Reference no: EM132930215

Question 1.

Regression analysis is used to study the relationship between variables. An example of a real world scenario could be using regression analysis to understand how the value of a home is affected by variables such as number of bathrooms, number of bedrooms, and size. In this scenario, the dependent variable is the value of the home and the explanatory variables are the bedrooms, bathrooms, and size. I would use StatTool's Regression tool to analysis the data. The value of R-square will indicate the variation of the home value as impacted by the three variables. If the value of R-square is closer to 1, I will know there is a good measure in the value of the variable's coefficients. The coefficient output in the Regression Table will provide an estimate of how each variable will influence the home value. A positive coefficient indicates an increase in value, whereas a negative coefficient indicates a decrease. For example, if the coefficient for bathrooms is greater than bedrooms, I would consider adding a bathroom to the home to increase its value. Additional variables can be added to the analysis, such as the home's location or amenities (pool, entertainment room, etc) to determine if they have much influence on the value of homes too. I would review how these additions change the R-square and standard error of estimate values.

Question 2.

It is imperative to understand how regression is analyzed and it requires the use of both an x-axis and y-axis on a graph. Simple regression is a relationship between two variables that create a straight line on a graph (Albright and Winston, 2017). Multiple regression is identifying a relationship between two or more variables (Albright and Winston, 2017). Whether one conducts a simple regression or a multiple regression, it is important to use a graph to detect a relationship between the variables that may not be obvious without a visual aid (Albright and Winston, 2017). Based on the amount of data that is required to conduct a multiple regression, proves that it may be better than performing a simple regression which limits the management in their decision-making and making accurate predictions.

A real-world example of a simple regression would be collecting data on the correlation between crime rate and poverty level across the United States. While the data would entail all different types of crime, which would be the independent variable, the dependent variable, in this case, would be the average poverty level for the United States. To perform a multiple regression, one must collect data to ensure the analysis is as accurate as possible. An example of a multiple regression would be collecting data that encompasses more variables, such as analyzing the crime rate and poverty levels across the globe. When considering crime rates over the poverty levels globally, the data should define the specific crimes committed and determine the poverty level for each country. The information gathered can aid in tourism updates, world health organization, world education services, and many other agencies and global organizations to focus on providing aid to lower crime while assisting those living in poverty.

References

Albright, S. C. Winston, W. L. (2017). Business Analytics: Data Analysis & Decision Making. Sixth Edition. Cengage Learning. Boston, MA.