A fancy new brand of laundry detergent just launched an aggressive advertisement campaign in the hope that people will use the b
rand despite its higher price point. An avid consumer is trying to determine whether this fancy new brand of laundry detergent cleans clothes better than his regular brand of laundry detergent. To do this, over the course of a month he randomly uses one of the detergents in each load of laundry and then, when the wash cycle is complete, assigns a value to how clean the clothes are based on the number of garments that are "sufficiently clean," with higher scores being better. If the consumer were to perform a test to tell the difference between the mean scores of each detergent (ignoring the flaws in this test design), what hypothesis would he use?
The consumer is testing to know if his new detergent is better off in cleaning than the regular. The question says that higher scores after cleaning is used to signify which is better based on sufficiently clean garment. Since he is interested in knowing the mean scores of the differences, he should use the hypothesis I stated above.
