ECN 221 ASU EXAM -1 QUESTIONS WITH COMPLETE SOLUTION GRADED A+

5 number summary and box plots - maximum Q3 median Q1 minimum outliers not based on zscore but IQR range (more than 1.5 IQR below Q1)*** A data set consists of all businesses in Tempe that accept Discover Card branded credit cards. The variables in the data set are the total amount of purchases using Discover Card credit cards and how many purchases were made using the card and all the data are for the year 2008. T/F: The data in this data set constitute a cross section, i.e., they are cross sectional data. - TRUE A data set consists of the number of new stores opened each year, internationally, for the years 1995 through 2015. That is, there are 21 observations, one for each of the years and the variable reported is the number of new stores. T/F: The data in this data set are time series data. - TRUE A histogram is useful for - observing relative frequencies of categorical data. addition laws - probability of event A, B or A and B occuring P(AuB) = P(A) + P(B) - P(AnB) Bar charts are a useful way to display: - categorical datacategorical data (qualitative) - identify characteristics of element ex: gender, marital status ALSO: zip code, phone number classical probability - based on assumption of equally likely outcomes ex: roulette table coefficient of variation - =std dev / mean how large std dev is relative to the mean combination example - 4 openings 11 people qualify 11! / 4! (11-4)! =330 combination EXCEL - =combin(n,k) (# being chosen from, end choices) combinations - n choose k n! / k! (n-k)! complement of event - all sample points NOT IN event A P(A) + P(A)^c = 1 correlation - measure of linear association, not necessarily causationbounds: 1. coefficient can be -1 to +1 2. values near -1 have strong NEGATIVE linear relationship 3. values near 1 have strong POSITIVE linear relationship 4. close to 0 means a WEAKER relationship