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

It is now 799 days since the first COVID-19 case was reported in Nigeria. As at May 07, 2022 the confirmed cases are 260,015 with 3,143 (1.23%) fatalities, an average of 4 fatalities per day. However, to date, 249,891 or 97.72% were successfully managed and discharged leaving a balance of 2,682 (1.05%) active cases being managed.

Based on equal days forecast, by July 14, 2024, Nigeria’s aggregate confirmed COVID-19 cases are forecast to be:

Unconstrained forecast of COVID-19 for Nigeria

Model Confirmed cases Recoveries Fatalities Active RMSE
With knots 10,872,880 10,624,979 133,736 114,165 212
Upper ARIMA 877,576 857,568 10,794 9,215 181
Semilog 298,547 291,740 3,672 3,135 181
Linear 189,466 185,146 2,330 1,989 405
Essembled based on weight of fit 146,357 143,020 1,800 1,537 1.8
Essembled with equal weight 122,436 119,645 1,506 1,286 306
Smooth Spline 33,922 33,148 417 356 212
Growth 2,935 2,868 36 31 262
Essembled based on summed weight -21,889 -21,390 -269 -230 421
Essembled based on weight -58,550 -57,215 -720 -615 421
Without knots -133,356 -130,315 -1,640 -1,400 406
Lower ARIMA -424,560 -414,880 -5,222 -4,458 175
Quadratic Polynomial -606,107 -592,287 -7,455 -6,364 254

Constrained forecast of COVID-19 for Nigeria

Model Confirmed cases Recoveries Fatalities Active
Essembled based on weight of fit 95% 2,555,175 2,496,917 31,429 26,829
ARIMA 95% 2,537,069 2,479,224 31,206 26,639
Essembled with equal weight 95% 2,536,024 2,478,202 31,193 26,628
Essembled based on weight 95% 2,147,601 2,098,635 26,415 22,550
Without knots 95% 1,297,296 1,267,717 15,957 13,622
Essembled based on summed weight 95% 879,220 859,174 10,814 9,232
Semilog 298,547 291,740 3,672 3,135
Linear 189,466 185,146 2,330 1,989
With knots 95% 113,593 111,003 1,397 1,193
Smooth Spline 95% 103,490 101,131 1,273 1,087
Smooth Spline 80% 76,867 75,115 945 807
Essembled based on weight of fit 80% 16,211 15,841 199 170
Essembled with equal weight 80% 15,039 14,697 185 158
Growth 2,935 2,868 36 31
Without knots 80% 940 918 12 10
Quadratic Polynomial 80% 533 521 7 6
Quadratic Polynomial 95% 565 552 7 6
ARIMA 80% 473 462 6 5
Essembled based on weight 80% 50 48 1 1
With knots 80% 3 3 0 0
Essembled based on summed weight 80% 1 1 0 0

However, the actual forecast made by the various models on the last day i.e. July 14, 2024 is shown below:

Unconstrained forecasts on the last day

Constrained forecasts on the last day

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. 1b COVID-19 cases and deaths in the omicron wave in Nigeria

Notes COVID-19 omicron wave - between November 16 and May 07, 2022 . That is 17.59% of total or 264 cases per day. The all time cases per day is 342 . The mortality in the omicron wave is 6.077% of the total or 1 deaths per day. The all time deaths per day is 4 .

Fig. 2 Perecentages and previous days differences of COVID-19 in Nigeria Starting from February 29, 2020 to May 07, 2022

Fig. 3 Cases recorded in percentages Starting from February 29, 2020 to May 07, 2022 (legend as Fig. 2)

Fig. 4 Cumulative cases and Forecast of COVID-19 cases in Nigeria Starting from May 08, 2022 to July 14, 2024

Fig. 4a Components of COVID-19 cases in Nigeria between February 29, 2020 and May 07, 2022

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 May 07, 2022 that cases were recorded in the States

Fig. 7a Numbers of States that COVID-19 cases were reported on daily basis

Fig. 7b Forecast of Numbers of States that may still be COVID-19 affected by July 14, 2024

Coefficient estimates for number of states reporting COVID-19 daily

LinearSemilogGrowthSpline without knotsLinear splinesSpline with knotsARIMA
(Intercept)0.563 ****15.397 ****2.632 ****8.982 ****2.842 *   -0.892          
(0.069)    (1.288)    (0.044)    (0.781)    (1.544)    (2.378)         
Series-0.002 ****         -0.001 ****                                
(0.000)             (0.000)                                    
log(Series)         -0.484 **                                           
         (0.226)                                             
bs(Series, knots = NULL)1                           19.567 ****                       
                           (2.256)                           
bs(Series, knots = NULL)2                           -5.533 ****                       
                           (1.430)                           
bs(Series, knots = NULL)3                           0.777                            
                           (1.234)                           
bs(DDPtable$Series, knots = LBREAKS)1                                    -2.787                   
                                    (2.203)                  
bs(DDPtable$Series, knots = LBREAKS)2                                    13.778 ****              
                                    (1.634)                  
bs(DDPtable$Series, knots = LBREAKS)3                                    22.696 ****              
                                    (1.907)                  
bs(DDPtable$Series, knots = LBREAKS)4                                    -0.727                   
                                    (1.693)                  
bs(DDPtable$Series, knots = LBREAKS)5                                    28.932 ****              
                                    (1.743)                  
bs(DDPtable$Series, knots = LBREAKS)6                                    -3.106 *                 
                                    (1.717)                  
bs(DDPtable$Series, knots = LBREAKS)7                                    3.207 *                 
                                    (1.740)                  
bs(DDPtable$Series, knots = LBREAKS)8                                    19.503 ****              
                                    (1.777)                  
bs(DDPtable$Series, knots = LBREAKS)9                                    0.431                   
                                    (1.799)                  
bs(DDPtable$Series, knots = LBREAKS)10                                    17.269 ****              
                                    (1.944)                  
bs(DDPtable$Series, knots = LBREAKS)11                                    -2.701                   
                                    (2.079)                  
bs(DDPtable$Series, knots = LBREAKS)12                                    3.333 *                 
                                    (1.877)                  
bs(Series, knots = QBREAKS)1                                             7.526 **       
                                             (2.928)         
bs(Series, knots = QBREAKS)2                                             22.138 ****     
                                             (2.510)         
bs(Series, knots = QBREAKS)3                                             17.576 ****     
                                             (2.843)         
bs(Series, knots = QBREAKS)4                                             12.636 ****     
                                             (2.536)         
bs(Series, knots = QBREAKS)5                                             9.649 ****     
                                             (2.609)         
bs(Series, knots = QBREAKS)6                                             16.298 ****     
                                             (2.744)         
bs(Series, knots = QBREAKS)7                                             8.807 ***      
                                             (2.974)         
bs(Series, knots = QBREAKS)8                                             4.779 *        
                                             (2.749)         
ma1                                                      -0.772 
                                                      (0.022)
nobs744         744         744         744         744         744         743     
r.squared0.105     0.006     0.053     0.223     0.749     0.351          
adj.r.squared0.104     0.005     0.051     0.219     0.745     0.344          
sigma0.946     6.044     0.598     5.353     3.061     4.906     3.152 
statistic87.427     4.589     41.115     70.596     181.609     49.757          
p.value0.000     0.033     0.000     0.000     0.000     0.000          
df1.000     1.000     1.000     3.000     12.000     8.000          
logLik-1013.754     -2393.153     -672.553     -2301.817     -1881.491     -2234.445     -1907.184 
AIC2033.508     4792.307     1351.106     4613.634     3790.982     4488.889     3818.368 
BIC2047.345     4806.143     1364.943     4636.694     3855.550     4535.010     3827.590 
deviance664.683     27102.255     265.630     21201.865     6849.527     17689.661          
df.residual742.000     742.000     742.000     740.000     731.000     735.000          
nobs.1744.000     744.000     744.000     744.000     744.000     744.000     743.000 
**** p < 0.001; *** p < 0.01; ** p < 0.05; * p < 0.1.

Properties of the estimated coefficients

Linear Semilog Growth Spline with knots Linear splines Spline without knots Smooth spline ARIMA
Absolute Error 9400 3800 7700 3000 1700 3400 1500 1800
Absolute Percent Error 750 560 560 350 200 460 170 190
Accuracy 0 0 0 0 0 0 0 0
Adjusted R Square 0.1 0.0048 0.051 0.34 0.74 0.22 0 0
Akaike’s Information Criterion AIC 2000 4800 1400 4500 3800 4600 0 3800
Allen’s Prediction Sum-Of-Squares (PRESS, P-Square) 0 0 0 0 0 0 0 0
Area under the ROC curve (AUC) 0 0 0 0 0 0 0 0
Average Precision at k 0 0 0 0 0 0 0 0
Bias 13 0.00000000000000058 10 0.000000000000000079 -0.000000000000000022 0.00000000000000064 -0.0000000000000042 0.022
Brier score 200 40 100 20 9 30 8 10
Classification Error 1 1 1 1 1 1 1 1
F1 Score 0 0 0 0 0 0 0 0
fScore 0 0 0 0 0 0 0 0
GINI Coefficient 0.3 0.3 0.3 0.6 0.9 0.4 0.9 0.9
kappa statistic 0 0 0 0 0 0 0 0
Log Loss Inf Inf Inf Inf Inf Inf Inf Inf
Mallow’s cp 4 4 4 4 4 4 NaN 4
Matthews Correlation Coefficient 0 0 0 0 0 0 0 0
Mean Log Loss 180 -400 -400 -400 -400 -400 -400 -400
Mean Absolute Error 13 5 10 4 2.3 4.5 2.1 2.4
Mean Absolute Percent Error 1 0.75 0.76 0.47 0.26 0.62 0.23 0.26
Mean Average Precision at k 0 0 0 0 0 0 0.12 0
Mean Absolute Scaled Error 4.4 1.8 3.6 1.4 0.81 1.6 0.72 0.83
Median Absolute Error 13 4.6 10 3.5 1.8 4.4 1.6 1.9
Mean Squared Error 200 36 140 24 9.2 28 7.8 9.9
Mean Squared Log Error 6.8 0.3 1.9 0.18 0.077 0.24 0.059 0.075
Model turning point error 442 442 442 423 416 420 414 552
Negative Predictive Value 0 0 0 0 0 0 0 0
Percent Bias 1 -0.5 0.72 -0.25 -0.1 -0.38 -0.09 -0.089
Positive Predictive Value 0 0 0 0 0 0 0 0
Precision 1 1 1 1 1 1 1 1
R Square 0.11 0.0061 0.053 0.35 0.75 0.22 0 0
Relative Absolute Error 2.5 0.99 2 0.78 0.45 0.88 0.41 0.46
Recall 0.86 1 1 0.71 1 1 1 1
Root Mean Squared Error 14 6 12 4.9 3 5.3 2.8 3.1
Root Mean Squared Log Error 2.6 0.55 1.4 0.43 0.28 0.49 0.24 0.27
Root Relative Squared Error 2.3 1 2 0.81 0.5 0.88 0.46 0.52
Relative Squared Error 5.4 0.99 3.9 0.65 0.25 0.78 0.21 0.27
Schwarz’s Bayesian criterion BIC 2000 4800 1400 4500 3900 4600 0 3800
Sensitivity 0 0 0 0 0 0 0 0
specificity 0 0 0 0 0 0 0 0
Squared Error 150000 27000 110000 18000 6800 21000 5800 7400
Squared Log Error 5100 220 1400 140 57 180 44 56
Symmetric Mean Absolute Percentage Error 1.9 0.43 1.2 0.35 0.23 0.4 0.2 0.22
Sum of Squared Errors 150000 27000 110000 18000 6800 21000 5800 7400
True negative rate 0 0 0 0 0 0 0 0
True positive rate 0 0 0 0 0 0 0 0

Fig. 8 Number of days the last COVID19 case was recorded as at May 07, 2022

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 May 07, 2022 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

COVID19PMSInflationTeledensityBirth ratePopulation
(Intercept)-244.389    185.820    -668.711 *** 570.883    -35.692 ****15.816 ****
(388.057)   (4153.269)   (205.324)    (539.761)   (6.237)    (0.191)    
PMSprice-0.041 **         0.034 *** 0.062 ** 0.000     -0.000     
(0.018)           (0.011)    (0.025)   (0.001)    (0.000)    
Inflation0.595 *  9.392 ***         -0.588    -0.025 ****0.008 *** 
(0.309)   (2.922)            (0.455)   (0.006)    (0.002)    
Teledensity0.421 ***3.489 ** -0.120             0.002     -0.001     
(0.121)   (1.417)   (0.093)            (0.004)    (0.001)    
`Birth rate`2.588    53.904    -16.259 ****7.702             0.274 ****
(8.466)   (89.263)   (4.162)    (11.877)            (0.044)    
Population11.914    -39.456    44.323 *** -29.955    2.330 ****         
(24.586)   (262.061)   (12.637)    (34.340)   (0.373)             
COVID19        -4.559 ** 0.242 *   0.840 ***0.002     0.001     
        (2.042)   (0.126)    (0.242)   (0.005)    (0.002)    
nobs28        28        28         28        28         28         
r.squared0.466    0.498    0.731     0.457    0.700     0.724     
adj.r.squared0.345    0.383    0.670     0.333    0.631     0.661     
sigma1.756    18.632    1.121     2.482    0.044     0.015     
statistic3.841    4.358    11.966     3.699    10.251     11.534     
p.value0.012    0.007    0.000     0.014    0.000     0.000     
df5.000    5.000    5.000     5.000    5.000     5.000     
logLik-52.125    -118.251    -39.560     -61.809    51.019     80.959     
AIC118.251    250.501    93.121     137.618    -88.037     -147.917     
BIC127.576    259.827    102.446     146.943    -78.712     -138.592     
deviance67.869    7637.283    27.662     135.538    0.043     0.005     
df.residual22.000    22.000    22.000     22.000    22.000     22.000     
nobs.128.000    28.000    28.000     28.000    28.000     28.000     
**** 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

LinearSemilogGrowthSpline without knotsSpline with knotsARIMAQuardratic polynomialEssembled based on weightEssembled based on summed weight
(Intercept)369.629 ****141.996   5.372 ****36.714     -2.695          119.296 *** 45.138  1.168     
(29.876)    (87.624)  (0.127)    (57.190)    (100.832)         (43.310)    (137.461) (19.376)    
Day-0.111 *          -0.001 ****                       1.765 ****               
(0.065)           (0.000)                           (0.250)                   
log(Day)         32.245 **                                                        
         (15.179)                                                          
bs(Day, knots = NULL)1                         806.586 ****                                      
                         (165.196)                                          
bs(Day, knots = NULL)2                         269.006 **                                        
                         (104.724)                                          
bs(Day, knots = NULL)3                         80.503                                           
                         (90.340)                                          
bs(Day, knots = BREAKS)1                                  2.753                                  
                                  (194.928)                                 
bs(Day, knots = BREAKS)2                                  15.357                                  
                                  (126.270)                                 
bs(Day, knots = BREAKS)3                                  839.804 ****                             
                                  (144.746)                                 
bs(Day, knots = BREAKS)4                                  175.647                                  
                                  (122.965)                                 
bs(Day, knots = BREAKS)5                                  189.805                                  
                                  (134.624)                                 
bs(Day, knots = BREAKS)6                                  -61.956                                  
                                  (126.526)                                 
bs(Day, knots = BREAKS)7                                  1999.040 ****                             
                                  (125.354)                                 
bs(Day, knots = BREAKS)8                                  -202.046                                  
                                  (124.182)                                 
bs(Day, knots = BREAKS)9                                  -134.394                                  
                                  (125.050)                                 
bs(Day, knots = BREAKS)10                                  884.354 ****                             
                                  (126.204)                                 
bs(Day, knots = BREAKS)11                                  -177.507                                  
                                  (120.712)                                 
bs(Day, knots = BREAKS)12                                  1420.187 ****                             
                                  (135.778)                                 
bs(Day, knots = BREAKS)13                                  -1145.398 ****                             
                                  (156.741)                                 
bs(Day, knots = BREAKS)14                                  370.860 ***                              
                                  (128.262)                                 
ar1                                           0.851                         
                                           (0.079)                        
ar2                                           0.228                         
                                           (0.052)                        
ar3                                           -0.225                         
                                           (0.053)                        
ar4                                           -0.012                         
                                           (0.046)                        
ar5                                           0.132                         
                                           (0.038)                        
ma1                                           -0.543                         
                                           (0.074)                        
intercept                                           300.797                         
                                           (127.648)                        
I(Day^2)                                                -0.002 ****               
                                                (0.000)                   
fitf                                                         -1.640  -0.057     
                                                         (1.768) (0.042)    
fit0f                                                         0.488  0.001     
                                                         (0.908) (0.201)    
fit1f                                                         -1.081  1.117 ****
                                                         (4.198) (0.068)    
fitpif                                                         -0.612  -0.001     
                                                         (0.711) (0.207)    
fitaf                                                         -0.458  -0.062     
                                                         (2.606) (0.065)    
fitf:fit0f                                                         0.011           
                                                         (0.016)          
fitf:fit1f                                                         0.009           
                                                         (0.011)          
fit0f:fit1f                                                         0.010           
                                                         (0.024)          
fitf:fitpif                                                         0.002           
                                                         (0.004)          
fit0f:fitpif                                                         -0.000           
                                                         (0.002)          
fit1f:fitpif                                                         0.007           
                                                         (0.020)          
fitf:fitaf                                                         0.012           
                                                         (0.011)          
fit0f:fitaf                                                         -0.018           
                                                         (0.015)          
fit1f:fitaf                                                         -0.001           
                                                         (0.014)          
fitpif:fitaf                                                         0.014           
                                                         (0.017)          
fitf:fit0f:fit1f                                                         -0.000 *         
                                                         (0.000)          
fitf:fit0f:fitpif                                                         -0.000           
                                                         (0.000)          
fitf:fit1f:fitpif                                                         -0.000           
                                                         (0.000)          
fit0f:fit1f:fitpif                                                         -0.000           
                                                         (0.000)          
fitf:fit0f:fitaf                                                         -0.000           
                                                         (0.000)          
fitf:fit1f:fitaf                                                         -0.000           
                                                         (0.000)          
fit0f:fit1f:fitaf                                                         0.000           
                                                         (0.000)          
fitf:fitpif:fitaf                                                         -0.000           
                                                         (0.000)          
fit0f:fitpif:fitaf                                                         0.000           
                                                         (0.000)          
fit1f:fitpif:fitaf                                                         -0.000           
                                                         (0.000)          
fitf:fit0f:fit1f:fitpif                                                         0.000           
                                                         (0.000)          
fitf:fit0f:fit1f:fitaf                                                         0.000           
                                                         (0.000)          
fitf:fit0f:fitpif:fitaf                                                         0.000           
                                                         (0.000)          
fitf:fit1f:fitpif:fitaf                                                         0.000           
                                                         (0.000)          
fit0f:fit1f:fitpif:fitaf                                                         -0.000           
                                                         (0.000)          
fitf:fit0f:fit1f:fitpif:fitaf                                                         -0.000           
                                                         (0.000)          
nobs799         799       799         799         799         799     799         799      799         
r.squared0.004     0.006   0.032     0.079     0.615          0.073     0.827  0.817     
adj.r.squared0.002     0.004   0.031     0.076     0.608          0.071     0.820  0.816     
sigma421.850     421.430   1.800     406.037     264.306     213.055 407.056     179.033  181.294     
statistic2.917     4.513   26.315     22.812     89.552          31.559     118.520  707.614     
p.value0.088     0.034   0.000     0.000     0.000          0.000     0.000  0.000     
df1.000     1.000   1.000     3.000     14.000          2.000     31.000  5.000     
logLik-5962.406     -5961.609   -1602.459     -5930.876     -5582.270     -5415.036 -5933.380     -5262.272  -5285.615     
AIC11930.811     11929.219   3210.917     11871.752     11196.541     10846.072 11874.761     10590.544  10585.230     
BIC11944.861     11943.269   3224.967     11895.168     11271.475     10883.539 11893.494     10745.095  10618.014     
deviance141832019.422     141549628.226   2582.839     131068486.834     54768527.097          131892781.351     24584572.177  26063853.584     
df.residual797.000     797.000   797.000     795.000     784.000          796.000     767.000  793.000     
nobs.1799.000     799.000   799.000     799.000     799.000     799.000 799.000     799.000  799.000     
**** p < 0.001; *** p < 0.01; ** p < 0.05; * p < 0.1.

Table 3 Various selection criteria for the estimated models2

Linears Semilogs Growths Spline with knots Spline without knots Smooth spline ARIMA Quardratic polynomial Essembled equal weight Essembled on weight Essembled summed weight Essembled weight of fit
Absolute Error 230000 230000 260000 120000 210000 65000 82000 210000 260000 67000 65000 260000
Absolute Percent Error Inf Inf Inf Inf Inf Inf Inf Inf Inf Inf Inf Inf
Accuracy 0 0 0 0 0 0 0 0 0.069 0 0 0.069
Adjusted R Square 0.0024 0.0044 0.031 0.61 0.076 0 0 0.071 0 0.82 0.82 0
Akaike’s Information Criterion AIC 12000 12000 3200 11000 12000 0 11000 12000 0 11000 11000 0
Allen’s Prediction Sum-Of-Squares (PRESS, P-Square) 0 0 0 0 0 0 0 0 0 0 0 0
Area under the ROC curve (AUC) 0 0 0 0 0 0 0 0 0 0 0 0
Average Precision at k 0 0 0 0 0 0 0 0 0.5 0 0 0.5
Bias 0.0000000000000096 -0.0000000000000096 320 -0.0000000000000027 -0.000000000000026 0.000000000000004 1.1 -0.0000000000000046 330 -0.0000000000000026 -0.000000000000000043 330
Brier score 200000 200000 300000 70000 200000 30000 40000 200000 10000000 30000 30000 10000000
Classification Error 1 1 1 1 1 1 1 1 1 1 1 1
F1 Score 0 0 0 0 0 0 0 0 0 0 0 0
fScore 0 0 0 0 0 0 0 0 0 0 0 0
GINI Coefficient 0.08 -0.08 0.08 0.9 0.4 1 0.9 0.3 0.9 1 1 0.9
kappa statistic 0 0 0 0 0 0 0 0 0 0 0 0
Log Loss Inf Inf Inf Inf Inf Inf Inf Inf Inf Inf Inf Inf
Mallow’s cp 2 2 2 2 2 NaN 2 5 2 2 2 2
Matthews Correlation Coefficient 0 0 0 0 0 0 0 0 NaN 0 0 NaN
Mean Log Loss -11000 -11000 -11000 -11000 -11000 -11000 -11000 -11000 NaN -11000 -11000 NaN
Mean Absolute Error 290 290 320 140 270 81 100 270 570 84 82 550
Mean Absolute Percent Error Inf Inf Inf Inf Inf Inf Inf Inf Inf Inf Inf Inf
Mean Average Precision at k 0 0 0 0 0 0.5 0 0 0 0 0 0
Mean Absolute Scaled Error 2.5 2.5 2.8 1.3 2.3 0.71 0.9 2.3 2.8 0.73 0.71 2.8
Median Absolute Error 240 240 160 100 200 34 46 200 110 37 35 120
Mean Squared Error 180000 180000 280000 69000 160000 33000 45000 170000 12000000 31000 33000 10000000
Mean Squared Log Error 4.2 4.2 13 NaN 3.3 0.57 1.1 3.2 26 NaN NaN 26
Model turning point error 416 415 416 393 396 385 506 395 470 354 368 470
Negative Predictive Value 0 0 0 0 0 0 0 0 0 0 0 0
Percent Bias -Inf -Inf -Inf NaN -Inf NaN -Inf -Inf -Inf NaN NaN -Inf
Positive Predictive Value 0 0 0 0 0 0 0 0 0 0 0 0
Precision 0.035 0.035 0.035 0 0.035 0 0.035 0.035 0 0.024 0 0
R Square 0.0036 0.0056 0.032 0.62 0.079 0 0 0.073 0 0.83 0.82 0
Relative Absolute Error 0.99 1 1.1 0.5 0.93 0.28 0.36 0.93 0.5 0.29 0.28 0.6
Recall 1 1 1 0 1 0 1 1 0 0.5 0 0
Root Mean Squared Error 420 420 530 260 410 180 210 410 3500 180 180 3200
Root Mean Squared Log Error 2.1 2.1 3.5 NaN 1.8 0.76 1.1 1.8 5.1 NaN NaN 5.1
Root Relative Squared Error 1 1 1.3 0.62 0.96 0.43 0.5 0.96 1.3 0.42 0.43 1.3
Relative Squared Error 1 0.99 1.6 0.38 0.92 0.18 0.25 0.93 1.6 0.17 0.18 1.6
Schwarz’s Bayesian criterion BIC 12000 12000 3200 11000 12000 0 11000 12000 0 11000 11000 0
Sensitivity 0 0 0 0 0 0 0 0 1 0 0 1
specificity 0 0 0 0 0 0 0 0 0 0 0 0
Squared Error 140000000 140000000 220000000 55000000 130000000 26000000 36000000 130000000 230000000 25000000 26000000 230000000
Squared Log Error 3400 3400 10000 NaN 2600 460 880 2600 21000 NaN NaN 21000
Symmetric Mean Absolute Percentage Error 0.97 0.97 1.8 0.75 0.95 0.43 0.5 0.95 0.7 0.48 0.44 0.75
Sum of Squared Errors 140000000 140000000 220000000 55000000 130000000 26000000 36000000 130000000 230000000 25000000 26000000 230000000
True negative rate 0 0 0 0 0 0 0 0 0 0 0 0
True positive rate 0 0 0 0 0 0 0 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 Unconstrained forecast of COVID-19 cases in Nigeria Starting from May 08, 2022 to July 14, 2024 using a more advaced plotting method

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

Fig. 20b Constrained forecast of COVID-19 cases in Nigeria Starting from May 08, 2022 to July 14, 2024 using a more advaced plotting method

Fig. 20c Constrained forecast of COVID-19 cases in Nigeria Starting from May 08, 2022 to July 14, 2024 using a more advaced plotting method

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

Table 4 Summary of the unconstrained dynamic COVID-19 forecasts
Model Apr 24, 22 - Jun 16, 24 May 01, 22 - Jun 30, 24 May 04, 22 - Jul 06, 24 May 05, 22 - Jul 08, 24 May 06, 22 - Jul 10, 24 May 07, 22 - Jul 12, 24
Linear 215242 202327 196749 194869 192993 191123
Semilog 290533 288035 300489 299983 299478 286136
Growth 3236 3088 3022 2994 2967 2939
Without knots -1580 -71026 -99078 -108473 -117693 -126739
Smooth Spline 12010925 11454470 11193146 11101534 11011039 10921615
With knots -17697 66970 2506 -35653 -56120 -57286
Quadratic Polynomial -528190 -567841 -584639 -590271 -595860 -601407
Lower ARIMA -418262 -420801 -422859 -423868 -424549 -425158
Upper ARIMA 866697 872479 874464 874979 875643 876344
Essembled with equal weight 144178 157995 152125 150972 119661 139911
Essembled based on weight 513708 492484 506986 535563 538233 543809
Essembled based on summed weight 373689 398767 409449 413058 416019 419542
Essembled based on weight of fit 1248327 148184 169194 152994 153663 142494
Table 4a Summary of the dynamic COVID-19 constrained forecasts
Model Apr 24, 22 - Jun 16, 24 May 01, 22 - Jun 30, 24 May 04, 22 - Jul 06, 24 May 05, 22 - Jul 08, 24 May 06, 22 - Jul 10, 24 May 07, 22 - Jul 12, 24
Linear 215,242 202,327 196,749 194,869 192,993 191,123
Semilog 290,533 288,035 300,489 299,983 299,478 286,136
Growth 3,236 3,088 3,022 2,994 2,967 2,939
Without knots 80% 14 1,027 566 18 1 1
Without knots 95% 32,458 2,050,718 873,948 2,412,211 78,852 816,471
Smooth Spline 80% 3 3 3 3 3 3
Smooth Spline 95% 302,679 166,842 129,146 126,015 107,653 87,793
With knots 80% 107,359 86,979 84,623 80,323 66,940 76,175
With knots 95% 149,201 125,320 110,308 108,157 113,308 100,997
Quadratic Polynomial 80% 2,269 1,221 881 780 687 601
Quadratic Polynomial 95% 2,410 1,293 932 826 727 635
ARIMA 80% 458 659 519 643 440 418
ARIMA 95% 2,527,503 2,627,149 2,592,058 2,641,849 2,599,253 2,566,162
Essembled with equal weight 80% 17,952 18,743 16,577 16,416 12,529 12,177
Essembled with equal weight 95% 1,846,956 1,949,033 2,221,154 2,193,432 2,568,093 2,569,849
Essembled based on weight 80% 54,381 49,402 29,140 44,621 38,372 37,172
Essembled based on weight 95% 2,795,053 2,824,580 3,005,904 2,927,774 2,976,493 2,993,297
Essembled based on summed weight 80% 247,985 268,537 279,557 279,858 279,309 280,228
Essembled based on summed weight 95% 688,084 716,731 720,783 734,760 749,283 760,735
Essembled based on weight of fit 80% 18,534 18,644 20,068 17,841 18,845 15,656
Essembled based on weight of fit 95% 2,209,982 2,582,241 2,253,402 2,352,675 1,399,490 2,410,551

Table 3 RMSE of the models in the dynamic forecasts
Model Apr 24, 22 - Jun 16, 24 May 01, 22 - Jun 30, 24 May 04, 22 - Jul 06, 24 May 05, 22 - Jul 08, 24 May 06, 22 - Jul 10, 24 May 07, 22 - Jul 12, 24
Linear 423.36 422.36 421.92 421.78 421.64 421.49
Semilog 421.97 421.44 421.22 421.15 421.08 421.01
Growth 534.71 532.36 531.36 531.03 530.7 530.37
Without knots 408.23 406.64 405.95 405.72 405.49 405.26
Smooth Spline 259.1 260.5 261.09 261.29 261.49 261.68
With knots 177.71 180.9 182.74 179.25 176.36 176.29
Quadratic Polynomial 409.86 408.07 407.31 407.05 406.8 406.55
Lower ARIMA 213.99 213.05 212.65 212.52 212.38 212.25
Upper ARIMA 213.99 213.05 212.65 212.52 212.38 212.25
Essembled with equal weight 253.61 254.02 254.3 253.38 252.65 252.58
Essembled based on weight 482.47 485.59 487.23 487.35 487.62 488.11
Essembled based on summed weight 438.48 441.75 443.17 443.8 444.42 444.97
Essembled based on weight of fit 305.86 313.14 316.26 317.18 318.12 319.15

Fig. 21 Percentage of COVID19 cases that resulted into casualty per State as at May 07, 2022

Fig. 22 Percentage of COVID19 cases that recovered per State as at May 07, 2022

Fig. 23 Percentage of recoveries and deaths from COVID19 cases per Zone as at May 07, 2022

Fig. 24 Distribution of COVID19 in the States as at May 07, 2022

  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↩︎