In: Statistics and Probability
7-3) A criminologist wanted to see if there is a significant difference in the sentence length [in months] between white and minority offenders convicted of drug-related crimes. She randomly selects a sample of 35 white offenders [mean sentence length = 49; std. dev. = 14] and a sample of 25 non-white offenders [mean sentence length = 60; std. dev. = 12].
Given:
We want to test if there is a significant difference in the sentence length [in months] between white and minority offenders convicted of drug-related crimes.
a) The hypothesis testing problem is:
Null hypothesis: There is no significant racial difference in the sentence length between white and minority offenders convicted of drug-related crimes.
i.e
b) Alternative Hypothesis:There is a significant racial difference in the sentence length between white and minority offenders convicted of drug-related crimes.
i.e
c) The test statistic is:
Where
Therefore,
d) Here degrees of freedom is n1+n2-2=58 and level of significance is 0.05,for two tail test
hence the critical t value is tcrit=-2.000 ### Using t table
e) Since -3.179<-2.000, we reject the null hypothesis at 5% level of significance with 58 degrees of freedom.
f) Therefore we conclude that there is a significant racial difference in the sentence length between white and minority offenders convicted of drug-related crimes.