Question

6. Effect size and Cohen's d

Suppose a researcher is trying to understand whether people who purchase fast-food hamburgers would be willing to pay more if the hamburger comes with a free key chain. Prior research suggests the mean amount customers say they are willing to pay for a hamburger is μ = 3.68 and σ = 0.70.

The researcher plans to conduct a study very similar to the prior research by selecting a sample of customers and asking them how much they are willing to pay for the hamburger. Before asking, however, he will tell the customer about the free key chain that will come with the hamburger.

The researcher’s null hypothesis is that the mean amount the customers are willing to pay when they are told about the free key chain is no different than the amount customers are willing to pay when they are not told they will receive a free key chain.

The researcher’s sample of 49 customers has a sample mean of M = 4.04. The test statistic for this sample mean is 3.60. Using a significance level of α = .05, which of the following is the most appropriate statement of the result? 

(Hint: For a two-tailed test with α = .05 and σ known, the boundaries of the critical region are always ±1.96.)

Telling customers they will receive a free key chain with their hamburger did not have a significant effect on the amount they say they are willing to pay for a hamburger, z = 4.04, p > .05.

Telling customers they will receive a free key chain with their hamburger had a significant effect on the amount they say they are willing to pay for a hamburger, z = 3.68, p < .05.

Telling customers they will receive a free key chain with their hamburger did not have a significant effect on the amount they say they are willing to pay for a hamburger, z = 3.60, p < .05.

Telling customers they will receive a free key chain with their hamburger had a significant effect on the amount they say they are willing to pay for a hamburger, z = 3.60, p < .05.

Compute the estimated Cohen’s d to measure the size of the treatment effect.

Note: Cohen’s d is always reported as a positive value and reflects the proportion of the standard deviation that is affected by the treatment.

Estimated Cohen’s d =     

Using Cohen’s criteria, the estimated Cohen’s d indicates that telling customers they will receive a free key chain is associated with a    in the amount they are willing to pay for the hamburger.