Intended to provide our own search engines and external engines with highly rich, chapter-representative searchable text on the opening pages of each chapter. Because it is UNCORRECTED material, please consider the following text as a useful but insufficient proxy for the authoritative book pages.
Do not use for reproduction, copying, pasting, or reading; exclusively for search engines.
OCR for page 51
51 evening sessions. In each location, the daytime session was 4.5 Effects of Demographics held from 10am-12:30pm and the evening session was held on LOS from 6:00-8:30pm. Hotel meeting rooms were set up classroom style with two This section presents the results of an investigation into the participants seated at each roughly 10-ft-long table. There effects of various socioeconomic and location factors on clip was an aisle between two rows of tables in which the video ratings for auto, bicycle, and pedestrian modes. The effects of equipment was placed, and a large-screen projector screen metropolitan area location on transit LOS ratings could not was set up at the front of the room. Light refreshments were be tested because of differences in the transit services pro- provided during each session. vided in each metropolitan area. As participants arrived, they were given a unique identifier For each of the auto, bicycle, and pedestrian modes, four code which was written on their survey sheets for them and common film clips were shown in each of the four metropol- also corresponded to the receipt sheets generated for each itan regions. We used the ratings on these clips to test for location. The unique identifier scheme is required by GMU effects of socioeconomic and location factors. to keep the participants' information confidential while For each factor, we divided the respondents into a test allowing the researchers to later make correlations between group and a control group. The test group contained those responses and some other demographic (i.e., age or sex). The respondents for which the factor was present (e.g., persons participants were then asked to complete a demographic having one or more cars available); the control group con- questionnaire while waiting for the remaining participants to tained those respondents for which the factor was not pres- arrive. Once all participants had arrived, Dr. Flannery ent (e.g., persons not having a car available). thanked them all for attending and gave a short introduction Once the groups were defined, we used a nonparametric to help them understand the task at hand. The opening re- randomization (bootstrap) (see Davison and Hinkley ) marks explained the study's purpose, who the study sponsor test to determine whether the difference in mean ratings for was, general procedures, location of facilities, explanation of an individual clip was significant. The sample size is the forms (survey forms, Informed Consent Form), their denoted by N and the size of the control group is denoted rights as study participants, and the schedule of the study. by k. For hypothesis testing, the bootstrap method works as The clips were shown in the order of pedestrian mode, bicy- follows: cle mode, and finally auto mode. Participants were asked to keep their opinions to themselves during the study so as to 1. Compute the difference in means between the test group not influence their neighbors and were informed that, at the and the control group. end of the clips, a short focus group would be conducted in 2. Generate a random permutation of cases. For each per- which they could provide more details on their opinions. mutation, compute the mean for the first k cases and the A practice clip was shown to participants at the beginning last N - k cases. If the difference is greater than or equal to of each mode to familiarize them with the task at hand. Ques- the difference computed in Step 1, add 1 to an indicator tions were clarified, if needed, once participants had com- variable X. Repeat this step B times. pleted rating the practice clip. The participants were not 3. Divide X by B - 1. The result is the estimated probability informed what specifically to rate each clip on--only that that the difference computed in Step 1 results from chance they should rate the clip on how satisfied as a traveler. Upon alone. completion of each mode, typically 20 to 25 minutes after the session had started, the participants had a 10- to 15-minute The bootstrap method has significant advantages over break before beginning the next mode video session. After all traditional hypothesis testing, mainly because it is nonpara- video clips had been rated by the participants, a short break metric and, therefore, makes no assumptions about the shape was taken to set up for the focus group session. During the of the distribution of responses. focus group session, participants were asked to discuss what For this analysis, we defined significance to be at the 10% factors greatly influenced their ratings in each of the mode level (i.e., the probability that the difference in ratings could video sessions. These comments were noted by Dr. Flannery have arisen by chance alone is less than 10%.). We judged the on her laptop, and efforts were made to focus the participants bootstrap test to be superior to other tests that might be used on one mode at a time and to complete discussion of that for the following reasons: mode before moving to the next. At the end of the session, the participants were allowed to · Standard analysis of variance requires that cell sizes be ask questions and then were compensated for their time with equal, or nearly so (see Searle ). This assumption is a $75.00 honorarium paid in cash and required to sign a re- violated for all the tests considered. ceipt. Then forms were collected, and participants were · Classic hypothesis tests (e.g., the t-test) assume that thanked for their contribution to the study. responses are normally distributed.