11.0 Visitor Surveys

The hotel/visitor survey provides unique and useful information about non-resident travel in areas where visitors make a significant contribution to the overall traffic. Some metropolitan areas draw thousands of visitors who travel for sightseeing, business, amusement, and sports events. None of the travel surveys described in previous chapters is likely to provide much information about visitor travel; the visitor survey collects information on the mode of travel and the geographic and temporal movements of non-residents.

Hotel/visitor surveys are designed to gather information about the characteristics of non-residents who stay at hotels or other places of lodging. (The term “hotel” will be used throughout this chapter to refer to all public lodging for hire, including hotels, motels, bed-and-breakfast establishments, etc.) Specific information about the number and type of trips is also obtained. These data can be used to develop visitor trip generation rates (i.e. trips/occupied hotel room). This type of survey is not used to gather information about specific tourist or recreational attractions such as theme parks. In those cases, a special generator or establishment survey, as described in Chapter 10.0, is the appropriate means to collect the data.

Data collected from hotel/visitor surveys can be used to estimate the potential visitor demand for new service modes, particularly specialty modes such as people movers or streetcars that are designed to appeal to visitors. The potential demand for travel to new destinations that would draw tourists can also be estimated. The trip information from the hotel/visitor survey can also be used to help estimate the effects of new development.

The hotel/visitor survey can be used to collect travel data for out-of-area visitors who stay at hotels in the area. The surveys usually will not account for visitors staying with resident friends (which could be accounted for in the household travel survey) or for visitors staying at non-commercial lodgings such as clubs, association facilities, or school dormitories. In addition, the hotel-based survey will not provide information on travel of visitors who do not stay overnight.

The format of a hotel/visitor survey is similar to that of a household travel survey. Instead of a dwelling unit, the hotel room is used as the sampling unit. Data can be expanded to the estimated number of occupied rooms in the same way in which household survey data are expanded to occupied dwelling units. Location within the study area may also be a predictive

variable in estimating the number of trips by mode and purpose. Combined with the occupancy rates by hotel size class and location collected from the sample of hotels, the rates can be used to estimate the number of visitor trips generated by mode and purpose for an estimate of all occupied hotel rooms in each size-class and (if applicable) by area-type for the entire study area.

 11.1 Assembly of Background Data

The main type of data required for initiating a hotel survey is a listing of hotels in the study area. Common sources for this listing include:

• Tourist trade or hotel associations (these vary depending on location);

• Chambers of Commerce; and

• Telephone directories.

It is a good idea to use one source to compile an initial list and another to check the list for completeness. Hotel associations or chambers of commerce can also be helpful in gaining cooperation from member hotels.

The listing of hotels can provide not only part of the sampling frame for the survey, but also information about the hotels. Information needed will include the name of a contact person, telephone number, hotel address, and the number of rooms.

 11.2 Hotel/Visitor Survey Design

The survey team faces several survey design issues regarding hotel/visitor surveys. Given that the survey population for the hotel/visitor survey is the set of registered guests at all area hotels, these issues include:

• What survey method(s) should be used?

• Given the survey method, what data collection techniques should be employed?

These issues are described below.

Survey Method

There are two main options for the survey method. These are:

• Centrally distributed self-completion surveys; and

• In-person intercept interviews, usually in the hotel lobby.

In the self-completion survey, forms can be distributed to pre-selected rooms. The in-person interviews can be conducted as guests are checking out or as they pass through the lobby. The advantages of each method are shown in Table 11.1. In general, the self-completion method is preferred by many surveyors because of its lower cost, greater amount of information that can be gathered, and better ability to target the desired sample population. However, this method is also characterized by low response rates, and it will not be available if hotels do not permit the survey forms to be delivered.

Data Collection Techniques

For the self-completion survey, the only issues concerning data collection techniques are the methods for distributing and retrieving the survey forms. For the most part, these are dictated by what the hotels will allow. Distribution methods include having hotel staff leave the survey forms in the rooms, sliding the forms under the room doors, or handing the forms out at the check-out desk. It is preferable to collect the forms at the hotel, but a mailback option can also be provided.

There are three data collection options for the intercept survey method:

• Personal distribution of self-administered survey forms;

• Personal interviews using pencil and paper methods; and

• Computer-assisted personal interviews (CAPI).

The advantages and disadvantages of self-administered surveys and personal interviews are described in Chapter 3.0. The primary tradeoff between the two methods is between the better response rates (and, therefore, lower potential for bias) of the interview method and the quicker distribution and the lower level of intrusiveness of the self-completion method.

If the survey team chooses to conduct interviews, they next need to decide whether the interviews will be recorded by conventional techniques or by CAPI techniques. CAPI systems have the following advantages:

Table 11.1

1. They can be designed to permit the entry of only legal codes in any particular field (preventing data entry errors).

2. They can be used to check entries to make sure that they are consistent with other previously entered data (preventing data inconsistencies).

3. They automatically route interviewers through the interview (ensuring respondents are asked all the relevant questions and are not asked ones that should be skipped).

4. They can use information from previous questions or previous interviews to make interview questions or the sequencing of questions specific to a particular respondent.

5. The survey team is able to use the computer screen as a means of communicating with respondents. With CAPI, the survey team is able to present visual information to which respondents can respond, including:

• The interview questions (some types of questions, such as rating scales, can be presented graphically);

• The interview answers so that respondents can check to ensure that the interviewer is recording the proper response;

• Information commonly shown to respondents on show cards such as household income-level categories;

• Computer graphics (including video) to illustrate particular questions; and

• Geographic representations of information provided by the respondent.

However, CAPI systems also have the following disadvantages compared with standard PAPI interviews:

1. A great amount of programming time and effort is needed before the survey. The CAPI program needs to be nearly perfect before the survey is fielded, because interviewers will not generally be able to fix it in the field.

2. They require interviewers with more skills (or, at least, different skills).

3. There are no source records for the interview. The survey team must rely on the interviewer to enter information correctly.

 11.3 Sample Design

Hotel surveys typically employ a two-stage sample design consisting of a sample of hotels in a region and a sample of guests at those specific hotels. The sample of hotels is a method which allows fieldwork to concentrate on specific sites; the hotels are simply a way in which to reach a cluster of tourists. The sampled hotels are typically stratified by area type and by size (number of rooms or units). The stratification of the sampled hotels is based on the assumption that guests of large hotels may travel differently than those of small hotels, and visitors staying downtown may travel differently than visitors staying near the airport. The second stage of the sample consists of guests who stay in the selected hotels. Each occupied room consists of a visitor or group of visitors, and like the household travel survey, data is collected for each member of an occupied room.

For most analyses, an approach that considers the number of occupied rooms (or guests) is desirable. One way to resolve the potential imbalance between large and small hotels is to weight employee and workplace frequencies. If one were to weight them equally, then:

where:

N_k = number of samples in class k;

n = total sample size;

F_k = total number of hotels in size class k;

E_k = number of occupied rooms in size class k.

This provides an equal weighting of incidence of rooms and hotels.

Another method of setting the number of samples is as a proportion of the universe. Briefly, these steps are:

1. Determine the distribution of hotels by area type and industry type.

2. Allocate the number of occupied rooms by area type.

3. Calculate the average number of occupied rooms per hotel by area type.

4. Compute the distribution percent of all hotels by area type.

5. Define the total sampled rooms by calculating the sample percent for rooms.

6. Determine the number of rooms to be sampled rooms, applying these rates to the total number of hotels.

7. Distribute the total sampled rooms across area types based on the portion found in the universe. This number of rooms to be sampled by area type is the minimum desired.

8. Calculate the number of hotels to be sampled by dividing this desired sample of rooms by the average number of occupied rooms by site.

9. Set the minimum number of sites in a cell so that if the number of sample sites is less than the minimum in any cell, the number is adjusted. A maximum may also be set.

The most simple and direct method of developing the sample is to select every nth room, and therefore the hotel in which that room is located. For example, if there are 1,000 rooms in the CBD and a two percent sample is desired, every 50th room becomes the sample indicator. One would first rank order the hotels by size from largest to smallest. Then a random digit lower than the interval of 50 is chosen as the start (say 3). The 3rd room indicates the first sampled hotel (the hotel in which that room is located). The second sampled hotel is the one containing the 53rd room (3 + the interval of 50), and the third is the one containing the 103rd room (53 + the interval of 50), etc. until 20 hotels (or fewer since some hotels might contain multiple selected rooms) have been selected. The number of rooms in the selected 20 (or fewer) hotels should be about two percent of the total rooms.

The number of hotels that will need to be contacted in order to achieve the number of samples required is based on the survey team’s expectations about:

• The hotel refusal rate;

• The guest response rate; and

• The completion (versus attempted) rate for the guest questionnaires.

In self-completion surveys where forms are delivered to rooms, not every guest at larger hotels is required to complete a questionnaire; a subsample of rooms is adequate. One method to accomplish this is to give every guest a questionnaire, sort the returns by serial number and then sample out (remove) each form that ends in a random digit(s) chosen beforehand, or every nth form. This method is simplest for the hotel to administer, but more costly for the survey team since there is a cost for printing the extra questionnaires. A second method of subsampling rooms is based on room number. If one-third of the rooms are to be sampled, three random digits can be chosen (such as 2, 5, and 6) and all rooms whose number ends in one of the digits becomes a sampled rooms“become sampled rooms” -Brenda Zhou 10/31/08 3:10 PM . SHOULD BE SINGULAR ROOMThis method is more work for the hotels, and requires a commitment from the hotel to succeed.

In order to properly weight the interviews, it is necessary to have a count of occupied rooms by number of occupants for the sampled hotels. This count can be used to estimate the total occupancy rate for all rooms in all hotels, and the number of total visitors for the study area for the travel date(s).

Like the workplace survey where a small number of employers can account for the majority of the work force, in most areas the largest hotels (over 500 rooms) account for a disproportionate amount of the total rooms available. The greatest number of hotels, on the other hand, are generally in the smaller size-class (less than 100 rooms). Because of the difference in travel characteristics between the large hotels, which may provide shuttle service and host conventions, and smaller hotels, which may attract different types of visitors, the sample must carefully represent the types of hotels available to a visitor.

Once the sampling frame has been established, a representative sample can be drawn. Typically, hotels in the study area are stratified into size categories. For example, the categories might be: small (less than 100 rooms), medium (100-500 rooms), and large (500 rooms and greater). In addition, the geography of an area might lend itself to stratification by area type such as downtown, tourist district, remaining city, and airport area or suburbs. This allows a sample matrix stratified by size and area type. In addition, the nightly room rate could be used to stratify the properties. All of these strata should be examined with the objective of achieving a reasonable distribution of observations in each category.

 11.4 Drafting and Constructing Survey Instruments and Materials

Survey Instruments

Depending on the chosen survey method, the survey team could need to design and construct any of the following:

• Letters of introduction requesting permission to conduct the survey work;

• An interview script for the hotel contact interview;

• Site diagram to help fieldworkers and supervisors station themselves at the hotel;

• A self-completion visitor survey form;

• Collection boxes for the self-completion surveys;

• Control sheets for hotel distributed surveys;

• An interview script or CAPI program for interviewing people at the survey sites; and

• Control sheets for interviewers and fieldworkers distributing forms.

•  

  • Posters for placing in sampled hotels to increase public awareness and to inform both guests and hotel employee of survey procedures. (from “Southeast Florida Regional Travel Characteristics Study: Visitor Travel Survey Plan and Findings” http://www.pbcgov.com/mpo/library/data/pdf/travelstudy/Trav_char_Tr3.pdf)

   -Brenda Zhou 10/31/08 3:10 PM 

The survey team should draft a letter requesting permission from hotels to conduct the survey. It is desirable to have the letter beDO NOT NEED WORD 'BE' sent from a third party, such as the Chamber of Commerce or the Mayor’s Office, but the survey team should produce the first draft of the letter to ensure that the survey procedures and uses are described accurately. The letter should stress the importance of the survey effort and the need to have the cooperation of the specific hotel in question. The letter should also explain the confidentiality of the survey data.

Once the survey team has obtained tentative permission to conduct the survey at a particular site, the hotel contact person or other knowledgeable staff should be interviewed about the hotel. These interviews are commonly conducted informally as the survey arrangements are being completed, but it is much better to take a few minutes to conduct a formal or semi-formal interview with a pre-established script or questionnaire. Informal data gathering often causes interviewers to forget to ask particular questions that might be important in analysis.

When one or more survey team members visit the hotel prior to the survey, a site plan should be obtained or developed. This plan should note any special circumstances and survey design issues.

The self-completion visitor survey questionnaires can actually be quite detailed because they may ask about each trip made. The forms may be presented on standard size and weight paper since they may not need to be mailed back, or they can be distributed with business reply envelopes. It is desirable to supply one or more collection boxes with accompanying signage to ease the return process. To help the contact person with their distribution efforts, it is also helpful to provide written instructions and to ask them to record their progress on a control form.

The in-person intercept survey instrument may be either an interview script or a self-completion questionnaire. If the self-completion approach is used, the survey forms are likely to be similar to what would have been distributed to rooms. The interview scripts, whether pencil and paper or CAPI should be designed to be administered quickly and with minimal perceived effort by the fieldworker. Both interviewers and fieldworkers distributing self-completion questionnaires are also usually asked to complete simple control logs on an hourly basis.

In general, the following guidelines are useful to keep in mind while developing data collection forms and interview scripts:

• Self-administered questionnaires should be clear and self-explanatory.

• Multiple languages should be considered if using a self-completion questionnaire for visitor surveys. The tourist bureau can give the survey planners a sense of the languages most likely to be spoken by visitors.

• A written form should be available for individuals (hearing impaired or non-English speaking) who can fill out a form but not be verbally interviewed.

• Interviewers can be trained to use skips, but the flow of the interview can be disrupted if the questions are not in logical and clear order. The forms typically request general information about the visitor’s trip to the study area, e.g., mode, purpose, arrival day/time, etc., and then specific data about the trips made yesterday. Socioeconomic information is collected at the end, with income generally being the last question.

In addition to the collection forms, a separate form will be used for the hotel information; that is: the name and location of the hotel, the total number of rooms, and the occupancy rate for the night before the survey day, along with the name and title of the manager, in case follow-up data is required.

Data Items

The data items to be obtained can be classified into three categories:

General Visit Data

• Number of persons occupying the respondent’s room (for most survey efforts, all should be interviewed);

• Purpose of the visit, for example:

• Tourist, Convention, Business, Visiting friends, Special events (football game, etc.)

• Local area auto availability:

• Owned, Rented, Borrowed

• Number of nights stayed;

• Mode of arrival into the area (Private Vehicle, Airplane, Bus, Train, Ship);

• Mode of departure from the area; and

• Frequency of visits during past year.

Travel Data (for each trip)

• The address of the starting point of the trip;

• The starting time of the trip;

• The name and address of the place visited, or where the trip ended;

• Arrival time at destination, or what time the trip ended;

• Purpose of the trip, for example:

• Shopping, Sightseeing, Eating, Wandering, Work, Business, Convention, Social, PersonalDON'T NEED BULLET BEFORE THIS LIST

• Mode of travel:

• Driver, Private vehicle passenger, Public Bus/Rail, Taxi, Walk, Bike, Tour Bus, Shuttle BusDITTO

• If private auto, number in vehicle and who is the driver (self, roommate, other);

• Departure time from that place, or next trip begin time; and

• Number of persons in travel party.

Demographic Data

• Age;

• Sex;

• Occupation; and

• Income.

 11.5 Pretesting

A pretest of the developed forms and procedures should be conducted on several sites in various area types and hotel sizes. No matter how straightforward the forms or procedures, the pretest invariably surfaces one or more problems or constraints that were overlooked, from a typing error on the forms to low response rates for one type of hotel or patron. Knowing the potential problems before full-scale field work begins is invaluable, and can avoid insurmountable difficulties or bad data later in the survey process.

NEW PARAIn a pretest, generally several hotels are recruited, surveyed, and analyzed. The staff for the pretest should include the survey planners and field staff who are SELECTED RATHER THAN SLATEDslated to become field supervisors during the full field study. Personally going through the entire set of procedures allows the field supervisors greater understanding of the strengths and weaknesses of the survey design. Depending on the complexity of the survey, the number of sites could be from three to 10 “3 to 10” -Brenda Zhou 10/31/08 3:14 PM . Sufficient visitor returns should be recovered to make estimates of the validity of the data; this requires at least 30 to 50 returns from each pretested hotel.

Each question in a self-completion form is typically analyzed with one of three outcomes: valid, invalid, or blank. A valid response means that the respondent understood the question and gave a logical response within the data range expected. An invalid response means the respondent did not understand the question or gave an illogical response outside of the expected range. For example, an invalid response often arises during an interview when the interviewer does not fully comprehend the basis and use of the question, and becomes confused by an unusual response. A blank response is self-explanatory, although in an interview the surveyors are trained to ask each question, so blanks should not occur, unless as a non-response for some demographic questions (age/sex/income).

Interviews require an edit of each completed form, and a face-to-face debriefing of the interviewer. Any incomplete data are unacceptable unless the respondent terminated the interview or refused to answer. Special codes should be assigned to cover these contingencies. Often the surveyors need to be reminded to get full and complete geographic detail for the origin information. Illogical data often appear during a pretest interview, because it is difficult for the interviewers to complete a form that may seem out-of-sequence. Survey teams should review the flow of questions, the time required to complete each section, and elicit constructive criticism from the interviewers. The more comfortable interviewers are with the forms, the more efficiently and precisely the data will be collected. Changes to the procedures should be documented carefully. If procedures are altered dramatically, the new procedures should be pretested again.

 11.6 Training of Fieldworkers

Interviewers can be secured through a temporary agency or through direct advertisement. Typically, a good interviewer is someone who has done telemarketing or other work involving public interaction. To ensure that candidates can understand and follow instructions for coding, a short test can be used to rate prospective interviewers. Supervisors can be drawn from the interviewer ranks or can be provided by the survey team. An unskilled supervisor can typically manage three to five people “3 to 5 people” -Brenda Zhou 10/31/08 3:14 PM in the field in addition to conducting interviews. A skilled manager should be able to supervise 10 to 15 people.

The interviewers should be trained for at least a day or two prior to the first survey day. At the training session, the purpose of the survey should be explained, the daily schedules outlined, and the forms and procedures demonstrated. Detailed attention should be given to each of the items on the forms, especially definitional items such as “what is a trip?” Mock interviews can be conducted showing professional interview techniques and tools. Each surveyor should complete four or more mock-interviews with a team leader before fieldwork begins to make sure that the interviewers are comfortable with the forms. This role playing during training is an invaluable tool to surface questions and problems before fieldwork begins.

A detailed description of the information that should be provided to interviewers and supervisors during training can be found in Appendix I, which contains a sample procedures manual.

 11.7 Conducting the Survey

Initial Contact and Site Visit

The first step in the full survey procedures is to contact the hotels to be sampled to elicit their participation. The following procedures are recommended:

1. Call each sampled hotel to verify the address and get the manager’s name. A brief explanation, if any at all, is all that is needed for this call.

2. Send a recruiting letter to each sampled hotel. Experience has shown that hotels are most likely to participate in the workplace survey if the first contact letter is sent from the Chamber of Commerce or some other well-known tourism organization, or from a major public agency

(e.g., the mayor’s office). This first contact letter should have a phone number that the hotel manager can call to verify that the survey is legitimate.

3. Interview/recruit the hotel. The first recruiting call should be made two to three weeks after an individually addressed and personally signed letter has been sent. The manager is the first contact to garner the hotel’s participation. When contact is made with him or her, the importance of that hotel’s participation in the survey and the survey procedures will be explained. Agreement to participate will be requested. A full explanation of the procedures during the recruitment call helps reduce late drop-outs which waste resources and time. Conduct as much of the hotel information interview as is feasible to allow the site to be properly scheduled. Keep track of the outcome of each call in the employer contact log.

4. Schedule the survey day. Plotting the sampled sites using a GIS, and recruiting and scheduling sites in the same area for the same day saves on oversight and supervisory time. For in-person interviews, this allows surveyors to carpool even though they may work at separate sites. If the sites are close together, one supervisor can manage oversight and relief of three to five sites (depending on the size and complexity). The survey day is tentative until the site visit is complete, and any special qualities of a particular site are understood.

5. Schedule a personal site visit. Set up a time for a personal visit, for field inspection, and to deliver in-room self-completion questionnaires (one or two days to a week or more before survey day). A personal visit to the hotel to drop off questionnaires and conduct the interview makes a large positive difference in completion rates for each hotel. It is recommended that the use of personal visits, at least for the larger hotels, be considered for the survey.

During the personal visit, conduct field inspection and estimate the number of surveyors required and the locations of survey sites and collection boxes. It is always a good idea to check the site plan with the contact person before completing the survey design. A copy of the site plan with survey/collection positions shown should be left with the hotel manager. The scheduled survey day can be confirmed unless peculiarities of the site require rescheduling.

6. On the designated survey day, set-up the survey station and/or remind the contact person to deliver in-room questionnaires. The site supervisor is responsible for complying with the instructions and placement shown on the site diagram.

The purpose of the personal visit to the site, although resource intensive, is threefold:

• To provide in-room questionnaires to the hotel staff;

• To complete the data needed on the hotel and to answer any remaining questions the manager may have; and

• To review the survey site.

While the first two objectives could be accomplished by telephone and mailout/mailback of questionnaires, experience has shown that a personal visit to each site has a positive impact on completion rates. A site visit is necessary, however, to review the site and develop a strategy.

In-Person Interviews

In-person interviews may be conducted seven days a week between the hours of 6:00 a.m. and noon, which is check-out time at most hotels. A 24-hour travel recall approach for each person in each occupied hotel room is commonly used.

Because the survey fieldworkers for in-person interviews will arrive earlier than the hotel day manager would normally arrive, the night manager should also be contacted, either by the survey supervisor or, preferably by the day manager or other contact person. This is imperative to keep the survey schedule since a night manager may not allow the survey to start in the morning, thereby requiring rescheduling of the entire day.

The survey station is located in a visible place in the lobby, usually near the front desk. Verbal interviews are conducted with guests who are checking out, waiting in the lobby area, or passing through the lobby. All persons in a room will usually need to be interviewed, just as the household survey commonly accounts for each person in the household separately.

For some recent survey efforts, in addition to the standard clipboard and pencils, or lap-top computer if CAPI is used, each interviewer is equipped with a large, foam-board map of the area and a stand-up “Survey Today” sign posted at the front desk. The map will be used by the interviewer to help the respondents locate trip ends and to code the intersecting streets on the travel diary. For a simple self-geocoding survey, the map may have zones already marked out, and the interview can automatically code the zone number as the destination of the visitor’s trip. An example procedures manual for a hotel visitor survey is shown in Appendix J.

Sufficient hotels to accommodate the size of the field staff are scheduled for each survey day. For instance, if the available field crew is two interviewers and one part-time supervisor, each hotel might have to be scheduled for two days to collect sufficient surveys. In this scenario, 35 sampled hotels would take 10 weeks to survey working seven days a week. However, with a field crew of 30 interviewers and three full-time experienced supervisors, four interviewers could be placed at the large hotels and one or two at the small hotels. With eight to 10 crews, the same 35 hotels might only take three to four days to complete.

Although completing fieldwork in a few days sounds enticing, experience has proven that very large field crews can be unwieldy. Errors which are made in the data collection or procedures may not be caught in time to correct or to reschedule the sampled hotel. Crews of 12 to 15 surveyors, with two to three field supervisors, and one overall survey manager work well and allow sufficient personal attention and good quality control.

 11.8 Processing the Survey Results

The processing of the data after collection can be as time consuming, expensive, and prone to error as the field collection. Processing includes:

• Editing;

• Coding and data entry;

• Geocoding origins and destinations;

• Computer edits and corrections; and

• Data expansion.

The editing and coding phase for self-completion or PAPI surveys requires a supervisor or trained editor to scan each returned interview form and related survey document to ensure that the information is complete and legible. The forms are generally produced to be self-coding, with a numeric code circled to represent the answer except in the case of trip origin and destination addresses. The editor checks that each data item has been coded, or if vital information is missing, discards the interview as incomplete. The number of interviews collected at a single hotel are reconciled with the available rooms; for instance, one would not accept 200 interviews from a hotel with 25 rooms. The occupancy rate is checked for reasonableness and completeness; if the data are missing or appear to be incorrect, the hotel is called for verification. NEW PARAOnce the forms are edited, the complete forms are sorted and placed with the hotel information sheet (which includes hotel name and address, manager’s name and phone, number of rooms, occupancy “occupancy rate” -Brenda Zhou 10/31/08 3:15 PM , area-type, and size code) for geocoding and/or data entry.

If the interviewers have collected street addresses and intersection information from the visitors and a GIS is available, automated address matching can be used. Special care needs to be given to the design and collection of address information since visitors are often unaware of where they have been, especially on tours and at special events.

Analysis can be greatly enhanced with additional data to assist in processing the survey, such as a record of special events and special transportation provided during the survey period. Such events can include conventions, shuttle buses run by hotels (including routes, schedules, who runs them , who can use them, cost), hotel tours (eligibility, schedule, cost, itinerary), sports events and any related special transportation, etc. These data can be used to help geocode and analyze the collected visitor information.

The expansion of the hotel survey data to the universe of hotel visitors is based on the total number of hotel rooms available in the study area. As discussed earlier, this information can be obtained from trade associations or similar hotel business groups. The estimation of the expansion factors is a two-step procedure. First, the surveys obtained at each hotel are expanded to the number of occupied rooms at that hotel for that preceding night. Second, the occupied room count for sampled hotels is expanded to total occupied rooms available in all eligible hotels. The basic unit of measurement is the occupied hotel room.

Factoring is the process that weights each completed interview so that the sum of the weights for all completed interviews is equal to the sum of the hotel rooms occupied in the study area. The factoring process consists of identifying an “overall factor” to be applied to the survey results for each hotel.

The completed interviews are first expanded from the number of respondents in each sampled hotel to the number of occupied rooms in that sampled hotel. This first factor is called the response factor. The response factor for a stratum is the ratio of occupied units to completed units in the stratum. One could calculate a response factor for each sampled hotel. However, any sampled hotels for which there were zero completed interviews would need to be aggregated with hotels which did have completed interviews. Either method will yield an answer equal to the total occupied rooms in the stratum. A response factor is appended to each completed interview record.

Because not every hotel room is occupied on a typical day and not every hotel is sampled, the surveys are expanded to represent the total number of occupied rooms for all hotels in each area in each size class. This second factor is called the hotel factor. The hotel factor accounts for travel by visitors in hotels which were not sampled. This factor is also by stratum, and is equal to the ratio of estimated occupied rooms in all hotels in the stratum to the number of occupied hotel rooms in the sampled hotels in the stratum. If the sampled hotels have the same average occupancy factor as the average occupancy rate for the stratum, then the hotel factor can be simplified to be the ratio of total available rooms in all hotels in the stratum to the available rooms in the sampled hotels.

The occupancy rates for total hotel and sampled hotels should be for the same time period, i.e., if the stratum occupancy rate is an annual average, then the annual average for the sampled hotels should be used rather than the observed occupancy rates during the survey. Occupancy rate information is sometimes considered to be proprietary information and not released for competitive reasons, so that assumptions must be made regarding the rate, and if it is not possible to make a reasonable estimate, then basing the hotel factor on available rooms rather than occupied rooms (the same as assuming an occupancy rate of 100 percent) may be necessary. Sometimes, the occupancy rate information is inflated for publicity purposes and therefore the occupancy rate should be judged for reasonableness and reassurance obtained that all hotels are similarly treated.

The hotel factor is a constant for each stratum and does not change for either sample hotels within a stratum or survey day. The hotel factor is appended to each completed interview record.

The overall factor is the product of the response factor and the hotel factor. Once all the factor data is obtained, each sample can have its overall factor calculated in one step using the following calculation:

where:

a = Hotel size category

b = Hotel area-type category

h = Sampled hotel

OF_hab = Overall factor applied to a sample

OR_h = Occupied rooms in sampled hotel for night preceding survey

SR_h = Number of rooms sampled in sampled hotel

TA_ab = Total number of hotel rooms available within a stratum

TAO_ab = Average occupancy rate for all hotels within a stratum

SA_ab = Number of available hotel rooms in sampled hotels within a stratum

SAO_ab = Average occupancy rate for sampled hotels within a stratum

For example, assume that a hotel visitor survey is being conducted. In the study area, there are 10,000 hotel rooms available for rent. The hotels are categorized into size and area-type groups and within the medium hotel category in the central business district (CBD) there are 1,000 total rooms available. They have achieved a 80 percent average occupancy rate during the past year resulting in an average of 800 occupied hotel rooms per night for all hotels in that category. The survey design requires that two hotels be surveyed in this category. These two hotels have 400 rooms available and had an occupancy rate of 75 percent during the past year. On the first day of the hotel visitor survey, valid samples are obtained from guests checking out from a total of 20 rooms at one of these hotels being sampled. This hotel had 160 rooms occupied during the night preceding the morning check-out survey. The two hotels that were sampled in that category had a total of 300 rooms occupied on that night.

Therefore,

OR_h = 160

SR_h = 20

TA_ab = 1,000

TAO_ab = 80 percent

SA_ab = 400

SAO_ab = 75 percent

and,

In this example the response factor is eight “8” -Brenda Zhou 10/31/08 3:15 PM and the hotel factor is 2.67. The overall factor is 21.36 for those 20 samples. The samples for the same hotel and same survey day would have the same overall factors, but the factors would differ among hotels and survey days (with rare exceptions).

Once the data have been expanded, the final tabulations will depend on the designed use of the data. To develop a visitor profile, the purpose of the trip into the study area, the number of nights stayed, whether the respondent rented an automobile, the number of persons in the visitor party, the age, sex, and income of the respondent are all valuable information.

For the development of a distribution/mode split model, the person trip rate per occupied room is a basic data item. The trip rates per occupied room should be examined by area type and hotel size to discern significant differences. The trip rates should be developed by mode, purpose of the trip, income of the respondent, time of day, and land use at destination at a minimum.