Investigating the Cases of Novel Coronavirus Disease (Covid-19) Using Dynamic Statistical Techniques

Investigating the Cases of Novel Coronavirus Disease (Covid-19) Using Dynamic Statistical Techniques

Chapter One

Aims and Objective

The main objectives of the study is to Investigating The Cases Of Novel Coronavirus Disease (Covid-19) Using Dynamic Statistical Techniques.

The following are the specific objectives

To predict the impulse-response between confirmed cases of COVID-19 and COVID-19-attributable deaths
To investigate the relationship between COVID-19 attributable deaths and confirmed cases

CHAPTER TWO

REVIEW OF RELATED LITERATURE

CONCEPTUAL FRAMEWORK

Concept of National Policy on Education

The National Policy on Education is a policy document of the government that contains the philosophy of Nigeria education. It presents the goals, purposes and orientations of all levels and aspects of the education system (Ezema 2009). It has various sections such as philosophy of Education in Nigeria, Pre-secondary education, Secondary Education, Secondary Education, Teacher Education, Adult Education, Special Education, Educational Services, and Financing of Education (FRN, 2004).

It is an important document that contains an attractive plan for the educational system of the country. It tries as much as possible to address the needs, interest and aspirations of Nigerians. This is quite unlike the educational system of the colonial masters that failed woefully to satisfy the needs of the people. It became very irrelevant in addressing national needs, goals and the aspiration of the nation (FRN, 2004). As a result of this, there was an expression of general dissatisfaction with the system. This led to the convocation of national curriculum conference in 1969. The conference was well attended by all the segments of the society. According to Aguokogbuo (2009) the 1969 conference was well attended by people from diverse backgrounds which include trade unions, farmer’s union, women organization, religious bodies, professional organizations (medicine, Legal, Engineering etc) lecturers from higher institutions, administrations and representatives from the governments of the twelve states of Nigeria, among others.

Consequently, the conference was followed with a seminar in 1973. Experts from different fields including external bodies deliberated on what a national policy on education of Nigeria as a nation should be. A draft document was produced by the participants in the seminar. After due modifications and corrections from comments and observations from relevant and interest groups, the final document of the National Policy on Education emerged in 1977. Since the inception, it has been reviewed three times (1981, 1998 and 2004). This is the document on which the present study hinges. The study intends to find out the state of art in nursery schools using the National Policy Pre-secondary Education as a bench mark.

Overview of Coronavirus Disease

Coronavirus Disease is a contagious disease that first emerged in Wuhan, China in 2019. It was later coded “COVID-19” by the W.H.O which stands for Coronavirus Disease 2019. The Coronavirus outbreak remains one of the worst global pandemics for decades. The mortality rate soared and the easy of spread was upsetting. Research shows that older people and those with underlying medical problems like cardiovascular diseases, diabetes, chronic respiratory disease, and cancer were more likely to develop serious illnesses from coronavirus (W.H.O, 2020). Some of the symptoms of Coronavirus include; Sore throat, runny nose, constant coughing/sneezing, breathing difficulty and fatigue.

Image 1: Illustration of the Morphology of Coronaviruses; the club-shaped viral spike pelomers, coloured red, create the look of a corona surrounding the virion when observed with an electron (Wikipedia, 2020a -SARS- CoV-2 without background.png).

Data description

Data were collated from the Center for disease and control in China website. The data spans from 21 January 2020 to 20 February 2020 and were preprocessed from wide to long, a replica of panel data and time series setting. The data consist of four health indicators such as deaths, confirmed cases, suspected cases, and recovered cases across 31 Provinces/States in China namely Anhui, Beijing, Chongqing, Fujian, Gansu, Guangdong, Guangxi, Guizhou, Hainan, Hebei, Heilongjiang, Henan, Hubei, Hunan, Inner Mongolia, Jiangsu, Jiangxi, Liaoning, Jilin, Ningxia, Qinghai, Shaanxi, Shandong, Shanxi, Shanghai, Tianjin, Tibet, Sichuan, Zhejiang, Yunnan and Xinjiang. Our intial observation of data available and presented in Figure 1 shows a widespread of case-patients in Hubei Province compared to other locations (Figure 2). This validates the exact location, the city of Wuhan, where the outbreak was first reported. We observe a daily average of about 1000 confirmed cases, 60 deaths and 161 recovered cases.

CHAPTER FOUR

RESULTS AND DISCUSSION

Data Presentation And Analysis

The parameter estimation of the relationship between novel corona- virus attributable deaths and conﬁrmed cases of COVID-19 is presented in Table 1. The estimated models are statistically signiﬁcant at 5% level (95% CI) and a corresponding predictive power (R-squared) between 68%-100%. The modiﬁed wald statistic (MWALD) of Model 3 rejects the null hypothesis of homoskedasticity. Meaning that the effect of conﬁrmed cases on the novel coronavirus attributable deaths is hetero- geneous across Provinces/States in China. In both panel and time series models presented, the lagged-dependent variable (LDV) of coronavirus attributable deaths (lnDeaths_t-1) is positive and statistically signiﬁcant at 1% level except Model 5 which shows a signiﬁcant (99% CI) negative coefﬁcient. LDV was introduced in the models to control for omitted variable bias and account for the inertia effects of the reported corona- virus attributable deaths. The positive coefﬁcient of lnDeaths_t-1 in almost all the models reveals that the historical factors of coronavirus attribut- able deaths are persistent and likely to affect future reported deaths. On the contrary, when unobserved common factors affecting coronavirus attributable deaths are controlled in Model 5, the coefﬁcient on LDV turns negative. Meaning that the inertia effect of historical deaths is curtailed, hence, reducing the impact of conﬁrmed cases.

CHAPTER FIVE

CONCLUSION AND RECOMMENDATIONS

Conclusion

Our study presented is based on phenomenological models but not a clinical procedure, hence, care should be taken in the interpretation of the outcome. We demonstrated that the effect of conﬁrmed cases on COVID-19 attributable-deaths is perfectly linear whereas the impact of conﬁrmed cases on recovery cases follows a nonlinear path. Our study suffers from the limitation of early case investigation and historical data, hence, our estimation results may change at the latter stage of the novel coronavirus disease (COVID-19). In view of this, we utilized a battery of estimation approach to increase the sensitivity and robustness of the models.

Recommendations

Based on the findings, the researchers hereby recommends that:

The Minister of education should direct all secondary Schools administrators to come up with strategies to cover up the one month teaching and learning gap created as result of the COVID-19 schools closed down
The Schools administrators should ensure teachers develop strategies to cover all their scheme of work for the term before going for internal examinations
The government should provide all infrastructural facilities that will support online education in all the secondary schools in Nigeria to prevent any eventuality of future close down of schools because ofpandemic

References

WHO, Novel Coronavirus (2019-ncov) – Situation Report – 1, 2020. https://www.whHYPERLINK “https://www.who.int/docs/default-source/coronaviruse/situation-reports/20200121-sitrep-1-2019-ncov.pdf?sfvrsn=20a99c10_4” \h o.int/docs/default-source/coronaviruse/situation-reports/20200121-sitrep-1-201HYPERLINK “https://www.who.int/docs/default-source/coronaviruse/situation-reports/20200121-sitrep-1-2019-ncov.pdf?sfvrsn=20a99c10_4” \h 9-ncov.pdf?sfvrsn 20a99c10_4. (Accessed 20 February 2020).
WHO, Novel Coronavirus (2019-ncov) – Situation Report – 22, 2020. https ://www.who.int/docs/default-source/coronaviruse/situation-reports/20200211-s itrep-22-ncov.pdf?sfvrsn fb6d49b1_2. (Accessed 20 February 2020).
Q. Li, X. Guan, P. Wu, X. Wang, L. Zhou, Y. Tong, R. Ren, K.S. Leung, E.H. Lau,
J.Y. Wong, Early transmission dynamics in wuhan, China, of novelHYPERLINK “http://refhub.elsevier.com/S2405-8440(20)30592-2/sref3” \h coronavirus–infected pneumonia, N. Engl. J. Med. (2020).
C. Huang, Y. Wang, X. Li, L. Ren, J. Zhao, Y. Hu, L. Zhang, G. Fan, J. Xu, X. Gu,HYPERLINK “http://refhub.elsevier.com/S2405-8440(20)30592-2/sref4” \h Clinical features of patients infected with 2019 novel coronavirus in wuhan, China,HYPERLINK “http://refhub.elsevier.com/S2405-8440(20)30592-2/sref4” \h Lancet (2020).
N.M. Linton, T. Kobayashi, Y. Yang, K. Hayashi, A.R. Akhmetzhanov, S.-m. Jung, Yuan,R. Kinoshita, H. Nishiura, Incubation period and other epidemiologicalHYPERLINK “http://refhub.elsevier.com/S2405-8440(20)30592-2/sref5” \h characteristics of 2019 novel coronavirus infections with right truncation: aHYPERLINK “http://refhub.elsevier.com/S2405-8440(20)30592-2/sref5” \h statistical analysis of publicly available case data, J. Clin. Med. 9 (2020) 538.
S. Zhao, S.S. Musa, Q. Lin, J. Ran, G. Yang, W. Wang, Y. Lou, L. Yang, D. Gao, D. He,HYPERLINK “http://refhub.elsevier.com/S2405-8440(20)30592-2/sref6” \h Estimating the unreported number of novel coronavirus (2019-ncov) cases in ChinaHYPERLINK “http://refhub.elsevier.com/S2405-8440(20)30592-2/sref6” \h in the ﬁrst half of january 2020: a data-driven modelling analysis of the earlyHYPERLINK “http://refhub.elsevier.com/S2405-8440(20)30592-2/sref6” \h outbreak, J. Clin. Med. 9 (2020) 388.
J.C. Driscoll, A.C. Kraay, Consistent covariance matrix estimation with spatiallyHYPERLINK “http://refhub.elsevier.com/S2405-8440(20)30592-2/sref7” \h dependent panel data, Rev. Econ. Stat. 80 (1998) 549–560.
B.H. Baltagi, P.X. Wu, Unequally spaced panel data regressions with ar (1)HYPERLINK “http://refhub.elsevier.com/S2405-8440(20)30592-2/sref8” \h disturbances, Econom. Theor. 15 (1999) 814–823.
M.H. Pesaran, Estimation and inference in large heterogeneous panels with aHYPERLINK “http://refhub.elsevier.com/S2405-8440(20)30592-2/sref9” \h multifactor error structure, Econometrica 74 (2006) 967–1012.

Data description

Other Topics