Phone surveys Anytime we conduct a survey, we must take care to avoid undercoverage. Suppose we plan to select 500 names from the city phone book, call their homes between noon and 4 pm, and interview whoever answers, anticipating contacts with at least 200 people. a) Why is it difficult to use a simple random sample here? b) Describe a more convenient, but still random, sampling strategy. c) What kinds of households are likely to be included in the eventual sample of opinion? Excluded? d) Suppose, instead, that we continue calling each number, perhaps in the morning or evening, until an adult is contacted and interviewed. How does this improve the sampling design? e) Random-digit dialing machines can generate the phone calls for us. How would this improve our design? Is anyone still excluded?

The Coefficient of Variation: C.V. = S / x(bar) X(bar) Mean of data Examples: #1 X(bar) 54 ft S 26 ft C.V. = S / x(bar) = 26/54 = .48 or 48% #2 X(bar) 2 hours S 2.7 hours C.V. = 2.7 / 2 = 1.35 NOTICE: the units cancel when you divide the two numbers, therefore the answer does not have units!! Chebyster’s Theorem: For any set of numbers with mean x(bar) and standard deviation, S, atleast (1 – (1/ k^2) x 100%) of those numbers must fall between [x(bar) – kS] and [x(bar) + kS] ________________________________________________________________________ Quartiles: specific values that attempt to divide quantitative data into four equal parts. 1. find median 2. take median of lower half and upper half 3. then you will find the three medians, th