Here are the estimated results for these 15 seasons of data (2000-2014).
Variable | Coefficient | Std. Error | t-Statistic | Prob. |
SINGLE | 0.499 | 0.02 | 24.87 | 0.00 |
DOUBLE | 0.718 | 0.04 | 16.86 | 0.00 |
TRIPLE | 1.137 | 0.12 | 9.32 | 0.00 |
HR | 1.463 | 0.04 | 37.62 | 0.00 |
NBB | 0.288 | 0.02 | 14.31 | 0.00 |
SB | 0.103 | 0.04 | 2.61 | 0.01 |
GDIPCS | -0.028 | 0.06 | -0.48 | 0.63 |
HBP | 0.398 | 0.08 | 4.88 | 0.00 |
SF | 0.774 | 0.17 | 4.63 | 0.00 |
OUTS | -0.102 | 0.02 | -4.19 | 0.00 |
C | -10.644 | 106.03 | -0.10 | 0.92 |
A few observations: first, other than grounded into double plays and caught stealing (GIDPCS) (along with the constant term) each of the variables is statistically significant at the 99% confidence level and of the correct sign. Only OUTS are negative and statistically significant. Second,the coefficient on HR's is greater than the coefficient on Singles, which means that a HR will on average generate more runs than a single. All the other coefficients seem to make sense as well.
For comparison purposes, here is the blog for 2013 MLB Team Runs Created.