miscellaneous

  Both X and Y can be placed on the same shelf, so that buyers of one item would be prompted to buy the other. Promotional discounts could be applied to just one out of the two items. Advertisements on X could be targeted at buyers who purchase Y. X and Y could be combined into a new product, such as having Y in flavors of X. Support:  It says, how many times item occurred in all records. ex. apples occurred 50% (0.5) times in all transactions. * Confidence: It says how many time both apple and beer are purchased whenever apple is purchased. example. confidence = 0.75  means 75% times apples and beer both purchased whenever apples are purchased. means if 100 people purchased apple then out of 100, 75 people purchased apple with beer both and  25% apple without beer. One drawback of the confidence measure is that it might misrepresent the importance of an association. This is because it only accounts for how popular apples are, but not beers. If beers are also ve...

When we want to do the hypothesis test i.e reject or accept the hypothesis basis on statistics then we use t test or z test. Criteria to use t test or z test: when number of samples are <=30 and population standard deviation is unknown, we use t test else we go with z test. in both tests, we have score and critical value. note: we calculate score by using the formula and calculate critical value for t test using table. * In the above problem statement, we have population standard deviation but number of samples are greater than 30 hence we'll use z test. we have to reject or accept null hypothesis at the 95% confidence level. so for 95% critical value will be -1.96 and 1.96. score = (sample mean - population mean) / (sample standard deviation / sqrt(number of samples)) if our score goes beyond critical value then we'll reject null hypothesis. (here null hypothesis is machine dispenses 80 ml of fluid) *  In this problem statement our alternate hypothesis is either it is less ...