Using data from the 2012 season for MLB a baseball analytics firm wants to determine which variable are important in predicting a teams wins. The data collected in clues wins, earned run average (ERA), and runs scored for the 2012 season. The firm also has each team categorized as being in the 0=American league or 1= National league.

The firm now wants to know if things are different between the two leagues. They run a model without interaction with the variables ERA and League (an indicator variable). the results are below.

SUMMARY OUTPUT
Regression Statistics
Multiple R	0.837773
R Square	0.701863
Adjusted R Square	0.679779
Standard Error	6.753069
Observations	30
ANOVA
	df	SS	MS	F	Significance F
Regression	2	2898.694	1449.347	31.78118	8.03E-08
Residual	27	1231.306	45.60394
Total	29	4130
	Coefficients	Standard Error	t Stat	P-value
Intercept	163.8291	10.46384	15.65669	4.54E-15
E.R.A.	-20.0106	2.524902	-7.92531	1.61E-08
League	-4.86216	2.495075	-1.9487	0.061793

Base on the above which statement is the most accurate (as always alpha = 0.05)

Group of answer choices

The model is not significant (based on the F-test) and neither variable should be used to predict wins

The model is significant based on the F-test. Both variables should be in the model

The model is significant based on the F-test. After considering the individual variables only ERA should be in the model

The model is significant based on the F-test. After considering the individual variables only runs scored should be in the model