When a road runner runs a route a common goal of runners is to run a *negative split*. A negative split means to run the second half of the route faster than the first half. I often run to Nett bridge and back, or down to Lidakida beach and back. On these "out-and-back" runs I usually push for a negative split. Sometimes I do not get a negative split, and the time differences are always small. Both routes are tough to negative split, the outbound is downhill and the inbound return is uphill. Do the seven runs below indicate that I am statistically significantly faster on the inbound return than on the outbound run?

Route | Outbound time (min) | Inbound time (min) | Diff |
---|---|---|---|

Nett Bridge | 22.25 | 20.38 | -1.87 |

Nett Bridge | 22.97 | 21.12 | -1.85 |

Lidakida | 16.97 | 16.05 | -0.92 |

Lidakida | 20.32 | 19.43 | -0.89 |

Nett Bridge | 22.67 | 22.13 | -0.54 |

Lidakida | 16.12 | 15.87 | -0.25 |

Nett Bridge | 26.75 | 27.25 | 0.5 |

1. | Sample size n | ||

2. | Sample mean x | ||

3. | Standard deviation sx | ||

4. | Standard error SE | ||

5. | t-critical for alpha α = 0.05 | ||

6. | Margin of error E | ||

7. | Lower bound ci | ||

8. | Upper bound ci | ||

9. | p-value from t-test for paired data | ||

10. | maximum confidence level c |

- __________ Does the 95% confidence interval for the mean of the paired differences include zero?
- __________ Am I statistically significantly faster (shorter time) on the inbound return than on the outbound run at an alpha of 5%?
- __________ If I am indeed faster inbound, as a percentage how sure can you be that I am faster?
- ____________________ Should you
*reject***or***fail to reject*the null hypothesis? - __________ If you reject the null hypothesis H
_{0}: μ_{diff}= 0, what is the risk that you will wrong?