Question

We run 9 subjects through our treatment program and then give them the GR-R (μ = 30; σ = 3). They get a mean GR-R score of 31.5

a) What z score is going to be our cutoff point for this null hypothesis? (+1.64, +/-2.33, +/-1.96, -1.64).

b) What if we failed to reject the null hypothesis, but I told you that your catharsis treatment really did increase aggression and that in reality the null hypothesis is false. What type of outcome occurred? (Type 1 Error, Type 2 Error, Power, Correct Decision)

c)What if we rejected the null hypothesis, but I told you that in reality there was no effect of your catharsis treatment? (Type 1 Error, Type 2 Error, Power, Correct Decision).

d) What if we repeated the same experiment with 100 people? This time our sample's mean was 31. (we're still using the same population parameters, etc from the previous GR-R questions, but we have a different sample this time.) What is the standard error of our comparison distributuion? (.3, 1, 3, none of these answers are close)

e)Based on the results of this study we should: reject the null hypothesis or fail to reject the null hypothesis

f) What best explains why pur result was not significant the first time but it was the secon time?

We increased n so we increased the power to detect a difference between the sample and the comparison distribution.

We increased n so we increased the amount of variability in our comparison distribution.

We increased n so we decreased the mean of our sample distribution.

Answer 1

The null hypothesis here is against the alternative at 5% level of significance will have a cut off of

at 2% level of significance will have a cut off of

and if the alternative is one sided here the chances are   so a 5% significance cut off score will be 1.64

The cut off score depends on the significance level mentioned

b) Type II error=Probability of (accepting the null hypothesis given that the null hypothesis is false)

c)Type I error = Probability of ( rejecting the null hypothesis given that the null hypotheisis is true)

d)Standard error=

e) we reject the null hypothesis as the value of the statistic z= and pvalue based on this value =0 < 0.01 so the hypothesis is rejected at all significance levels

f) We increased n so we increased the power to detect a difference between the sample and the comparison distribution. ie the power to reject the null hypothesis has been increased by increasing the sample size