Table 5 Estimates and p-values for each predictor, test period #1.

From: Forecasting the spread of COVID-19 based on policy, vaccination, and Omicron data

Predictor (Model)

New cases

Deaths

ICU patients

Raw

Smoothed

Raw

Smoothed

Raw

Smoothed

Estimate

Pr( >|t|)

Estimate

Pr( >|t|)

Estimate

Pr( >|t|)

Estimate

Pr( >|t|)

Estimate

Pr( >|t|)

Estimate

Pr( >|t|)

Intercept

− 0.66790

3.50e− 05*

− 0.90356

6.04e− 05*

− 0.27847

0.0374*

− 0.91120

1.64e-05*

− 1.15828

1.32e-06*

− 1.56572

1.46e− 09*

BiLSTM

0.28847

9.70e− 06*

0.24581

0.01585*

0.11603

0.0402*

0.37717

0.000110*

0.56921

2.70e-07*

0.73186

1.31e− 11*

GAM

0.36787

1.10e− 08*

0.37328

0.00021*

0.11500

0.0361*

0.32542

0.000677*

0.49300

7.68e-06*

0.90331

1.89e− 15*

lightGBM

0.04372

0.4724

− 0.04826

0.61800

− 0.08473

0.1164

0.21973

0.017149*

0.02571

0.806

0.47151

4.12e− 06*

Extended SEIR

0.40807

1.99e− 10*

0.54506

5.96e− 08*

0.42644

1.64e-13*

0.93339

 < 2e-16*

–

–

–

–

TSGLM

0.14249

0.0208*

0.24966

0.01104*

0.04311

0.4264

0.49576

2.10e-07*

0.52226

1.95e-06*

0.90945

8.25e-16*

  1. ARIMA model is given as the baseline model. The asterisk * indicates that we can reject the null hypothesis at a significance level = 0.05.
Back to article page