Hwk7SolnGdDrtSp06 - Question 1. One of the resulting...

Info iconThis preview shows pages 1–3. Sign up to view the full content.

View Full Document Right Arrow Icon
Question 1. One of the resulting consequences of 9/11 for the hotel industry was the tremendous discounting and merchant model partnerships established. Even now, hotels are working on recapturing reservation market share from on-line players like Expedia and Travelocity, which can cost the hotel about 25% of room revenue in “commissions.” At the corporate level, some chains are encouraging properties to promote themselves through local websites, and then channel bookings to the corporate site, away from the third party companies. One of the most important ways hotels can increase traffic to their site is through on-line marketing campaigns, like search engine optimization (SEO). In order to determine the effectiveness of these SEO programs (which can cost thousands of dollars), suppose Hilton asked 120 randomly selected Hilton Garden Inns to develop their own sites and asked half of them (randomly chosen) to use SEO, while asking the other half to not invest in any special marketing for their sites. Hilton then tracks how many bookings on Hilton.com came from links from those independent property sites each day for three months. The data file shows the total number of bookings per property over the three months. Do SEO websites bring in more reservations than non SEO sites? Data appears in Hwk7Q1DatSp06. A) What inferential technique is appropriate here? Why? Hypothesis test, because we’re answering a yes/no question. B) State your hypotheses in terms of the relevant parameters, then define each of the parameters in your statement. This is a two sample test because there are two INDEPENDENT samples using SEO versus not using SEO. H 0 : μ1- μ 2 = 0 H A : μ1- μ2 > 0 Parameters: μ1 is the mean number of reservations for hotels using SEO websites μ2 is the mean number of reservations for hotels not using SEO sites. C) What is the point estimate (stated symbolically) for the function of your parameters you stated in your hypotheses? The mean of the sample 1 minus the mean of the sample 2 ( 2 1 y y - ) is the point estimate for the function of the parameters started in the hypothesis
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
D) Get the descriptive statistics for both samples, then use these to compute the point estimate for the function of the parameters stated in your hypotheses. Descriptive Statistics: Properties with SEO, Properties without SEO Variable N N* Mean SE Mean StDev Minimum Q1 Median Q3 Properties with 60 0 8790 112 871 7005 8175 8734 9393 Properties witho 60 0 8375 101 784 7095 7904 8156 8681 Variable Maximum Properties with 10634 Properties witho 11529 Point Esimate: 2 1 y y - = 8790-8375 = 415 E) What is the VARIANCE (NOT estimated variance; this should be stated symbolically) of your point estimate? (Page 73 of your notes.) Var( 2 1 y y - )=(σ 1 2 /n 1 )+(σ 2 2 /n 2 ) F) Follow the steps on page 64 to go from the variance of your point estimate to the standard error of your point estimate, then plug in the appropriate descriptive statistics from part D above to get a numerical value for the standard error. St dev =
Background image of page 2
Image of page 3
This is the end of the preview. Sign up to access the rest of the document.

This homework help was uploaded on 02/19/2008 for the course H ADM 201 taught by Professor Rlloyd during the Spring '06 term at Cornell University (Engineering School).

Page1 / 11

Hwk7SolnGdDrtSp06 - Question 1. One of the resulting...

This preview shows document pages 1 - 3. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online