Bus80017 Impact Of Covid -19 Answers


  • Internal Code :
  • Subject Code : BUS80017
  • University : swinbourneSwinburne University of Technology
  • Subject Name : Quantitative Research Methods

Quantitative Research Methods

1.Introduction to Quantitative Research Methods

The Covid 19 pandemic has hit the global economy and it reflected that the healthcare system preparedness is one of the important factors that impacted the spread of COVID 19 infections. In the current study, relationship will be assessed between the preparedness of healthcare systems of different countries and growth of infections in the economies. The secondary data has been collected regarding the number and growth of infections in different economies. The quality of the heath care systems has been assessed through WHO SPRAR preparedness metrics.

2.Research Purpose of Quantitative Research Methods 

The purpose of the research is to find the relationship between Healthcare system preparedness and number of infections reported related to COVID 19 in the economies. The findings of the study will prove to be helpful in finding out the varied capacities of the economies to handle the pandemic crisis which will further help the economies in getting prepared for any such crisis in the future.

3.Data Sources

In order to conduct a quality study, it becomes important for the researcher to collect quality data for further ensuring the quality of the analysis undertook in the study. Secondary data has been collected from authentic sources including World Bank, EU Centre and WHO SPAR data in order to retrieve authentic data for ensuring the quality of the research findings.

4.Data Analysis

Data regarding various dependent and independent variables was collected. The independent variables like Healthcare systems readiness, economic development and Compliance to safety measures and restrictions were used in the analysis conducted in the current study. Dependent variables like total infections and total causalities were used in the analysis performed in the current study. The dimensions of the dependent variable were to inspect the capacity to prevent, detect, and respond to the on-going risk of COVID infection across the global world.

5.Research Methods of Quantitative Research Methods

In order to analyse the relationship between the dependent and the independent variable included in the analysis conducted, cluster analysis was undertaken. Data of 157 countries was included in the analysis conducted. In cluster analysis, the Ward’s method and Euclidian distance metric was used in order to undertake hierarchical cluster analysis. This analysis was based on four indicators including Prevent, Detect, Respond and Function.

The idea of using cluster analysis was to measure the distance or difference between the economies in terms of the mentioned indicators. The results collected will help in understanding the readiness of different 157 countries included in the analysis.

6.Data Findings

6.1Cluster Analysis

The cluster analysis divides the countries into clusters on the basis of similarity between the countries. Under K means clustering, the entire analysis will be first performed using three clusters, then four and then 5 clusters.

The 157 countries were first divided into three clusters. On the basis of % change in the number of infections in every stage in the countries, ranking was computed for the indicators including Prevent, Detect, Respond, Enable and Membership. The cluster solution table indicated that the Readiness cluster mean of the first cluster was equivalent to 84.7, the Readiness cluster mean of the second cluster was equivalent to 36.5 and the Readiness cluster mean of the third cluster was equivalent to 60.2. Box plot analysis was undertaken in order to detect the presence of outliers between the data of the three countries. It can be evaluated that the box of the first cluster is plotted at the highest position on the prevent graph which indicates that the first cluster is able to better prevent itself from the risk of COVID infection as compared to the second and third cluster. In the detect box plot, a similar finding is retrieved in which the first cluster is plotted above the second and the third cluster. Similarly, the same finding was retrieved when the clusters were plotted on the respond and enable graphs. Therefore, from the readiness graph it could be understood that the cluster analysis divided the countries into three clusters wherein which the countries were clustered in hierarchical manner in terms of their performance indicators including Prevent, Detect, Respond and Function.

After performing the cluster analysis on 3 groups, the cluster analysis was performed using four clusters. In the analysis, the readiness cluster mean of the first cluster was equivalent to 90.1, the readiness cluster mean of the first cluster was equivalent to 71.8, the readiness cluster mean of the third cluster was equivalent to 32.9 and the readiness cluster mean of the fourth cluster was equivalent to 53.2. In the second stage, the boxplot diagram was again computed in order to detect the presence of outliers in the data of four clusters. In the second box plot, the countries are divided into four clusters. It can be evaluated from the second box plot that the first cluster is plotted well above the other clusters in the graph of the prevent indicator. The second best performing cluster is the second cluster which indicates that the countries in the second cluster are able to prevent the risk of COVID infections effectively after the first cluster. However, out of all the clusters the third cluster consists of the countries that are unable to prevent the risk of COVID infections. A similar pattern can be understood from the other indicators including Detect, Respond and Function.

After performing the cluster analysis with 4 clusters, the cluster analysis solution was retrieved of countries divided into 5 clusters. The cluster solution table indicated that the Readiness cluster mean of the first cluster was equivalent to 91.4, the Readiness cluster mean of the second cluster was equivalent to 64.1 and the Readiness cluster mean of the third cluster was equivalent to 48.5, the Readiness cluster mean of the fourth cluster was equivalent to 32.2 and the Readiness cluster mean of the fifth cluster was equivalent to 77.7. Therefore, it can be interpreted that the first cluster has the highest Readiness Cluster Mean.

Box plot analysis was undertaken in order to detect the presence of outliers between the data of the three countries. It can be evaluated that the box of the first cluster is plotted at the highest position on the prevent graph which indicates that the first cluster is able to better prevent itself from the risk of COVID infection as compared to other clusters. In the detect box plot, a similar finding is retrieved in which the first cluster is plotted above the other clusters. Similarly, the same finding was retrieved when the clusters were plotted on the respond and enable graphs. The second best performing cluster is the fifth cluster which indicates that the countries in the fifth cluster are able to prevent the risk of COVID infections effectively after the first cluster. However, out of all the clusters the fourth cluster consists of the countries that are unable to prevent the risk of COVID infections. A similar pattern can be understood from the other indicators including Detect, Respond and Function. Therefore, from the readiness graph it could be understood that the cluster analysis divided the countries into five clusters wherein which the countries were clustered in hierarchical manner in terms of their performance indicators including Prevent, Detect, Respond and Function.

6.2Descriptive Statistics

Group comparisons are done for n = 154 observations, since observations with missing data on cases numbers(3 cases) have been removed. Descriptive statistics of the WHO SPAR indicators have been calculated for 3 cluster solution, 4 cluster solution and 5 cluster solution.

6.3 Cluster Analysis

In the analysis, for the 3 cluster solution, the prevention capacity mean of the first cluster was equivalent to 83.1385, the preventive capacity mean of the second cluster was equivalent to 31.8621 and the preventive capacity of the third cluster was equivalent to 54.3333. Therefore, it could be understood that the first cluster was taking more preventive measures to stop the spread of infections on comparison to the other two clusters. The preventive capacity standard deviation of second cluster was equivalent to 9.9417. This variation was the highest among all the three clusters. The detection capacity mean of first cluster was equivalent to 87.6923. This was the highest mean followed by the third cluster mean. Again, the detection capacity standard deviation of second cluster was the highest among all the three clusters. The response capacity mean of first cluster was equivalent to 83.1831 and the response capacity standard deviation was equivalent to 12.05364. This was the highest mean and standard deviation among all the three clusters. The enabling capacity mean and readiness mean of the first cluster was 85.8462 and 85.0662, which was the highest among all. Also, the difference between groups and within groups was statistically significant. Thus, we can say that first cluster was performing better in terms of the performance indicators including Prevent, Detect, Respond and Function.

6.4 Cluster Analysis

In the analysis, for the 4 cluster solution, the preventive capacity mean of the first, second, third and fourth cluster were equivalent to 88.7179, 66.6154, 28.60 and 48.6512 respectively. The detection capacity mean of first, second, third and fourth cluster were equivalent 92.9923, 79.4865, 45 and 68.5256 respectively. The response detection capacity mean of first, second, third and fourth cluster were equivalent to 90.6872, 65.4961, 26.665 and 43.9535 respectively.The enabling capacity mean of first, second, third and fourth cluster were equivalent to 90.67, 74.67, 30 and 51.87 respectively. The readiness mean of the first, second, third and fourth cluster were equivalent to 90.6051, 71.8961, 32.94 and 53.2 respectively. Also, the differences between the groups were statistically significant. Therefore, the performance indicators in terms of Prevent, Detect, Response, Enable and Function shows that cluster one was performing relatively better followed by the second and then fourth cluster. The preventive capacity, detection capacity and response capacity standard deviation shows that the second cluster has high level of variability.

6.5 Cluster Analysis

However, for the 5 cluster solution, the results were a little different. The preventive capacity mean of the first, second, third, fourth and fifth cluster were equivalent to 89.29, 56.78, 43.58, 28.67 and 76.37 respectively. The detection capacity mean of first, second, third, fourth and fifth cluster were equivalent to 93.73, 76.26, 66.66, 42.59 and 81.04 respectively. The response capacity mean of first, second, third, fourth and fifth cluster were equivalent to 92.16, 55.67, 39.42, 26.29 and 72.60 respectively. The enabling capacity mean of first, second, third, fourth and fifth cluster were equivalent to 91.64, 66.9, 45.10, 29.33 and 79.5 respectively. The readiness capacity mean of the first, second, third, fourth and fifth cluster were equivalent to 91.44, 64.08, 48.34, 32.22 and 77.88 respectively. Therefore, we conclude that the performance indicators in terms of Prevent, Detect, Response, Enable and Function shows that first cluster performs best, followed by the fifth cluster.

Cluster analysis

In order to find the difference between the groups of countries, Anova analysis was conducted. One way analysis was conducted in order to compute the difference between and within the groups. The indicators based on which the difference between the groups was computed included prevention capacity, detection capacity, response capacity, enabling capacity and readiness. The results of the one way ANOVA statistics depicted that the significance value of all indicators was equivalent to 0.000. The significance value is less than 0.05, therefore it can be evaluated that there exists significant difference between and within the clusters when compared on the basis of given clusters.

cluster analysis

After conducting the one way ANOVA analysis on three clusters, the analysis was conducted using 4 clusters. The results of the one way ANOVA statistics depicted that the significance value of all indicators was equivalent to 0.000. The significance value is less than 0.05, therefore it can be evaluated that there exists significant difference between and within the clusters when compared on the basis of given clusters. Therefore, it can be evaluated that one way anova analysis depicted that there existed difference between and within the groups even when the countries were divided into three or four clusters.

cluster analysis

After conducting the one way ANOVA analysis on five clusters, the analysis was conducted using 5 clusters. The results of the one way ANOVA statistics depicted that the significance value of all indicators was equivalent to 0.000. The significance value is less than 0.05, therefore it can be evaluated that there exists significant difference between and within the clusters when compared on the basis of given clusters. Therefore, it can be evaluated that one way anova analysis depicted that there existed difference between and within the groups even when the countries were divided into three, four and then five clusters.

Outcome variables

The preventive, detective and responsive ability of the countries had an impact on the total number of COVID cases in the countries. Descriptive statistics and one way anova table was computed in order to find the difference between the countries in terms of total number of COVID cases among the clusters of countries.

Descriptive Statistics

All the 154 countries were divided into three clusters. The first cluster consisted of 65 countries, the second cluster consisted of 29 countries and the third cluster consisted of 60 countries. The average of total number of COVID 19 cases of cluster 1 is equivalent to 1.64, while the average of the total number of COVID 19 cases of cluster 2 is equivalent to 0.21, the average of total number of COVID cases in the third cluster is equivalent to 0.46. Therefore, it can be evaluated that the cluster 1 has the highest number of average number of COVID 19 cases.

The averages of total number of COVID 19 casualties were also computed for all the clusters. The average casualty cases of cluster 1 was equivalent to 0.07, the average casualty cases of cluster 2 was equivalent to 0.004 and the average casualty cases of cluster 3 was equivalent to. 0.016. Therefore, it can be evaluated that cluster 1 had the highest number of COVID 19 casualties as compared to the other clusters.

Anova Analayis

Anova analysis was also computed in order to find out whether significant difference existed within the clusters in terms of total number of COVID cases and casualties experienced by the countries grouped together as clusters. According to the results retrieved from ANOVA analysis, it could be retrieved that computed value was less than the critical value of 0.05 and thus it could be evaluated that there existed significant difference between the clusters in terms of total number of COVID cases experienced by each cluster.

cluster analysis

In the four cluster analysis, the first cluster consisted of 39 countries, the second cluster consisted of 52 countries, the third cluster consisted of 20 countries and fourth cluster consisted of 43 countries. The average of the total number of COVID 19 cases of first cluster is equivalent to 2.158, average of the total number of COVID 19 cases of second cluster is equivalent to 0.74, the average of the total number of COVID 19 cases of third cluster is equivalent to 0.27and the average of the total number of COVID 19 cases of fourth cluster is equivalent to 0.28. Therefore, it could be evaluated that the cluster 1 has the highest number of COVID 19 cases in the cluster 1 as compared to the other clusters included in the analysis.

Regression Model

Y = β0 + β1X + β2X

COVID cases and casualties = β0 + β1 Healthcare systems + β2Readiness Indicators

The value of the R square is equivalent to 0.201 which depicts that the independent variable is only able to define 20% changes in the dependent variable. The beta coefficient of preventive capacity is equivalent to .008 which indicates that one unit increase in the prevention capacity will increase the total number of COVID cases by .008 units. The beta coefficient of detection capacity is equivalent to .005 which indicates that one unit increase in the prevention capacity will increase the total number of COVID cases by .005 units. The beta coefficient of response capacity is equivalent to .011 which indicates that one unit increase in the prevention capacity will increase the total number of COVID cases by .011 units. The beta coefficient of enabling capacity is equivalent to -0.10 which indicates that one unit increase in the enabling capacity will decrease the total number of COVID cases by 0.10 units. However, the p value for all the beta coefficients is greater than 0.05 which indicates that the analysis conducted is not significant enough.

Conclusion on Quantitative Research Methods 

It can be evaluated from the analysis conducted above that the health care readiness of the countries cannot explain the difference in the total number of cases in the countries. There are many other factors that are not encountered in the current study that impact the number of COVID casualties and infections dealt by the countries.

Remember, at the center of any academic work, lies clarity and evidence. Should you need further assistance, do look up to our Quantitative Research Methods Assignment Help


Book Online Sessions for Bus80017 Impact Of Covid -19 Answers Online

Submit Your Assignment Here