Question: Sometimes, it takes multiple statistical tests to figure out what you want to know. The SPSS data file ‘Yates’ contains some data from a research project based on the Andrea Yates case. The researcher was interested in whether or not parents would be more punitive towards Yates, who murdered her five children but was ultimately found NGRI by a jury. Subjects who were either parents or non-parents read a summary of a case based off the Yates case and were asked to select a sentence option from the following choices:

__________ no punishment

__________ probation with no time spent in prison

__________ confinement in a mental hospital

__________ 1 year in a county jail

__________ 5 years in a state prison

__________ 10 years in a state prison

__________ life in prison with the possibility of parole after 25 years

__________ life in prison with no possibility of parole

__________ the death penalty

(a) Treat the sentence data as interval and conduct a t-test to test a hypothesis that there will be no difference between parents and non-parents in sentence (do not use the 5-step procedure, simply conduct the test and decide whether or not to reject the null hypothesis) (5)

(b) Upon further consideration, the researcher is concerned that perhaps this data is ordinal. Perform a chi-square test to see if there is a difference in sentence based on parental status (do not use the 5-step procedure, simply conduct the test and decide whether or not to reject the null hypothesis) (5)

(c) Finally, what the researcher is most interested in is whether or not parents will be more likely to vote for the death penalty than non-parents. Using the results from (b), test for a difference in death sentences between parents and non-parents (do not use the 5-step procedure, simply conduct the test and decide whether or not to reject the null hypothesis) (5)