COVID-19 short-term forecasts Deaths 2020-06-26


Disclaimer

  • Forecasts produced by Jennie Castle, Jurgen Doornik, and David Hendry, researchers at the University of Oxford. These are our forecasts, and should not be considered official forecasts from, or endorsed by, any of: University of Oxford, Oxford Martin School, Nuffield College, or Magdalen College.
  • These forecasts are short term time-series extrapolations of the data. They are not based on epidemiological modelling or simulations. The documentation that is provided is still in progress and not peer reviewed. All forecasts are uncertain: their success can only be determined afterwards. Many mitigation strategies are in place, which, if successful, invalidate our forecasts. An explanation of our methods is provided below.

Recent changes

[2020-03-24] Our forecasts are starting to overestimate in some cases. This was always expected to happen when the increase starts to slow down. Scenario forecasts that are based on what happened in China earlier this year, but only for Italy and Spain sofar.
[2020-03-26] Scenario forecasts that are based on what happened in China earlier this year, only for Italy.
[2020-03-31] Scenario forecasts, based on what happened in China earlier this year, are presented for several countries (line marked with x). Created more plausible 90% confidence bands (dotted line in same colour).
[2020-04-02] Now including more US States, based on New York Times data. And the world.
[2020-04-06] Added a post hoc estimate of the peak number of cases. This needs at least three confirmed observations (four for deaths) after the event. It is based on the averaged smooth trend, and can change later or be a local peak. It is marked with a vertical line with the date label, or a date with left arrow in the bottom left corner of the graph. This is backported to 2020-04-04.
[2020-04-08] Minor correction to peak estimates. Added table with scenario forecasts.
[2020-04-09] Added table with estimated peak dates (if happened) and dates to and since the peak. Note that this can be a local peak, and subsequent re-acceleration (or data revisions) can result in a new peak later.
[2020-04-10] Updated documentation with better description of short-term estimates and peak determination.
[2020-04-16] Added scenario forecasts to all graphs now. This would now be the preferred forecast for most.
This is the first time with a peak in confirmed UK cases (also for deaths, but this is uncertain because it is at the same date).
[2020-04-17] Bird and Nielsen look into nowcasting death counts in England.
[2020-04-24] A summary of our work on short-term COVID-19 forecasting appeared as a voxeu.
[2020-04-27] Our short-term COVID-19 forecasting paper is now available as Nuffield Economics Discussion Paper 2020-W06.
A small adjustment has been made to the scenario forecast methodology, and will be documented shortly.
[2020-04-29] See our blog entry at the International Institute of Forecasters.
US history of death counts revised in Johns Hopkins/CSSE data.
UK death counts have been revised to include the deaths in care homes. In the Johns Hopkins/CSSE data set, which we use, the entire history has been revised. So forecasts made up to 2020-04-29 cannot be compared to later outcomes. In the ECDC data set only the last observation has changed, causing a jump in the series.
[2020-05-06] The New York Times is in the process of redefining its US state data. Unfortunately, at the moment only the last observation has changed (e.g New York deaths jumped from 19645 on 2020-05-05 to 25956 a day later). This means the data is currently useless; however it does bring it close to the Johns Hopkins/CSSE count (25626 on 2020-05-06). The aggregate US count is based on JH/CSSE so unaffected. We now use Johns Hopkins/CSSE US state data, including all states with sufficient counts. So the new forecasts cannot be compared to those previously.
A minor change is that we show the graph without scenario forecast if no peak has been detected yet.
[2020-05-13] We now omit countries with fewer than 200 confirmed cases in the last week (25 for deaths).
The short-term paper has some small updates, including further comparisons with other models.
Data for Ecuador are not reliable enough for forecasting.
Switched to an improved version of scenario forecasting.
[2020-05-18] Minor fixes to the improved version of scenario forecasting, backported to 2020-05-13.
[2020-05-20] Problem with UK confirmed cases: negative daily count. This makes the forecasts temporarily unreliable.
Updated the second paper.
[2020-06-04] Data issues with confirmed cases for France.
Added an appendix to the short term paper with further forecast comparisons for European and Latin American countries.
Both Sweden and Iran have lost their peak in confirmed cases. For Sweden the previous peak was on 24 April (daily peak of 656 cases), for Iran it was on 31 March (peak of 3116). For Iran this looks like a second wave, with increasing daily counts for the last four weeks. For Sweden this is a sudden jump in confirmed cases in the last two days, compared to a fairly steady weekly pattern over the previous six weeks.
[2020-06-06] Removed Brazil from yesterday's forecasts (only; last observation 2020-06-05).
[2020-06-24] Research presentation on short-term COVID-19 forecasting on 26 June (14:00 UK time) at the Quarterly Forecasting Forum of the IIF UK Chapter.

Further information

  • We believe these forecasts fill a useful gap in the short run. They give an indication of what is likely to happen in the next few days, removing some aspect of surprise. Moreover, a noticeable drop in comparison to the extrapolations could be an indication that the implemented policies are having some impact. It is difficult to understand exponential growth. We hope that these forecasts may help to convince viewers to adhere to the policies implemented by their respective governments, and keep all arguments factual and measured.
  • We use the data repository for the 2019 Novel Coronavirus Visual Dashboard operated by the Johns Hopkins University Center for Systems Science and Engineering. This is updated daily, but we tend to update our forecasts only every other day.
    US state data as of 2020-03-28 is courtesy of the New York Times.
  • We can only provide forecasts of what is measured. If confirmed cases are an underestimate of actual cases, then our forecasts will also be underestimates. No other epidemiological data is used. Data definition and collection differs between countries and may change over time.
  • We will update the methodology as we learn what is happening in the next few days or weeks. Once the number of cases levels off, there is no need to provide these forecasts anymore.
  • Countries where the counts are very low or stable have been omitted.
  • The graphs have dates on the horizontal axis (yyyy-mm-dd) and cumulative counts on the vertical axis. They show
    1. bold dark grey line (with circles): observed counts (Johns Hopkins CSSE);
    2. many light grey lines (with open circles): forecasts using different model settings and starting up to four periods back;
    3. red line (with open circles): single forecasts path using default model settings;
    4. black line (with crosses): average of all forecasts, recentered on the last observation;
    5. thin green lines: some indication of uncertainty around the red forecasts, but we do not know how reliable that is.
    Both the red line forecasts and the black lines are also given in the tables above. These forecasts differ, we are currently inclined to use the average forecasts.
  • The forecasts are constructed as follows:
    1. An overall `trend' is extracted by taking a window of the data at a time. In each window we draw `straight lines' which are selected using an automatic econometric procedure (`machine learning'). All straight lines are collected and averaged, giving the trend.
    2. Forecasts are made using the estimated trend, but we note that this must be done carefully, because simply extrapolating the flexible insample trend would lead to wildly fluctuating forecast. We use the `Cardt' method, which has been found to work well in other settings.
    3. Residuals from the trend are also forecast, and combined with trend forecasts into an overall forecast.
  • Scenario forecasts are constructed very differently: smooth versions of the Chinese experience are matched at different lag lengths with the path of each country. This probably works best from the peak, or the slowdown just before (but we include it for the UK nonetheless).
  • The forecast evaluation shows past forecasts, together with the outcomes (in the grey line with circles).
  • EU-BS is Estonia, Latvia, and Lithuania together.
  • This paper describes the methodology and gives further references. Also available as Nuffield Economics Discussion Paper 2020-W06. Still preliminary is the documentation of the medium term forecasts.

Deaths count average forecast Europe (bold black line in graphs) 2020-06-27 to 2020-07-03

DateUKEUBEDEFRITPLPTROSE
2020-06-26 43414 132645 9731 8965 29705 34708 1429 1555 1579 5280
2020-06-27 43500 133000 9740 8970 29700 34700 1440 1560 1590 5290
2020-06-28 43700 133000 9750 8980 29800 34700 1450 1560 1610 5310
2020-06-29 43800 133000 9750 8990 29800 34800 1460 1570 1620 5340
2020-06-30 44000 133000 9760 9010 29800 34800 1470 1570 1640 5360
2020-07-01 44100 134000 9770 9020 29800 34800 1490 1570 1650 5390
2020-07-02 44200 134000 9780 9030 29900 34800 1500 1580 1670 5420
2020-07-03 44400 134000 9790 9040 29900 34900 1510 1580 1690 5450

Deaths count average forecast (bold black line in graphs) 2020-06-27 to 2020-07-03

DateBrazilCanadaChileColombiaIndiaIndonesiaIranMexicoPeruPhilippinesRussiaSouth AfricaTurkeyUSUS-ALUS-ARUS-AZUS-CAUS-COUS-CTUS-DEUS-FLUS-GAUS-IAUS-ILUS-INUS-KYUS-LAUS-MAUS-MDUS-MIUS-MNUS-MOUS-MSUS-NCUS-NEUS-NHUS-NJUS-NMUS-NYUS-OHUS-PAUS-SCUS-TNUS-TXUS-VAUS-WAUS-WI
2020-06-26 55961 8571 5068 2786 15685 2683 10239 25779 8939 1224 8770 2340 5065 125039 887 249 1535 5868 1673 4307 507 3366 2725 704 6847 2403 553 3077 8005 3116 6061 1411 966 1022 1348 265 365 14914 489 31342 2788 6579 694 569 2354 1700 1304 766
2020-06-27 56700 8590 5140 2830 15800 2690 10300 26700 9100 1230 8850 2400 5090 125000 900 250 1570 5910 1680 4320 510 3390 2740 710 6870 2410 550 3080 8020 3130 6070 1420 970 1030 1370 270 370 15200 490 31400 2800 6600 700 570 2370 1700 1310 770
2020-06-28 57700 8610 5240 2890 16100 2730 10400 27800 9300 1240 8970 2470 5110 126000 910 260 1600 5960 1680 4330 520 3420 2760 710 6910 2420 560 3090 8040 3140 6080 1420 980 1040 1410 270 370 15600 490 31400 2820 6620 710 580 2380 1710 1320 770
2020-06-29 58700 8640 5340 2960 16400 2770 10500 28900 9400 1260 9090 2550 5130 126000 920 260 1650 6020 1690 4340 540 3460 2770 710 6940 2430 560 3110 8070 3160 6090 1430 980 1050 1440 270 370 16100 500 31500 2840 6640 720 580 2400 1720 1320 780
2020-06-30 59600 8660 5450 3040 16700 2810 10700 30100 9600 1270 9210 2630 5150 127000 930 260 1690 6080 1690 4350 550 3490 2790 710 6980 2450 560 3120 8100 3170 6100 1440 990 1060 1470 280 380 16600 500 31500 2850 6670 720 590 2430 1730 1330 780
2020-07-01 60600 8680 5550 3110 17100 2850 10800 31300 9800 1280 9330 2720 5170 128000 940 270 1740 6140 1700 4360 560 3530 2810 710 7020 2460 570 3130 8130 3190 6110 1450 990 1070 1510 280 380 17100 510 31600 2870 6700 730 600 2450 1750 1340 790
2020-07-02 61600 8710 5660 3200 17400 2890 10900 32500 10000 1290 9450 2800 5190 129000 950 270 1780 6200 1700 4370 580 3570 2830 710 7050 2470 570 3150 8160 3200 6120 1450 1000 1090 1540 290 380 17700 510 31600 2890 6720 740 610 2480 1760 1340 790
2020-07-03 62700 8730 5800 3290 17700 2930 11000 33800 10200 1300 9580 2890 5220 129000 960 280 1830 6270 1710 4380 590 3600 2840 720 7090 2480 580 3160 8190 3220 6130 1460 1000 1100 1580 290 390 18400 510 31700 2910 6750 750 620 2500 1770 1350 800

Deaths count forecast Europe (bold red line in graphs) 2020-06-27 to 2020-07-03

DateUKEUBEDEFRITPLPTROSE
2020-06-26 43414 132645 9731 8965 29705 34708 1429 1555 1579 5280
2020-06-27 43600 133000 9740 8990 29700 34700 1440 1560 1590 5310
2020-06-28 43700 133000 9750 9000 29800 34800 1460 1560 1600 5350
2020-06-29 43800 133000 9760 9020 29800 34800 1470 1570 1620 5380
2020-06-30 44000 133000 9770 9040 29800 34800 1480 1570 1630 5410
2020-07-01 44100 133000 9770 9060 29800 34800 1500 1580 1640 5440
2020-07-02 44300 134000 9780 9080 29900 34900 1510 1580 1650 5470
2020-07-03 44400 134000 9790 9090 29900 34900 1520 1590 1660 5500

Deaths count forecast (bold red line in graphs) 2020-06-27 to 2020-07-03

DateBrazilCanadaChileColombiaIndiaIndonesiaIranMexicoPeruPhilippinesRussiaSouth AfricaTurkeyUSUS-ALUS-ARUS-AZUS-CAUS-COUS-CTUS-DEUS-FLUS-GAUS-IAUS-ILUS-INUS-KYUS-LAUS-MAUS-MDUS-MIUS-MNUS-MOUS-MSUS-NCUS-NEUS-NHUS-NJUS-NMUS-NYUS-OHUS-PAUS-SCUS-TNUS-TXUS-VAUS-WAUS-WI
2020-06-26 55961 8571 5068 2786 15685 2683 10239 25779 8939 1224 8770 2340 5065 125039 887 249 1535 5868 1673 4307 507 3366 2725 704 6847 2403 553 3077 8005 3116 6061 1411 966 1022 1348 265 365 14914 489 31342 2788 6579 694 569 2354 1700 1304 766
2020-06-27 56900 8590 5200 2860 16000 2710 10300 26800 9100 1230 8890 2410 5090 126000 900 250 1590 5930 1680 4320 510 3400 2740 710 6880 2410 560 3090 8040 3130 6070 1420 970 1030 1380 270 370 15100 490 31400 2800 6610 700 580 2380 1710 1310 770
2020-06-28 57800 8610 5320 2970 16300 2750 10500 27700 9300 1250 9010 2480 5110 126000 900 260 1640 5990 1680 4330 510 3440 2760 710 6920 2420 560 3110 8070 3150 6080 1420 980 1050 1410 270 380 15400 500 31400 2820 6630 700 590 2410 1730 1320 770
2020-06-29 58800 8620 5450 3070 16600 2790 10600 28800 9500 1260 9130 2550 5130 127000 910 260 1700 6060 1690 4340 520 3480 2780 720 6950 2430 570 3120 8100 3160 6090 1430 980 1060 1440 270 380 15800 500 31500 2830 6660 710 600 2440 1740 1320 780
2020-06-30 59700 8640 5570 3170 16900 2830 10700 29800 9700 1270 9250 2630 5150 127000 920 260 1750 6120 1690 4350 520 3520 2800 720 6990 2440 570 3140 8140 3180 6100 1430 990 1070 1470 280 390 16200 500 31500 2850 6690 710 610 2470 1760 1330 780
2020-07-01 60600 8660 5710 3280 17200 2880 10800 30900 9900 1280 9370 2710 5170 128000 930 270 1810 6180 1690 4360 530 3550 2820 720 7020 2450 570 3160 8170 3190 6110 1440 990 1080 1500 280 400 16600 510 31600 2860 6710 710 610 2500 1770 1340 780
2020-07-02 61600 8680 5840 3400 17500 2920 10900 32000 10100 1290 9490 2790 5190 128000 940 270 1870 6250 1700 4370 530 3590 2840 730 7060 2460 580 3170 8210 3210 6120 1440 1000 1090 1530 290 400 17000 510 31600 2880 6740 720 620 2520 1780 1340 790
2020-07-03 62600 8700 5980 3520 17800 2960 11000 33200 10300 1300 9610 2870 5210 129000 950 280 1930 6310 1700 4370 530 3630 2860 730 7090 2470 580 3190 8240 3220 6130 1450 1000 1100 1570 290 410 17400 510 31700 2890 6770 720 630 2550 1800 1350 790

Deaths count scenario forecast (bold purple line in graphs) 2020-06-27 to 2020-07-05

DateUKEUBEDEFRITPLPTROSEBrazilCanadaChileColombiaIndiaIndonesiaIranMexicoPeruPhilippinesRussiaSouth AfricaTurkeyUSUS-ALUS-ARUS-AZUS-CAUS-COUS-CTUS-DEUS-FLUS-GAUS-IAUS-ILUS-INUS-KYUS-LAUS-MAUS-MDUS-MIUS-MNUS-MOUS-MSUS-NCUS-NEUS-NHUS-NJUS-NMUS-NYUS-OHUS-PAUS-SCUS-TNUS-TXUS-VAUS-WAUS-WI
2020-06-26 43414 132645 9731 8965 29705 34708 1429 1555 1579 5280 55961 8571 5068 2786 15685 2683 10239 25779 8939 1224 8770 2340 5065 125039 887 249 1535 5868 1673 4307 507 3366 2725 704 6847 2403 553 3077 8005 3116 6061 1411 966 1022 1348 265 365 14914 489 31342 2788 6579 694 569 2354 1700 1304 766
2020-06-27 43500 133000 9740 8970 29700 34700 1440 1560 1590 5290 56800 8600 5140 2860 15800 2710 10300 26800 9070 1230 8870 2420 5090 125000 900 250 1570 5900 1680 4320 520 3390 2730 700 6870 2410 550 3080 8020 3130 6080 1420 970 1040 1380 270 370 15400 490 31400 2800 6600 700 580 2360 1710 1310 770
2020-06-28 43600 133000 9750 8980 29700 34700 1450 1560 1600 5300 57800 8620 5230 2960 16000 2740 10500 27600 9200 1240 8980 2510 5110 126000 910 250 1610 5950 1680 4320 550 3430 2750 710 6910 2420 560 3090 8040 3140 6090 1420 980 1050 1400 270 370 15700 500 31400 2820 6620 710 580 2380 1720 1320 780
2020-06-29 43700 133000 9760 8990 29800 34800 1450 1570 1610 5320 59000 8640 5300 3150 16300 2770 10600 28400 9340 1250 9080 2600 5130 127000 920 260 1660 5990 1680 4330 570 3460 2760 710 6930 2420 560 3100 8060 3160 6100 1430 980 1060 1410 270 370 16400 500 31500 2830 6640 720 590 2400 1740 1320 780
2020-06-30 43800 133000 9760 9000 29800 34800 1460 1570 1620 5330 60200 8650 5360 3260 16500 2810 10700 29300 9450 1260 9170 2700 5140 127000 930 260 1700 6020 1690 4340 580 3490 2770 710 6960 2430 560 3120 8090 3170 6110 1430 990 1070 1410 270 370 16800 500 31500 2850 6670 720 600 2410 1750 1330 780
2020-07-01 43900 133000 9770 9010 29800 34800 1470 1570 1630 5340 61300 8670 5420 3360 16800 2840 10700 30100 9580 1270 9300 2790 5150 128000 940 260 1750 6050 1690 4350 610 3510 2780 710 6980 2430 560 3130 8110 3180 6110 1440 990 1080 1450 270 370 17100 500 31600 2860 6690 730 610 2430 1760 1330 790
2020-07-02 44000 133000 9770 9010 29800 34800 1470 1580 1640 5350 62300 8700 5490 3430 17000 2880 10800 30900 9700 1280 9370 2900 5160 128000 950 260 1810 6080 1690 4350 620 3530 2790 710 7000 2440 570 3130 8130 3190 6120 1440 990 1090 1500 270 380 17800 510 31600 2870 6700 730 620 2440 1770 1340 790
2020-07-03 44100 133000 9780 9020 29800 34800 1480 1580 1650 5370 63300 8710 5570 3500 17200 2910 10900 31800 9800 1280 9510 3000 5180 128000 960 270 1850 6100 1700 4350 630 3550 2800 720 7020 2450 570 3140 8150 3210 6130 1450 1000 1100 1530 270 380 17800 510 31700 2880 6720 740 640 2460 1780 1350 790
2020-07-04 44200 133000 9780 9030 29900 34800 1480 1580 1660 5380 64400 8730 5640 3560 17400 2950 11000 32600 9900 1290 9670 3110 5190 129000 960 270 1900 6120 1700 4360 660 3570 2810 720 7040 2450 570 3150 8170 3220 6140 1450 1000 1110 1550 280 380 17800 510 31700 2890 6740 740 650 2480 1790 1350 800
2020-07-05 44200 133000 9780 9030 29900 34800 1490 1590 1670 5390 65400 8750 5690 3590 17500 2990 11000 33200 10000 1300 9780 3200 5200 129000 970 270 1940 6140 1700 4370 680 3580 2820 720 7060 2460 570 3160 8180 3230 6150 1450 1000 1110 1570 280 380 17800 520 31800 2900 6750 740 660 2490 1800 1360 800

Peak increase in estimated trend of Deaths in Europe 2020-06-26

UKEUATBEBGBSCZDEDKESFIFRHUIEITNLPLPTROSENOCH
Peak date04-0904-0704-0704-1006-2204-1104-0904-1504-0403-3004-2104-0704-1904-2403-2804-0704-2404-1105-0104-2204-0804-04
Peak daily increment 1019 3232 22 349 5 8 11 269 18 896 17 1028 14 101 839 159 29 33 25 120 9 61
Days from 100 to peak 22 34 8 17 38 1 0 23 3 17 1 23 6 22 24 18 18 13 29 25 -1 12
Days from peak/2 to peak 16 24 16 15 95 22 14 22 14 13 24 16 26 25 19 18 28 19 37 27 21 17
Last total 43414 132645 698 9731 215 257 349 8965 604 28338 328 29705 578 1730 34708 6103 1429 1555 1579 5280 249 1962
Last daily increment 184 197 0 5 4 0 4 25 1 8 1 25 1 3 30 3 17 6 14 50 0 4
Last week 825 801 10 35 16 2 13 70 4 16 2 137 8 15 98 14 83 27 79 171 5 6
Days since peak 78 80 80 77 4 76 78 72 83 88 66 80 68 63 90 80 63 76 56 65 79 83

Peak increase in estimated trend of Deaths 2020-06-26

BrazilCanadaChileColombiaIndiaIndonesiaIranMexicoPeruPhilippinesRussiaSouth AfricaTurkeyUSUS-ALUS-ARUS-AZUS-CAUS-COUS-CTUS-DCUS-DEUS-FLUS-GAUS-IAUS-ILUS-INUS-KSUS-KYUS-LAUS-MAUS-MDUS-MIUS-MNUS-MOUS-MSUS-NCUS-NEUS-NHUS-NJUS-NMUS-NVUS-NYUS-OHUS-OKUS-ORUS-PAUS-SCUS-TNUS-TXUS-VAUS-WAUS-WI
Peak date06-0405-0406-08 --06-1606-1503-19 --06-1404-1205-29 --04-2004-1505-0606-18 --04-2304-2404-2004-25 --05-0604-2005-2005-1304-2904-1404-1604-1404-2704-2904-2205-2805-0505-06 --05-2005-29 --05-1204-1204-0704-2904-2104-0905-0504-2904-0605-1504-2204-0605-29
Peak daily increment 1097 179 309 902 49 147 230 27 184 125 2272 17 7 87 51 115 12 54 46 16 127 50 7 11 75 221 63 151 27 19 22 23 15 10 10 1068 54 9 4 170 18 10 39 47 31 14
Days from 100 to peak 68 33 53 72 78 14 68 11 48 23 30 23 31 26 21 18 5 35 20 26 43 25 -6 1 18 26 22 25 41 26 23 0 16 15 0 18 25 8 -21 32 14 -5 41 7 14 51
Days from peak/2 to peak 59 34 47 60 87 16 67 25 48 25 21 37 79 30 28 20 26 41 25 48 44 32 18 21 21 26 26 26 55 39 38 41 31 40 18 13 31 27 21 33 34 8 50 14 30 65
Last total 55961 8571 5068 2786 15685 2683 10239 25779 8939 1224 8770 2340 5065 125039 887 249 1535 5868 1673 4307 546 507 3366 2725 704 6847 2403 264 553 3077 8005 3116 6061 1411 966 1022 1348 265 365 14914 489 498 31342 2788 377 202 6579 694 569 2354 1700 1304 766
Last daily increment 990 4 165 175 384 63 109 719 178 12 176 48 19 629 7 9 41 62 4 9 3 0 39 23 8 37 9 3 7 26 49 16 1 5 10 6 12 6 8 42 4 3 41 16 2 5 22 1 11 37 25 4 0
Last week 5985 105 773 638 2431 254 732 4998 1078 74 778 463 138 5319 59 25 190 374 26 56 15 73 222 124 23 222 57 8 29 85 188 89 47 38 31 84 133 22 26 1990 23 12 259 91 9 13 160 50 53 171 93 39 22
Days since peak 22 53 18 10 11 99 12 75 28 67 72 51 8 64 63 67 62 51 67 37 44 58 73 71 73 60 58 65 29 52 51 37 28 45 75 80 58 66 78 52 58 81 42 65 81 28

Initial visual evaluation of forecasts of Deaths