Update on COVID-19 visuals for Nigeria

+++++++++++++++++++***************************+++++++++++++++++++++++++++

It is now 420 days since the first COVID-19 case was reported in Nigeria. As at April 23, 2021 the confirmed cases are 167,522 with 2,061 (1.25%) fatalities, however, 154,643 (93.93%) have recovered leaving 7,929 (4.82%) active cases.

Based on equal days forecast, by June 17, 2022, Nigeria’s aggregate confirmed COVID-19 cases are forecast to be:

Model	Confirmed cases	Recoveries	Fatalities	Active	RMSE
Without knots	3,478,739	3,267,580	43,484	167,675	195
Upper ARIMA	822,879	772,930	10,286	39,663	200
Essembled with equal weight	664,124	623,811	8,302	32,011	231
Essembled based on weight of fit	329,337	309,346	4,117	15,874	291
Essembled based on weight	50,381	47,323	630	2,428	173
Quadratic Polynomial	27,750	26,065	347	1,338	397
With knots	19,360	18,185	242	933	179
Essembled based on summed weight	-184,392	-173,200	-2,305	-8,888	178
Smooth Spline	-668,039	-627,489	-8,350	-32,199	387
Lower ARIMA	-759,095	-713,018	-9,489	-36,588	200

Refer to Table 2 and Table 3 as well as Fig. 18-20 for more details on how the estimates and forecasts were obtained.

+++++++++++++++++++***************************+++++++++++++++++++++++++++

The visuals below supports this facts, take a look!

Fig. 1a Daily observed cases of COVID-19 in Nigeria

Fig. 2 Perecentages and previous days differences of COVID-19 in Nigeria Starting from February 29, 2020 to April 23, 2021

Fig. 3 Cases recorded in percentages Starting from February 29, 2020 to April 23, 2021 (legend as Fig. 2)

Fig. 4 Cumulative cases and Forecast of COVID-19 cases in Nigeria Starting from April 23, 2021 to June 17, 2022

Fig. 4a Components of COVID-19 cases in Nigeria between February 29, 2020 and April 23, 2021

Fig. 5 Number of days since average recorded cases exceeded one in each State

Fig. 6 Daily confirmed Coronavirus cases, by number of the days since 1 first daily case recorded

Fig. 7 Number of days from February 29, 2020 to April 23, 2021 that cases were recorded in the States

Fig. 8 Number of days the last COVID19 case was recorded as at April 23, 2021

Fig. 9 Diverging Bars of COVID-19 cases in the States (normalised)

Fig. 10 Monthly summary of COVID19 cases in the States

Fig. 11 Daily recorded cases of COVID19 in the States

Fig. 12 Number of days since average recorded cases exceeded one in each geo-political zone

Fig. 13 Number of days from February 29, 2020 to April 23, 2021 that cases were recorded in the Zones

Fig. 14 Monthly summary of COVID19 cases in the Zones

Table 1 Regression estimates of factors that might have stressed Nigeria’s economy within the period of the COVID-19 pandemic

	COVID19	PMS	Inflation	Teledensity	Birth rate	Population
(Intercept)	-314.283	-1041.323	-265.706	535.259	-42.626 ****	15.902 ****
	(471.641)	(2340.704)	(301.446)	(502.257)	(7.679)	(0.367)
PMSprice	-0.183 ****		0.112 ***	0.208 ****	0.001	0.000
	(0.030)		(0.024)	(0.029)	(0.002)	(0.001)
Inflation	1.199 ***	6.366 ***		-1.137 **	-0.030 *	0.006
	(0.321)	(1.341)		(0.420)	(0.014)	(0.005)
Teledensity	0.816 ****	4.096 ****	-0.395 **		0.000	-0.003
	(0.132)	(0.571)	(0.146)		(0.010)	(0.003)
`Birth rate`	4.372	29.389	-11.533 *	0.420		0.298 ****
	(9.864)	(47.844)	(5.222)	(11.000)		(0.047)
Population	14.072	37.199	20.142	-27.346	2.752 ****
	(29.945)	(147.934)	(18.532)	(32.172)	(0.430)
COVID19		-4.380 ****	0.507 ***	0.993 ****	0.005	0.002
		(0.731)	(0.136)	(0.160)	(0.011)	(0.004)
nobs	15	15	15	15	15	15
r.squared	0.893	0.953	0.927	0.932	0.917	0.911
adj.r.squared	0.834	0.927	0.887	0.894	0.871	0.861
sigma	1.015	4.973	0.660	1.120	0.034	0.011
statistic	15.044	36.345	22.894	24.585	19.963	18.314
p.value	0.000	0.000	0.000	0.000	0.000	0.000
df	5.000	5.000	5.000	5.000	5.000	5.000
logLik	-17.682	-41.513	-11.227	-19.155	33.293	49.970
AIC	49.363	97.027	36.454	52.310	-52.586	-85.940
BIC	54.319	101.983	41.410	57.267	-47.630	-80.983
deviance	9.279	222.580	3.924	11.293	0.010	0.001
df.residual	9.000	9.000	9.000	9.000	9.000	9.000
nobs.1	15.000	15.000	15.000	15.000	15.000	15.000
**** p < 0.001; *** p < 0.01; ** p < 0.05; * p < 0.1.

Fig. 15 COVID-19, inflation, PMS price, Teledensity and birth rate in Nigeria

Fig. 15 Relationship between COVID-19, inflation, PMS price, Teledensity and birth rate in Nigeria

Table 2 The coefficient estimates of the various models for forecasting of COVID-19 for Nigeria¹

	Spline with knots	Spline without knots	ARIMA	Quardratic polynomial
(Intercept)	175.273 **	-1.620		-64.620
	(75.141)	(75.390)		(58.601)
bs(niz[, 1], knots = NULL)1	-363.578 *
	(217.172)
bs(niz[, 1], knots = NULL)2	1229.276 ****
	(137.965)
bs(niz[, 1], knots = NULL)3	30.650
	(118.597)
bs(niz[, 1], knots = BREAKS)1		-1.182
		(145.742)
bs(niz[, 1], knots = BREAKS)2		19.175
		(94.409)
bs(niz[, 1], knots = BREAKS)3		833.097 ****
		(108.223)
bs(niz[, 1], knots = BREAKS)4		184.336 **
		(91.938)
bs(niz[, 1], knots = BREAKS)5		169.340 *
		(100.662)
bs(niz[, 1], knots = BREAKS)6		-27.596
		(94.671)
bs(niz[, 1], knots = BREAKS)7		2698.340 ****
		(115.095)
bs(niz[, 1], knots = BREAKS)8		-904.006 ****
		(117.355)
bs(niz[, 1], knots = BREAKS)9		319.098 ***
		(101.601)
ar1			1.005
			(0.103)
ar2			-0.303
			(0.059)
ma1			-1.651
			(0.095)
ma2			0.754
			(0.076)
Day				4.202 ****
				(0.643)
I(Day^2)				-0.007 ****
				(0.001)
nobs	420	420	419	420
r.squared	0.203	0.797		0.159
adj.r.squared	0.197	0.792		0.155
sigma	388.426	197.615	201.131	398.419
statistic	35.326	178.516		39.561
p.value	0.000	0.000		0.000
df	3.000	9.000		2.000
logLik	-3098.028	-2811.148	-2815.425	-3109.201
AIC	6206.056	5644.297	5640.851	6226.402
BIC	6226.257	5688.739	5661.040	6242.563
deviance	62763909.877	16011186.663		66193747.337
df.residual	416.000	410.000		417.000
nobs.1	420.000	420.000	419.000	420.000
**** p < 0.001; *** p < 0.01; ** p < 0.05; * p < 0.1.

Table 3 Various selection criteria for the estimated models²

	Spline with knots	Spline without knots	Smooth spline	ARIMA	Quardratic polynomial
Absolute Error	124348	44377	37554	43099	119583
Absolute Percent Error	Inf	Inf	Inf	Inf	Inf
Accuracy	0	0	0	0	0
Adjusted R Square	0.2	0.79	0	0	0.16
Akaike’s Information Criterion AIC	6206	5644	0	5641	6226
Allen’s Prediction Sum-Of-Squares (PRESS, P-Square)	0	0	0	0	0.15
Area under the ROC curve (AUC)	0.2	0.05	0.01	0.02	0.01
Average Precision at k	0	0	0	0	0
Bias	0	0	0	0.52	0
Brier score	149438	38122	32102	39972	157604
Classification Error	1	1	1	1	1
F1 Score	0	0	0	0	0
fScore	0	0	0	0	0
GINI Coefficient	1	1	1	1	1
kappa statistic	0	0	0	0	0
Log Loss	Inf	Inf	Inf	Inf	Inf
Mallow’s cp	4	10	0	0	3
Matthews Correlation Coefficient	0	0	0	0	0
Mean Log Loss	Inf	Inf	Inf	Inf	Inf
Mean Absolute Error	296	106	89	103	285
Mean Absolute Percent Error	Inf	Inf	Inf	Inf	Inf
Mean Average Precision at k	0	0	0	0	0
Mean Absolute Scaled Error	2.5	0.89	0.75	0.86	2.4
Median Absolute Error	260	59	40	52	250
Mean Squared Error	149438	38122	32102	39972	157604
Mean Squared Log Error	2.4	NaN	0.18	0.18	NaN
Model turning point error	215	202	197	273	216
Negative Predictive Value	0	0	0	0	0
Percent Bias	-Inf	NaN	NaN	NaN	NaN
Positive Predictive Value	0	0	0	0	0
Precision	NaN	NaN	NaN	NaN	NaN
R Square	0.2	0.8	0	0	0.16
Relative Absolute Error	0.94	0.33	0.28	0.32	0.9
Recall	164	-1.3	-0.16	0.5	-40
Root Mean Squared Error	387	195	179	200	397
Root Mean Squared Log Error	1.5	NaN	0.42	0.43	NaN
Root Relative Squared Error	0.89	0.45	0.41	0.46	0.92
Relative Squared Error	0.8	0.2	0.17	0.21	0.84
Schwarz’s Bayesian criterion BIC	6226	5689	0	5661	6243
Sensitivity	0	0	0	0	0
specificity	0	0	0	0	0
Squared Error	62763910	16011187	13483043	16788341	66193747
Squared Log Error	990	NaN	74	77	NaN
Symmetric Mean Absolute Percentage Error	0.87	0.47	0.34	0.38	0.81
Sum of Squared Errors	62763910	16011187	13483043	16788341	66193747
True negative rate	0	0	0	0	0
True positive rate	0	0	0	0	0

Fig. 18 Models of COVID-19 Cases using ensemble technology

Fig. 19 Equal duration forecast of COVID-19 Cases from the ensemble models using a native plotting method

Fig. 20 Forecast of COVID-19 cases in Nigeria Starting from April 23, 2021 to June 17, 2022 using a more advaced plotting method

Fig. 20a Lagged forecasts (1-14 days) of COVID-19 cases in Nigeria

Table 4 Summary of the dynamic COVID-19 forecasts

Model	Apr 10, 21 - May 20, 22	Apr 17, 21 - Jun 03, 22	Apr 20, 21 - Jun 09, 22	Apr 21, 21 - Jun 11, 22	Apr 22, 21 - Jun 13, 22	Apr 23, 21 - Jun 15, 22
Without knots	-241075	-474037	-565413	-589428	-616302	-640268
Smooth Spline	2306377	2945009	3156764	3267424	3341193	3429841
With knots	-152203	-108785	-158406	18928	31322	111174
Quadratic Polynomial	214041	117047	76552	65116	52518	40804
Lower ARIMA	-734418	-750904	-758481	-752286	-755388	-752463
Upper ARIMA	796130	805475	809195	818575	819182	825966
Essembled with equal weight	343924	488383	447601	536767	647700	654879
Essembled based on weight	249673	253691	260932	262296	263825	265313
Essembled based on summed weight	128540	77550	56952	49094	44578	37184
Essembled based on weight of fit	203918	249155	216266	265712	326761	326908

Table 3 RMSE of the models in the dynamic forecasts

Model	Apr 10, 21 - May 20, 22	Apr 17, 21 - Jun 03, 22	Apr 20, 21 - Jun 09, 22	Apr 21, 21 - Jun 11, 22	Apr 22, 21 - Jun 13, 22	Apr 23, 21 - Jun 15, 22
Without knots	390.48	389.09	388.16	387.75	387.37	386.95
Smooth Spline	194.52	194.42	194.76	194.74	194.88	194.97
With knots	182.11	180.48	179.94	179.75	179.38	179.35
Quadratic Polynomial	395.24	396.85	397.19	397.09	397.08	396.98
Lower ARIMA	203.3	201.58	200.86	200.63	200.39	200.16
Upper ARIMA	203.3	201.58	200.86	200.63	200.39	200.16
Essembled with equal weight	233.11	232.05	231.62	231.41	231.21	231.05
Essembled based on weight	453.25	451.52	450.92	450.6	450.38	450.13
Essembled based on summed weight	451.94	448.76	447.36	446.8	446.3	445.75
Essembled based on weight of fit	210.54	209.08	209.14	209.15	209.23	209.33

Fig. 21 Percentage of COVID19 cases that resulted into casualty per State as at April 23, 2021

Fig. 22 Percentage of COVID19 cases that recovered per State as at April 23, 2021

Fig. 23 Percentage of recoveries and deaths from COVID19 cases per Zone as at April 23, 2021

Fig. 24 Distribution of COVID19 in the States as at April 23, 2021

---

1. Note that Smooth spline does not estimate coefficients and other model-characteristic statistics↩︎

2. Multiclass Area Under the Curve (MAUC) is the mean of the various AUC estimated from the same data↩︎