Warning: This analysis contains the results of a predictive model. There are a number of assumptions made which include some speculation. Furthermore, this analysis was not prepared or reviewed by an Epidimiologist. Therefore, the assumptions and methods presented should be scrutinized carefully before arriving at any conclusions.

Summary for the United States on 2020-05-08:

Reported Case Count: 1,245,874

Predicted Case Count: 1,475,200

Percentage Underreporting in Case Count: 15.5%

COVID-19 Case Estimates, by State

Definition Of Fields:

  • Reported Cases: The number of cases reported by each state, which is a function of how many tests are positive.
  • Est Cases: The predicted number of cases, accounting for the fact that not everyone is tested.
  • Est Range: The 95% confidence interval of the predicted number of cases.
  • Ratio: Estimated Cases divided by Reported Cases.
  • Tests per Million: The number of tests administered per one million people. The less tests administered per capita, the larger the difference between reported and estimated number of cases, generally.
  • Cases per Million: The number of reported cases per on million people.
  • Positive Test Rate: The reported percentage of positive tests.
Reported Cases Est Cases Est Range Ratio Tests per Million Cases per Million Positive Test Rate
state
NY 327649 370104 (339574, 435759) 1.1 56026.6 16842.6 30%
NJ 133635 158080 (141771, 198878) 1.2 32948.9 15045.3 46%
MA 73721 84487 (77209, 103229) 1.1 51016.6 10695.8 21%
IL 70873 84075 (75111, 105362) 1.2 29912.3 5593.0 19%
CA 60614 73674 (64583, 93412) 1.2 21332.0 1534.1 7%
PA 52915 64451 (56581, 84838) 1.2 20527.1 4133.3 20%
MI 45646 55003 (48744, 69599) 1.2 24738.7 4570.6 18%
FL 38828 47236 (41473, 61975) 1.2 22951.7 1807.8 8%
TX 35390 44130 (38075, 56734) 1.2 15697.5 1220.5 8%
GA 31439 38548 (33757, 51928) 1.2 20466.6 2961.1 14%
CT 31784 37393 (33552, 45671) 1.2 32584.8 8914.9 27%
MD 29374 35480 (31504, 44911) 1.2 24579.5 4858.7 20%
LA 30652 35397 (32177, 44621) 1.2 43186.9 6593.5 15%
OH 22131 28163 (23914, 38138) 1.3 15061.8 1893.3 13%
IN 22503 27903 (24095, 37884) 1.2 18535.0 3342.6 18%
VA 21570 27345 (23392, 37485) 1.3 14428.2 2527.1 18%
CO 17830 22328 (19279, 29039) 1.3 15862.3 3096.2 20%
WA 15905 18851 (16909, 23851) 1.2 29522.8 2088.7 7%
NC 13397 16688 (14360, 21849) 1.2 16335.5 1277.4 8%
TN 14096 16520 (14879, 20111) 1.2 34605.6 2064.1 6%
IA 11059 13487 (11768, 17475) 1.2 21054.0 3505.2 17%
AZ 9945 12523 (10713, 16576) 1.3 15261.8 1366.3 9%
RI 10530 11718 (10886, 13639) 1.1 77705.3 9940.0 13%
MO 9341 11659 (10144, 15134) 1.2 16883.6 1522.0 9%
MN 9365 11611 (10109, 15464) 1.2 17274.4 1660.6 10%
WI 9215 11419 (9871, 14697) 1.2 17561.4 1582.7 9%
AL 8898 10775 (9468, 14119) 1.2 23489.4 1814.7 8%
MS 8686 10351 (9225, 13594) 1.2 27144.8 2918.5 11%
SC 6936 8694 (7518, 11651) 1.3 15048.8 1347.1 9%
NE 6771 8243 (7233, 10407) 1.2 19519.2 3500.3 18%
KS 6144 7724 (6640, 10300) 1.3 15385.2 2108.9 14%
KY 5934 7332 (6390, 9451) 1.2 17594.4 1328.2 8%
NV 5766 7262 (6186, 10049) 1.3 16673.5 1872.0 11%
DE 5939 7027 (6296, 8934) 1.2 28062.2 6099.0 22%
DC 5654 6618 (5965, 8079) 1.2 36636.3 8011.3 22%
UT 5724 6610 (6010, 8142) 1.2 41966.6 1785.4 4%
OK 4330 5248 (4627, 6806) 1.2 21958.0 1094.3 5%
NM 4291 4972 (4503, 6097) 1.2 40863.6 2046.4 5%
AR 3611 4426 (3862, 5852) 1.2 19880.4 1196.6 6%
OR 2989 3738 (3237, 4939) 1.3 16705.2 708.7 4%
SD 2905 3542 (3090, 4584) 1.2 22736.4 3283.8 14%
NH 2740 3345 (2932, 4316) 1.2 21185.4 2015.1 10%
ID 2158 2675 (2329, 3534) 1.2 17285.3 1207.6 7%
ME 1330 1658 (1445, 2205) 1.2 17424.3 989.4 6%
ND 1371 1555 (1431, 1871) 1.1 53626.9 1799.1 3%
WV 1287 1527 (1357, 1891) 1.2 32096.1 718.1 2%
VT 916 1086 (970, 1388) 1.2 29569.4 1468.0 5%
WY 631 768 (669, 1055) 1.2 20792.8 1090.3 5%
HI 626 751 (667, 953) 1.2 25101.8 442.1 2%
MT 456 562 (490, 753) 1.2 18944.1 426.7 2%
AK 374 438 (395, 543) 1.2 33273.4 511.2 2%

Appendix: Model Diagnostics

Derived relationship between Test Capacity and Case Under-reporting

Plotted is the estimated relationship between test capacity (in terms of people per test -- larger = less testing) and the likelihood a COVID-19 case is reported (lower = more under-reporting of cases).

The lines represent the posterior samples from our MCMC run (note the x-axis is plotted on a log scale). The rug plot shows the current test capacity for each state (black '|') and the capacity one week ago (cyan '+'). For comparison, South Korea's testing capacity is currently at the very left of the graph (200 people per test).

About this Analysis

This analysis was done by Joseph Richards.

This project1 uses the testing rates per state from https://covidtracking.com/, which reports case counts and mortality by state. This is used to estimate the number of unreported (untested) COVID-19 cases in each U.S. state.

The analysis makes a few assumptions:

  1. The probability that a case is reported by a state is a function of the number of tests run per person in that state. Hence the degree of under-reported cases is a function of tests run per capita.
  2. The underlying mortality rate is the same across every state.
  3. Patients take time to succumb to COVID-19, so the mortality counts today reflect the case counts 7 days ago. E.g., mortality rate = (cumulative deaths today) / (cumulative cases 7 days ago).

The model attempts to find the most likely relationship between state-wise test volume (per capita) and under-reporting, such that the true underlying mortality rates between the individual states are as similar as possible. The model simultaneously finds the most likely posterior distribution of mortality rates, the most likely true case count per state, and the test volume vs. case underreporting relationship.

  1. Full details about the model are available at: https://github.com/jwrichar/COVID19-mortality↩