James et al. (1997) demonstrated that the chemical hypoxanthine in the vitreous humor (the colorless jelly filling the eye) shows a postmortem linear increase in concentration with time since death. This suggests that hypoxanthine concentration might be useful in predicting time of death when it is unknown. The following graph shows measurements collected by the researchers on 48 subjects whose time of death was known. The regression line, the 95% confidence bands, and the 95% prediction interval are included on the graph.

a. The data set depicted in the graph includes one conspicuous outlier on the far right. If you were advising the forensic scientists who gathered these data, how would you suggest they handle the outlier?

b. What do the confidence bands measure?

c. Are the inner dashed lines the confidence bands or the prediction interval?

d. If the regression depicted in the graph was to be used to predict the time of death in a murder case, which bands would provide the most relevant measure of uncertainty, the confidence bands or the prediction interval? Why?

Transcribed Image Text:

Hours since death 100- 80- 60- 40 20- 0 0 200 400 Hypoxanthine concentration (μmol/l) I 100 300