Ch

.pdf

School

University Of Arizona *

*We aren’t endorsed by this school

Course

277

Subject

Business

Date

Apr 3, 2024

Type

pdf

Pages

5

Uploaded by DrBear3077

Report
Page 1 of 5 ANALYTICS REPORT TO: BNAN 277 GRADING TEAM FROM: SHAYNAH MERILAN SUBJECT: CH. 5 DISCUSSION-REGRESSION DATE: 26 MARCH 2024 Introduction This report aims to help Fisher Investments enhance their investment strategy by forecasting the Earnings per Share (EPS) of NYSE-listed companies, a crucial profitability metric. By analyzing a dataset of these companies, we sought predictors of EPS that don't include direct income measures, like Net Income, to avoid skewed results. The goal is to find financial indicators that signal profitable investment opportunities, assisting in making informed investment decisions. Data Analysis Population Regression Equation 𝐸?? = 𝛽 0 + 𝛽 1 𝐸𝐵? + 𝛽 2 ?𝑀 + 𝛽 3 ??𝑀 + 𝜀 Estimated Sample Regression Equation 𝐸?? ̂ = 4.21 + 2.14𝐸 − 10(𝐸𝐵?) − 0.07(?𝑀) − 0.01(??𝑀) Our y variable is earning per share what we’re trying to solve earnings before tax is the x Fit of the Model The R 2 = 0.1969 tells us we are 19.69%. Of the way toward perfectly predicting Earnings per Share using this model. On average, our predictions of Earnings Per Share are off by an average of $4.27 per share. Test of Joint Significance H 0 : None of the independent variables significantly impacts Earnings per share. H A : At least one of the independent variables significantly impacts Earnings per share.
Page 2 of 5 Because the p-value (Significance F) = 2.35E-71 is less than the significance level of 0.05, we can reject the null hypothesis and can conclude that at least one of the independent variables significantly impacts Earnings per Share. Earnings Before Tax Individual Significance Test H 0 : Earnings before tax does not significantly impact Earnings per share. H A : Earnings before tax significantly impact Earnings per share. Because the p-value = 1.21E-29 is less than the significance level of 0.05, we can reject the null hypothesis and can conclude that Earnings before tax significantly impacts Earnings per Share. As Earnings Before Tax increases by $1, Earnings Per Share increases by $2.14E-10/share, on average and all else constant. Operating Margin Individual Significance Test H 0 : Operating Margin does not significantly impact Earnings per share. H A : Operating Margin significantly impacts Earnings per share. Because the p-value = 6.06E-09 is less than the significance level of 0.05, we can reject the null hypothesis and can conclude Operating Margin significantly impacts Earnings per share. As Operating Margin increases by 1 percentage point, Earnings Per Share decreases by $0.07/share, on average and all else constant. Pre-Tax Margin Individual Significance Test H 0 : Pre-tax Margin does not significantly impact Earnings per share. H A : Pre-tax Margin significantly impacts Earnings per share. Because the p-value = 0.38 is more than the significance level of 0.05, we cannot reject the null hypothesis and cannot conclude Pre-Tax Margin significantly impacts Earnings per share. Residual Plot Interpretations Earnings Before Tax This residual plot appears to have a funnel shape which indicates possible heteroskedasticity. This could cause the standard error for Earnings Before Tax to be incorrect or biased which would mean the hypothesis testing for Earnings Before Tax is also incorrect.
Page 3 of 5 Operating Margin This residual plot appears to have a random shape which indicates possible homoscedasticity. This means that the regression model is perfectly specified, and its assumptions are not violated. Pre-Tax Margin This residual plot appears to have a random shape which indicates possible homoscedasticity. This means that the regression model is perfectly specified, and its assumptions are not violated. Check for Multicollinearity and Endogeneity Check for Multicollinearity: We do have multicollinearity between Pre-Tax Margin and Operating Margin because the correlation between those 2 variables is larger than 0.8. This could be the reason why Pre-tax Margin is not showing up as significant. To see the true impact of each variable, they should be looked at in separate regressions. Check for Endogeneity: Since the correlations between the residuals and x-variables are all very close to zero, we do not have evidence of endogeneity meaning that our coefficients are unbiased. Example Predictions: Nike: 𝐸?? ̂ = 4.21 + 2.14𝐸 − 10(6.20) − 0.07(14.23) − 0.01(12.3) = 4.418 Disney: 𝐸?? ̂ = 4.21 + 2.14𝐸 − 10(5.87) − 0.07(6.38) − 0.01(6.41) = 4.955 Recommendation The analysis shows the characteristics of a profitable company. These following coefficient interpretations support these findings. Because of the Earnings per Tax significance test the characteristics of a profitable company would be high earnings before tax and low operating margin. Given these two hypothetical companies we would choose to invest in Disney because it had a higher predicted Earnings Per Share. Conclusion It is recommended that companies that are profit focused have the characteristics: high earnings before tax and a low operating margin. By focusing on the identified variables, Fisher Investments can make more informed decisions, targeting companies likely to offer profitable returns. Reach out to Shaynah Merilan for more details or questions shaynahm@arizona.edu. Thank you for your consideration.
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help