Professional Documents
Culture Documents
Analytics Report: Gray Hunter
Analytics Report: Gray Hunter
Analytics Report: Gray Hunter
SUBJECT: LAB #5
DATE: 10/12/2020
Introduction
Given the information about companies that are traded on the New York Stock Exchange, I
developed a model to predict earnings per share. The purpose of this was to determine which
variables would be helpful to our company in predicting the companies that would be worth
investing in. This document contains regression tests that identify the variables that are good
predictors of earnings per share.
Data Analysis
Regression Equation
^
E /S=4.13+2.03 E - 10 ( EBT )−.06 ( OM )−0.004 (PTM )
Fit of the Model
The R2 = 0.16 tells us we are 16% of the way to perfectly predicting earnings per share using this
model.
The standard error of 4.25 tells us our predictions of earnings per share are off by an average of
$4.25/share.
Appendix
SUMMARY OUTPUT
Regression Statistics
Multiple R 0.40104488
R Square 0.16083699
Adjusted R Square
0.15910079
Standard Error 4.25037521
Observations 1454
ANOVA
df SS MS F Significance F
Regression 3 5020.67556 1673.55852 92.6374014 7.5194E-55
Residual 1450 26195.2496 18.0656894
Total 1453 31215.9252
0
0 5 10 15 20 25 30 35 40 45 50
-2
-4
-6
-8
-10
Operating Margin
Earnings Before Tax Residual Plot
60
50
40
30
20
Residuals
10
0
-50000000000 -10 0 50000000000 100000000000
-20
-30
-40
Earnings Before Tax
0
-2 0 5 10 15 20 25 30 35 40 45 50
-4
-6
-8
-10
Pre-Tax Margin
Residuals Earnings BeforeOperating
Tax Margin
Pre-Tax Margin
Residuals 1
Earnings Before Tax
-1.72879E-15 1
Operating Margin-2.45572E-15 -0.1119405 1
Pre-Tax Margin 5.03355E-16 -0.0402728 0.8524628 1