Suppose that you belong to a panel with representatives from theMinistry of the Environment and the Accreditation Services Branchof the Standards Council of Canada. You are responsible for testingscrubbers, i.e. devices to capture carbon dioxidefrom smokestacks. You do so by measuring how much carbon dioxidethey capture in a standard lab setting.

A manufacturer has stated, "When our Scrubber 2 is installed inthe standard lab setting, the amount of carbon dioxide capturedfollows a normal distribution with a mean of more than 800 tons."You are responsible for verifying this. For five different Scrubber2's, you record the following noisy data indicating the number oftons of carbon dioxide captured:

• 503, 854, 647, 701, 620

Question: Suppose that you're curious as to whether there's adifference between the Scrubber 2 and its predecessor, the Scrubber1, in terms of the average amount of carbon dioxide captured. Forfour different Scrubber 1's, you take additional measurements inthe standard lab setting:

• 683, 305, 377, 539

Consider the data set of now nine points. You do not wish toassume that either group follows a normal distribution. Would arandomization test be appropriate to assess the difference inmeans? If yes, run it and report your results. If no, suggest andperform an alternative.

State any assumptions you make.