Competency 3 Statement Utilizing Statistical Regression And

Competency 3 Statementutilizing Statistical Regression And Time Series

Utilizing statistical regression and time series analysis models, you will be able to evaluate and analyze how multiple variables impact an organization. You will also be able to create forecasts and interpret data to analyze performance as it impacts strategic planning and comparative advantage for an organization. Manipulating data to create models helps us describe and summarize relationships between variables. Understanding how variables relate to each other helps businesses predict performance and make informed strategic plans. For example, to make an informed recommendation to management regarding which types of office buildings to acquire or sell, you would model the relationship between assessed value and given variables.

This reflection gives you an opportunity to develop, evaluate, and apply bivariate and multivariate linear regression models, and then reflect on office buildings you recommend acquiring and selling, and why.

Pre-Reflection Exercise Download the Competency 3 Reflection Data Set. The data set is information about the tax assessment value assigned to medical office buildings in a city. The following is a list of the variables in the database: Floor Area: square feet of floor space; Offices: number of offices in the building; Entrances: number of customer entrances; Age: age of the building (years); Assessed Value: tax assessment value (thousands of dollars). As you work through the following exercises, note your answers to the given questions so you can easily summarize them in your reflection.

Use the data set to construct a model that predicts the tax assessment value assigned to medical office buildings with specific characteristics.

1. Construct a scatter plot in Excel with Floor Area as the independent variable and Assessment Value as the dependent variable. Insert the bivariate linear regression equation and R² in your graph. Do you observe a linear relationship between the 2 variables?
2. Use Excel's Analysis ToolPak to conduct a regression analysis of Floor Area and Assessment Value. Is Floor Area a significant predictor of Assessment Value?
3. Construct a scatter plot in Excel with Age as the independent variable and Assessment Value as the dependent variable. Insert the bivariate linear regression equation and R² in your graph. Do you observe a linear relationship between the 2 variables?
4. Use Excel's Analysis ToolPak to conduct a regression analysis of Age and Assessment Value. Is Age a significant predictor of Assessment Value?
5. Construct a multiple regression model using Assessment Value as the dependent variable and Floor Area, Offices, Entrances, and Age as independent variables. Report the overall fit R² and the adjusted R². Identify which predictors are significant at α=0.05. Determine which predictors can be eliminated. Formulate the final model using only significant predictors, for example: Assessed Value = 115.9 + 0.26 × Floor Area + 78.34 × Offices. Calculate the assessed value of a building with 3500 sq. ft., 2 offices, built 15 years ago, using this model. Discuss whether this value aligns with data in the database.

Paper For Above instruction

In the evolving landscape of real estate valuation, statistical regression models serve as essential tools for predicting property values based on multiple variables. Particularly in specialized sectors like medical office buildings, understanding how attributes such as floor area, age, number of offices, and entrances influence assessed values can aid investors, developers, and management in making strategic decisions—whether to acquire, sell, or renovate properties. This analysis explores how bivariate and multivariate regression models can be constructed and utilized effectively to inform such decisions.

The foundational step involves visualizing the relationship between key variables through scatter plots. For example, by plotting Floor Area against Assessment Value, one can observe whether a linear pattern exists. Typically, larger office buildings tend to have higher assessed values, which often manifests as a positive linear relationship. After generating this scatter plot in Excel and fitting a regression line, the resulting equation and R² value quantitatively describe this relationship. An R² value approaching 1 indicates a strong linear fit, whereas lower values suggest weaker relationships. Empirical analysis often reveals a significant positive correlation between Floor Area and Assessment Value, reinforcing the importance of size as a predictor.

Similarly, examining the impact of Age on Assessment Value provides insights into depreciation effects. Regression analysis and scatter plots typically show a negative relationship, with older buildings often valued less due to wear and obsolescence. Once again, statistical significance is determined via p-values in the regression output. Building on bivariate analyses, multivariate regression incorporates multiple predictors simultaneously, helping identify which factors independently affect assessed values when controlling for others. Variables such as the number of offices and entrances also contribute variably to valuation; some may prove statistically significant, while others may be redundant.

Applying Excel’s Analysis ToolPak enables the calculation of regression coefficients and significance testing. For example, if Floor Area and Offices emerge as significant predictors at α=0.05, the model can be further refined. A typical resulting regression equation might look like: Assessed Value = 115.9 + 0.26 × Floor Area + 78.34 × Offices. Using this model, an office building measuring 3500 square feet, with 2 offices, constructed 15 years ago, would have its assessed value estimated by substituting into the equation. The result should be consistent with the observed range in the database, validating the model’s predictive usefulness.

However, not all predictors contribute equally. Variables like Entrances or Age might have high p-values, indicating they are not statistically significant and can be eliminated to simplify the model without sacrificing accuracy. This process of model refinement increases reliability and interpretability. The adjusted R² further guides the model's validity, accounting for the number of predictors relative to the sample size.

From a strategic perspective, these statistical insights inform decision-making about property portfolio management. For example, properties with low predicted assessed values might be candidates for disposition, while those with high, value-adding attributes warrant acquisition or renovation. In the context of medical offices, factors like size and number of offices significantly influence valuation, guiding management to focus on buildings that maximize value based on these characteristics.

In conclusion, combining graphical analysis, regression modeling, and significance testing provides a robust framework for evaluating medical office buildings. This quantitative approach supports strategic decisions with empirical evidence, minimizes subjective biases, and enhances the ability to predict future values—crucial for optimizing real estate assets in competitive markets.

References

• Bowerman, B. L., O’Connell, R. T., & Koch, G. (2014). Regression Analysis and Linear Models: Concepts, Methods, and Applications. Routledge.
• Frost, J. (2020). Regression analysis made easy. Journal of Business & Economic Perspectives, 6(2), 45-59.
• Garson, G. D. (2016). Basic Statistical Concepts: A Primer for the Behavioral Sciences. Statistical Associates Publishing.
• Hayes, A. F. (2018). Introduction to Mediation, Moderation, and Conditional Process Analysis. New York: Guilford Publications.
• Hubbard, R., & Vetter, K. (2017). Property Valuation Techniques in Real Estate. Journal of Real Estate Finance and Economics, 54(3), 345–362.
• Krause, R. M. (2013). Economic analysis of real estate investments: A regression approach. Real Estate Economics, 41(4), 695-731.
• Schwarz, G. (1978). Estimating the dimension of a model. The Annals of Statistics, 6(2), 461–464.
• Tabachnick, B. G., & Fidell, L. S. (2013). Using Multivariate Statistics. Pearson Education.
• Wooldridge, J. M. (2015). Introductory Econometrics: A Modern Approach. Cengage Learning.
• Zeng, S. (2019). Real estate valuation using regression analysis: Methodologies and applications. International Journal of Housing Markets and Analysis, 12(4), 657-674.