COVID-19 short-term forecasts

Peak increase in estimated trend of Deaths in Europe 2020-09-21

	UK	EU	AT	BE	BG	BS	CZ	DE	DK	ES	FI	FR	GR	HR	HU	IE	IT	NL	PL	PT	RO	SE	NO	CH
Peak date	04-10	04-06	04-06	04-15	08-29	04-11	--	04-15	04-04	03-31	04-21	04-08	--	--	04-19	04-24	03-29	04-04	04-25	04-15	08-23	04-12	04-07	04-06
Peak daily increment	964	3095	20	328	9	7		226	15	946	30	943			13	167	781	153	23	31	44	98	8	60
Days from 100 to peak	23	33	7	22	107	0		22	3	18	1	23			6	21	25	15	19	17	143	18	-2	14
Days from peak/2 to peak	17	23	16	21	155	22		22	15	14	20	18			26	22	20	16	31	23	149	21	20	19
Last total	41788	144370	767	9950	765	275	522	9390	640	30663	341	31174	344	253	686	1792	35724	6281	2298	1920	4458	5865	267	2050
Last daily increment	11	359	1	2	4	0	19	0	2	168	2	89	6	5	3	0	17	2	5	8	23	0	0	5
Last week	124	1713	10	20	29	0	46	23	7	659	2	336	31	23	40	5	91	23	71	45	222	14	2	22
Days since peak	164	168	168	159	23	163		159	170	174	153	166			155	150	176	170	149	159	29	162	167	168

Peak increase in estimated trend of Deaths 2020-09-21

	Australia	Brazil	Canada	Chile	Colombia	India	Indonesia	Iran	Mexico	Peru	Philippines	Russia	South Africa	Turkey	US	US-AL	US-AR	US-AZ	US-CA	US-CO	US-CT	US-DC	US-DE	US-FL	US-GA	US-IA	US-ID	US-IL	US-IN	US-KS	US-KY	US-LA	US-MA	US-MD	US-MI	US-MN	US-MO	US-MS	US-NC	US-NE	US-NH	US-NJ	US-NM	US-NV	US-NY	US-OH	US-OK	US-OR	US-PA	US-SC	US-SD	US-TN	US-TX	US-UT	US-VA	US-WA	US-WI	US-WV
Peak date	09-03	07-21	05-06	07-17	08-21	06-16	--	07-27	06-24	07-23	09-14	05-29	07-22	04-15	04-13	09-16	09-15	07-21	08-06	04-24	04-20	04-29	06-23	08-07	08-22	05-21	09-09	05-12	05-02	--	04-14	04-14	04-25	04-29	04-14	05-28	09-05	08-26	--	05-20	05-29	06-25	05-13	08-19	05-18	08-29	08-22	07-28	05-05	07-28	--	08-21	07-27	04-17	04-22	04-06	04-11	04-23
Peak daily increment	35	1065	168	785	340	1662		214	683	2947	154	171	323	125	2226	91	135	78	138	72	105	11	46	175	67	14	15	112	99		10	64	459	56	137	23	25	31		40	25	1566	9	19	3573	92	10	5	137	45		27	386	6	104	25	12	16
Days from 100 to peak	108	115	36	93	131	72		144	79	107	166	48	84	18	28	156	122	100	131	21	18	10	60	127	144	27	60	41	28		0	17	23	22	17	41	149	135		0	17	85	16	129	59	147	131	89	32	103		131	115	-45	7	15	2	-89
Days from peak/2 to peak	157	106	37	63	124	52		144	72	78	168	49	76	20	19	163	136	108	133	27	20	30	74	127	147	50	160	44	32		19	21	20	27	18	56	160	148		30	31	81	41	145	49	151	149	131	33	119		143	111	18	11	30	18	4
Last total	854	137272	9279	12298	24397	88935	9677	24478	73697	31369	4999	19420	15992	7574	199865	2439	1197	5477	15056	2018	4494	621	627	13317	6450	1284	447	8457	3287	601	1112	5207	9311	3873	6901	1969	1732	2810	3247	450	438	16069	851	1531	33073	4623	948	529	7985	3212	202	2203	15127	365	3019	2044	1244	315
Last daily increment	3	377	12	12	189	1053	124	177	204	0	15	71	39	68	356	2	16	2	40	4	2	1	6	21	2	19	4	7	6	6	1	9	7	3	12	4	9	0	4	8	0	2	2	0	2	8	2	3	25	13	0	14	39	1	6	12	2	1
Last week	30	4153	40	258	1109	6869	712	1025	2019	557	336	697	351	388	4084	186	47	134	462	22	9	5	9	530	198	50	24	125	52	44	38	99	92	39	47	42	75	76	136	14	0	26	21	49	52	117	36	10	125	114	18	108	534	4	182	33	24	32
Days since peak	18	62	138	66	31	97		56	89	60	7	115	61	159	161	5	6	62	46	150	154	145	90	45	30	123	12	132	142		160	160	149	145	160	116	16	26		124	115	88	131	33	126	23	30	55	139	55		31	56	157	152	168	163	151

Deaths count forecast Europe (bold red line in graphs) 2020-09-22 to 2020-09-28

Date	UK	EU	BE	BG	CZ	DE	ES	FR	GR	HR	HU	IT	NL	PL	PT	RO	CH
2020-09-21	41788	144370	9950	765	522	9390	30663	31174	344	253	686	35724	6281	2298	1920	4458	2050
2020-09-22	41790	144500	9950	779	537	9396	30730	31200	348	256	692	35740	6281	2310	1928	4494	2053
2020-09-23	41790	144600	9950	782	551	9403	30790	31230	351	259	697	35750	6282	2321	1935	4531	2055
2020-09-24	41790	144700	9950	789	564	9405	30850	31250	355	262	702	35760	6286	2336	1942	4566	2057
2020-09-25	41790	144800	9950	793	578	9412	30910	31280	358	265	708	35770	6291	2348	1949	4602	2060
2020-09-26	41790	144900	9950	796	591	9414	30970	31310	362	268	713	35780	6293	2358	1956	4637	2062
2020-09-27	41790	145000	9950	800	604	9415	31020	31330	365	271	718	35790	6296	2368	1963	4673	2064
2020-09-28	41790	145100	9950	804	617	9416	31070	31360	369	274	724	35800	6297	2375	1969	4709	2067

Deaths count forecast (bold red line in graphs) 2020-09-22 to 2020-09-28

Date	Australia	Brazil	Canada	Chile	Colombia	India	Indonesia	Iran	Mexico	Peru	Philippines	Russia	South Africa	Turkey	US	US-AL	US-AR	US-AZ	US-CA	US-CO	US-FL	US-GA	US-IA	US-ID	US-IL	US-IN	US-KS	US-KY	US-LA	US-MA	US-MD	US-MI	US-MN	US-MO	US-MS	US-NC	US-NJ	US-NM	US-NV	US-NY	US-OH	US-OK	US-PA	US-SC	US-TN	US-TX	US-VA	US-WA	US-WI	US-WV
2020-09-21	854	137272	9279	12298	24397	88935	9677	24478	73697	31369	4999	19420	15992	7574	199865	2439	1197	5477	15056	2018	13317	6450	1284	447	8457	3287	601	1112	5207	9311	3873	6901	1969	1732	2810	3247	16069	851	1531	33073	4623	948	7985	3212	2203	15127	3019	2044	1244	315
2020-09-22	860	138200	9284	12370	24600	89980	9780	24640	74550	31480	5050	19510	16060	7633	200900	2446	1209	5491	15220	2021	13450	6532	1290	449	8471	3302	608	1126	5239	9324	3878	6901	1973	1747	2838	3284	16080	854	1548	33080	4667	956	7985	3246	2242	15310	3022	2050	1255	319
2020-09-23	866	139200	9289	12390	24790	91000	9890	24800	74850	31600	5104	19640	16130	7691	201800	2476	1219	5511	15320	2028	13600	6551	1302	452	8502	3315	615	1135	5254	9337	3883	6901	1980	1762	2860	3322	16090	857	1561	33100	4707	966	7993	3276	2266	15420	3024	2055	1263	324
2020-09-24	871	139900	9293	12480	24990	92020	9990	24960	75100	31710	5158	19770	16200	7748	202600	2486	1229	5542	15420	2032	13750	6599	1305	454	8525	3321	621	1147	5270	9350	3889	6901	1990	1775	2880	3350	16100	860	1574	33110	4736	973	8005	3299	2288	15490	3028	2061	1267	328
2020-09-25	877	140700	9298	12540	25190	93040	10090	25120	75610	31820	5213	19880	16270	7805	203500	2496	1238	5573	15520	2036	13870	6648	1318	456	8545	3335	628	1155	5296	9364	3894	6902	1998	1789	2889	3375	16110	864	1586	33120	4763	982	8028	3323	2317	15630	3031	2066	1273	332
2020-09-26	882	141300	9303	12590	25390	94050	10190	25280	76020	31930	5268	20000	16340	7861	204100	2511	1247	5590	15620	2043	13930	6696	1319	458	8566	3346	635	1162	5296	9378	3899	6904	2008	1802	2899	3403	16110	867	1592	33130	4777	986	8041	3336	2340	15720	3033	2072	1277	336
2020-09-27	888	141600	9308	12630	25590	95070	10290	25430	76180	32050	5323	20070	16410	7918	204300	2511	1255	5596	15620	2045	13930	6705	1319	460	8576	3348	642	1164	5322	9393	3904	6905	2012	1816	2900	3406	16120	870	1592	33150	4777	988	8053	3345	2345	15750	3036	2077	1278	340
2020-09-28	893	142000	9312	12660	25790	96100	10400	25590	76340	32160	5378	20130	16480	7975	204600	2516	1264	5598	15650	2047	13950	6710	1332	462	8582	3353	649	1165	5332	9407	3909	6907	2015	1829	2900	3410	16130	873	1594	33160	4787	989	8076	3358	2356	15800	3038	2083	1280	345

Deaths count average forecast Europe (bold black line in graphs) 2020-09-22 to 2020-09-28

Date	UK	EU	BE	BG	CZ	DE	ES	FR	GR	HR	HU	IT	NL	PL	PT	RO	CH
2020-09-21	41788	144370	9950	765	522	9390	30663	31174	344	253	686	35724	6281	2298	1920	4458	2050
2020-09-22	41800	144500	9952	771	527	9396	30700	31190	345	255	691	35730	6281	2310	1923	4490	2051
2020-09-23	41820	144700	9954	775	532	9403	30750	31230	347	259	696	35740	6282	2321	1927	4525	2053
2020-09-24	41830	144900	9956	781	540	9405	30820	31260	351	261	702	35750	6285	2334	1931	4561	2056
2020-09-25	41850	145100	9959	786	548	9412	30880	31290	354	265	707	35760	6290	2346	1937	4596	2058
2020-09-26	41860	145300	9962	790	557	9414	30940	31330	358	268	712	35770	6291	2357	1942	4632	2060
2020-09-27	41870	145500	9965	795	565	9416	31000	31360	361	272	718	35780	6293	2366	1947	4667	2062
2020-09-28	41880	145700	9966	802	572	9417	31070	31400	365	275	723	35790	6293	2375	1952	4703	2065

Deaths count average forecast (bold black line in graphs) 2020-09-22 to 2020-09-28

Date	Australia	Brazil	Canada	Chile	Colombia	India	Indonesia	Iran	Mexico	Peru	Philippines	Russia	South Africa	Turkey	US	US-AL	US-AR	US-AZ	US-CA	US-CO	US-FL	US-GA	US-IA	US-ID	US-IL	US-IN	US-KS	US-KY	US-LA	US-MA	US-MD	US-MI	US-MN	US-MO	US-MS	US-NC	US-NJ	US-NM	US-NV	US-NY	US-OH	US-OK	US-PA	US-SC	US-TN	US-TX	US-VA	US-WA	US-WI	US-WV
2020-09-21	854	137272	9279	12298	24397	88935	9677	24478	73697	31369	4999	19420	15992	7574	199865	2439	1197	5477	15056	2018	13317	6450	1284	447	8457	3287	601	1112	5207	9311	3873	6901	1969	1732	2810	3247	16069	851	1531	33073	4623	948	7985	3212	2203	15127	3019	2044	1244	315
2020-09-22	856	138000	9280	12330	24520	90030	9760	24550	74200	31470	5054	19510	16040	7627	200600	2449	1211	5487	15170	2020	13420	6479	1286	450	8472	3303	607	1118	5226	9320	3877	6908	1973	1740	2827	3281	16070	853	1543	33080	4663	952	7987	3226	2222	15230	3033	2046	1250	318
2020-09-23	860	138900	9282	12370	24670	91150	9880	24650	74520	31600	5125	19620	16110	7686	201400	2473	1222	5507	15280	2024	13560	6506	1295	454	8500	3316	615	1127	5242	9333	3882	6915	1980	1750	2852	3317	16080	856	1555	33090	4697	960	7993	3253	2246	15350	3052	2051	1258	323
2020-09-24	863	139600	9286	12440	24820	92280	9990	24750	74770	31740	5197	19740	16170	7746	202000	2486	1231	5531	15390	2027	13710	6550	1299	458	8523	3322	623	1137	5259	9346	3888	6923	1990	1760	2873	3345	16080	859	1568	33090	4724	968	8002	3275	2271	15420	3071	2057	1262	328
2020-09-25	867	140400	9290	12490	24990	93410	10100	24850	75260	31870	5269	19850	16230	7806	202600	2498	1240	5554	15490	2031	13830	6594	1310	461	8543	3337	631	1145	5281	9359	3893	6931	1999	1770	2884	3372	16090	862	1580	33100	4752	975	8022	3298	2296	15560	3090	2061	1268	332
2020-09-26	871	141000	9294	12550	25220	94550	10200	24950	75830	32010	5342	19960	16300	7866	203100	2513	1252	5573	15590	2035	13910	6635	1313	464	8563	3348	639	1153	5291	9372	3898	6939	2008	1780	2897	3400	16090	865	1588	33110	4759	982	8033	3316	2321	15660	3109	2064	1275	337
2020-09-27	874	141500	9298	12600	25390	95720	10300	25050	76020	32140	5417	20050	16360	7926	203300	2523	1264	5586	15600	2037	13930	6667	1317	468	8576	3351	648	1159	5315	9385	3903	6947	2015	1790	2903	3411	16100	868	1592	33120	4761	987	8041	3334	2344	15730	3128	2068	1277	341
2020-09-28	878	142000	9303	12660	25540	96890	10410	25150	76280	32260	5492	20120	16430	7987	203500	2533	1275	5594	15650	2039	13970	6690	1323	471	8584	3354	656	1165	5331	9398	3908	6955	2019	1801	2909	3423	16100	871	1596	33130	4765	991	8057	3351	2367	15780	3148	2071	1278	346

Deaths count scenario forecast (bold purple line in graphs) 2020-09-22 to 2020-09-30

Date	UK	EU	BE	BG	CZ	DE	ES	FR	GR	HR	HU	IT	NL	PL	PT	RO	CH	Australia	Brazil	Canada	Chile	Colombia	India	Indonesia	Iran	Mexico	Peru	Philippines	Russia	South Africa	Turkey	US	US-AL	US-AR	US-AZ	US-CA	US-CO	US-FL	US-GA	US-IA	US-ID	US-IL	US-IN	US-KS	US-KY	US-LA	US-MA	US-MD	US-MI	US-MN	US-MO	US-MS	US-NC	US-NJ	US-NM	US-NV	US-NY	US-OH	US-OK	US-PA	US-SC	US-TN	US-TX	US-VA	US-WA	US-WI	US-WV
2020-09-21	41788	144370	9950	765	522	9390	30663	31174	344	253	686	35724	6281	2298	1920	4458	2050	854	137272	9279	12298	24397	88935	9677	24478	73697	31369	4999	19420	15992	7574	199865	2439	1197	5477	15056	2018	13317	6450	1284	447	8457	3287	601	1112	5207	9311	3873	6901	1969	1732	2810	3247	16069	851	1531	33073	4623	948	7985	3212	2203	15127	3019	2044	1244	315
2020-09-22	41810	144500	9950	770	527	9396	30660	31180	346	255	693	35730	6284	2311	1926	4501	2051	859	138300	9281	12370	24550	90040	9760	24610	74350	31580	5125	19510	16080	7622	201000	2475	1213	5502	15190	2022	13470	6513	1286	449	8482	3299	611	1125	5233	9330	3880	6902	1978	1739	2837	3283	16070	854	1549	33080	4649	959	7998	3237	2233	15270	3043	2049	1250	321
2020-09-23	41840	144700	9950	774	534	9400	30660	31220	348	258	700	35730	6286	2326	1936	4528	2053	860	139000	9289	12410	24680	91140	9880	24750	74690	31680	5199	19590	16140	7680	201600	2517	1229	5518	15270	2025	13540	6541	1292	451	8505	3309	620	1133	5253	9347	3884	6904	1984	1747	2849	3314	16080	857	1557	33090	4670	964	8018	3252	2251	15350	3122	2053	1255	327
2020-09-24	41860	144900	9950	778	541	9404	30660	31270	352	261	706	35740	6289	2336	1947	4559	2056	860	139600	9297	12450	24820	92180	9990	24910	75030	31760	5273	19670	16190	7730	202200	2542	1234	5536	15340	2027	13610	6569	1295	453	8525	3321	627	1140	5274	9367	3888	6905	1990	1754	2862	3327	16080	859	1563	33100	4689	971	8042	3269	2268	15430	3173	2059	1259	332
2020-09-25	41870	145100	9950	782	547	9410	30680	31310	356	264	710	35750	6292	2347	1957	4586	2057	861	140300	9307	12490	24950	93150	10090	25030	75420	31830	5339	19720	16250	7781	202700	2577	1244	5555	15400	2030	13670	6592	1297	454	8547	3330	636	1147	5292	9394	3891	6905	1994	1760	2874	3355	16080	861	1570	33100	4707	976	8067	3285	2291	15500	3228	2063	1261	340
2020-09-26	41910	145300	9950	785	553	9414	30680	31360	359	268	714	35770	6294	2361	1969	4608	2058	861	140900	9318	12530	25060	94060	10180	25140	75800	31900	5406	19790	16300	7835	203100	2606	1255	5574	15460	2031	13730	6615	1300	456	8571	3339	644	1153	5310	9421	3896	6905	1999	1767	2883	3377	16080	864	1576	33110	4722	981	8101	3298	2304	15580	3348	2068	1264	348
2020-09-27	41930	145500	9950	789	560	9420	30680	31400	362	270	718	35770	6296	2371	1980	4633	2059	861	141500	9330	12560	25170	94850	10280	25250	76190	31960	5467	19830	16340	7882	203600	2635	1263	5591	15520	2032	13780	6640	1301	458	8595	3349	653	1166	5328	9444	3900	6905	2003	1773	2894	3402	16080	865	1582	33120	4740	985	8132	3312	2321	15640	3437	2071	1267	357
2020-09-28	41960	145600	9950	793	567	9424	30680	31450	365	273	723	35780	6298	2383	1992	4653	2061	861	142000	9341	12600	25280	95710	10350	25330	76530	32020	5530	19870	16380	7929	204100	2666	1271	5608	15570	2035	13830	6659	1301	459	8626	3352	660	1175	5356	9476	3903	6905	2007	1778	2902	3422	16080	866	1588	33130	4757	989	8160	3323	2335	15700	3501	2075	1269	367
2020-09-29	41980	145800	9950	795	572	9429	30680	31480	368	275	727	35780	6299	2388	2005	4672	2061	861	142500	9355	12640	25370	96420	10440	25410	76870	32090	5580	19920	16430	7980	204400	2691	1284	5623	15610	2036	13870	6678	1304	461	8657	3360	668	1184	5375	9506	3904	6905	2010	1783	2910	3437	16080	866	1593	33140	4770	992	8189	3335	2349	15750	3562	2079	1272	383
2020-09-30	42000	145900	9950	798	577	9434	30680	31510	370	278	730	35790	6301	2394	2017	4687	2061	861	143200	9368	12670	25460	97120	10530	25500	77240	32160	5630	19960	16460	8031	204900	2720	1292	5639	15660	2037	13900	6696	1305	463	8687	3369	675	1194	5380	9539	3904	6905	2013	1788	2918	3450	16080	866	1598	33150	4784	995	8218	3347	2358	15810	3628	2083	1275	398

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.

Recent changes and notes

[2020-07-01] Modified the short-term model to allow for (slowly changing) seasonality. Many countries show clear seasonality after the initial period, likely caused by institutional factors regarding data collection. This seasonality was also getting in the way of peak detection. As a consequence estimates of the peak date may have changed for countries with strong seasonality.
Added forecasts of cumulative confirmed cases for lower tier local authorities of England. The data is available from 2020-07-02 including all tests (pillar one and two). Only authorities with more than 5 cases in the previous week are included.
[2020-06-29] Tables in April included the world, but not the world as we know it (double counting China and the US). So removed the world from those old tables.
Why short-term forecasts can be better than models for predicting how pandemics evolve just appeared at The Conversation.
Thursday 2 July webinar at the FGV EESP - São Paolo School of Economics. This starts at 16:00 UK time (UTC+01:00) and streamed here.
[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.
[2020-06-06] Removed Brazil from yesterday's forecasts (only; last observation 2020-06-05).
[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.
[2020-05-20] Problem with UK confirmed cases: negative daily count. This makes the forecasts temporarily unreliable.
Updated the second paper.
[2020-05-18] Minor fixes to the improved version of scenario forecasting, backported to 2020-05-13.
[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.
[2020-05-06] 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.
[2020-04-29] 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.
[2020-04-27] 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.
[2020-04-24] A summary of our work on short-term COVID-19 forecasting appeared as a voxeu.
[2020-04-17] Bird and Nielsen look into nowcasting death counts in England.
[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).
[2020-04-10] Updated documentation with better description of short-term estimates and peak determination.
[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.
[2020-04-08] Minor correction to peak estimates. Added table with scenario forecasts.
[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.
[2020-04-02] Now including more US States, based on New York Times data.
[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).
[2020-03-26] Scenario forecasts that are based on what happened in China earlier this year, only for Italy.
[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.

COVID-19 short-term forecasts Deaths 2020-09-21

General information