike: 0 means no map pattern, and higher means neighbours are more similar. For the part of each county that the adjustment leaves unexplained, it is +0.89 (p = 0.001). That unexplained part still clusters on the map. So some regional factor shared by both measures is not accounted for.

Did they change together?

The figures above compare counties at one moment. This asks a different question: where people per tax return rose most, did days of 90°F or hottermove too? Each county’s change is compared with the average change in its own state. That takes out ups and downs that hit a whole region at once. Each change is the gap between two estimates that both contain some error. That error pulls these links towards zero, so a weak one is weak partly for that reason. The q column shows whether a link could be a fluke, allowing for the many pairs tested: 0.05 or less means it is unlikely to be chance.

Period	Counties	Change together	Within states	q
2014–2019 the main test: each Census survey figure averages five years, and these two do not overlap; before the pandemic	3,108	-0.29	-0.07	0.117
2019–2023 a repeat check: its two five-year survey figures both include 2019, and it covers the COVID years	3,108	+0.06	-0.02	0.629

Over the main period, any link between the changes could easily be chance. How change is measured.

Related pairs

Days of 90°F or hotter and Cooling degree days — +0.95
Days of 90°F or hotter and Average temperature — +0.88
Days of 90°F or hotter and Heating degree days — -0.80
Days of 90°F or hotter and Winter daily sunlight — +0.79
Freezing days and Days of 90°F or hotter — -0.74
Days of 90°F or hotter and Daily sunlight — +0.74
Days of 90°F or hotter and Winter nightly low — +0.73
Days of 90°F or hotter and Cloud cover — -0.69

Association only. Nothing here shows that either measure changes the other. This describes counties, not the people in them. Two measures going together across places does not mean the same people have both. How the US county data works · Explore People per tax return and Days of 90°F or hotter