A company that makes robotic vacuums claims their newest model of vacuum lasts, on average, 2 hours when starting on a full charge. To investigate this claim, a consumer group purchases a random sample of 5 vacuums of this model. They charge each unit fully and then measure the amount of time each unit runs. They would like to know if there is convincing evidence that the true mean run time differs from 2 hours. The consumer group plans to test the hypotheses  = 2 versus < 2, where μ = the true mean run time for all vacuums of this model. The power of this test to reject  = 2 when μ = 1.75 is 0.0865 using a significance level of 0.05. Which combination of sample size and significance level would increase the power of this test the most?