MKT 317 January 22 2010 HOMEWORK 7 46

MKT 317 January 22, 2010

HOMEWORK 7. 46 (do not do the p-value part) 8. 2 (do not do the confidence interval part) 8. 12 (do not do the confidence interval part) 8. 48 Due Friday, January 29, 2010

Class Slides http: //www. msu. edu/~whitery 2/mkt 317 slides. html

TYPES OF MEASUREMENT LOWEST HIGHEST NOMINAL ORDINAL INTERVAL RATIO

TYPES OF MEASUREMENT NOMINAL - IDENTIFY ORDINAL - ORDER INTERVAL RATIO - COMPARISON OF INTERVALS - COMPARISON OF ABSOLUTE MAGNITUDES

EXAMPLES Marital Status ACT Score Weight Movie Ratings

EXAMPLES Temperature (°F) Zodiac Sign Class Rank Number of Classes Skipped

ERROR TYPES TYPE I ERROR REJECTING A TRUE H 0 TYPE II ERROR ACCEPTING A FALSE H 0

Tests Learned Last Week § TWO MEANS – INDEPENDENT SAMPLES § t-test or z-test § Depending on what?

WHEN TO USE A Z- or T- TEST ? n ≥ 30 for both = Z-TEST n < 30 for either = T-TEST

TWO MEANS HYPOTHESES Two Tailed Test H 0: μ 1 – μ 2 = D 0 H 1: μ 1 – μ 2 = D 0 Left Tailed Test H 0: μ 1 – μ 2 ≥ D 0 H 1: μ 1 – μ 2 < D 0 Right Tailed Test H 0: μ 1 – μ 2 ≤ D 0 H 1: μ 1 – μ 2 > D 0

Z – TEST TWO MEANS FORMULA

t= Where T-TEST TWO MEANS FORMULA – – (x 1 - x 2) – D 0 ______ df =(n + n ) - 2 1 2 Sp 2 + Sp 2 __ __ n 1 n 2 √ S p 2 = 2 2 (n – 1) S + (n – 1) S 1 1 2 2 _________ n 1 + n 2 - 2

Example for Independent Small Samples Two sections of MSC 317 complete a homework assignment and the instructor wants to see whether the two sections show equal performances or not. She takes a random sample of the students from each class, and computes the following descriptive statistics: SEC 203: n 1=10, =21. 05, S 1 =2. 41 SEC 204: n 2=10, =21. 75, S 2 =2. 18 What would be the statistical and managerial conclusions based on these samples? Use =. 05.

Example for Independent Large Samples According to G. Hill in the “Digital Age: How It is Changing Our Lives” the average number of hours on the internet per internet-connected household was 4. 2 in 1995, and 4. 4 in 1996. Assuming both of these samples are based on independent random samples of 1, 000 households each with standard deviation of 2 hours. Is internet usage greater in 1996 than in 1995?

HOW TO READ A T-TABLE

How to Read a Z-Table