1. The behavioral scientists have conducted one of the studies of the effect of

Question

1. The behavioral scientists have conducted one of the studies of the effect of a teaching method designed to oncrease the probability of successful completion of a statistics course on the self esteem of students in the course. The study revealed a statistically significant difference between the population 1 and population 2 means (p < .5) with n = 100 students. How would you interpret this result to a person who understands hypothesis testing but who has never learned about effect size and power?

2. The behavioral scientists have replicated the study described in Problem 5 and obtained a statistically significant difference between population 1 and population 2 means (p<.5), but with N = 15. How would this result change your interpretation of this result to a person who understands hypothesis testing, but who has never learned about effect size and power.

Explanation / Answer

1. I assume you mean p < .05 here. We reject the null hypothesis. There is evidence of a difference between the completion rates for the two methods. If in fact there were no difference between the completion rates, we would expect to see sample proportions this far apart in less than 5% of all random samples. 2. I assume you mean p < .05 here as well. You don't mention what problem 5 is, so it's hard to say, but if in fact there were no difference between the two populations, then when we repeatedly sample groups of size 15 from these populations, we would expect to see differences in the sample results at least as big as the difference we observed in less than 5% of all samples.

Related Questions

Navigate

• Browse (All)
• Browse 1
• Subjects

---