Discriminant analysis

This study goes about to analyze the consequences of the coronavirus on human livelihood. Door to door survey has been done to collect local people's responses. To find out the effect of coronavirus on human livelihood discriminant analysis has been done and Pearson’s correlation analysis has been accomplished. For fulfillment of the objective of this study, 13 mouzas (small administrative units in India) and 1 census town have been selected as study units along the banks of river Kharkhari. The outcome of this study shows that the coronavirus pandemic impacted the reduction in the income level of people in the selected study units. People of villages were less affected by coronavirus than the people of towns. However, the effect of this pandemic is not less in villages and it has a considerable effect on income, education and health of people. There is a negative and significant correlation (r=-0.718, at 99 percent level of confidence) between COVID symptoms/affected and reduction in income level. The result of discriminant analysis reveals that the leading independent variable is a reduction in income level as it has the highest value (2.234) in the standardized canonical function coefficient table. A considerable number of school dropouts has been observed after the lockdown due to this pandemic. Field survey reveals that people are still in fear regarding a reduction in income level due to this pandemic.

This study is to identify the potential of tourism in areas that According to weaknesses of usual methods, the Discriminant analysis approach was used for this purpose. A method for combining the independent variables, to create a new variable that can be obtained using different variations. In order to have criteria for comparison, six another tourism regional information, entered in the analysis and differences between study areas examined. The dependent variable of this study is the planar variable of regions, in both tourist attraction areas and areas with tourism potential have been diagnosed. This method shows combines two or more independent variables that best explain the difference between two or more groups. The results showed that 25 variables of 33 study variables have no significant effect in attracting tourists and rate of them in control areas and areas of study were identical. Also, the 53.414 for detection indicator (between 0 to 100) was estimated tourist areas and areas with potential for tourism that is obtained from 8 variables of the notification, Reputation, awareness of people from regional, tourism service availability, quality of access reads, the route map existence, access to water for washing and access to drinking water. As results, four of the five target area has the potential for tourism.