Selecting a Sample

User's Guide: Hospital Survey on Patient Safety Culture

The population from which you select your sample will be staff in your hospital or hospital system. You either can administer surveys to everyone in your population of hospital staff, or you can administer surveys to a subset or sample of your population. Although surveying all staff may seem simple or most desirable, the additional time and resources required may eliminate that option. If you decide to administer surveys to all hospital staff, this section is not applicable. If you are uncertain or have decided that you will administer surveys to a sample of hospital staff, however, this section tells you how to select your sample. 

When you select a sample, you are selecting a group of people that closely represents the population so that you can generalize your sample's results to the broader population. To select your sample, you need to determine which hospital staff you want to survey and the number of staff that need to be surveyed.

Determine Whom To Survey

All staff in your hospital or hospital system represent your population. From this population, you may want to survey staff from every area of the hospital, or you may want to focus on specific units, staffing categories, or staffing levels. There are several ways to select a sample from a population. Several types of samples are described below. Select the type that best matches your needs, taking into account what is practical given your available resources.

  • Staff in particular staffing categories. You may be interested only in surveying staff in specific staffing categories, such as nursing. With this approach, you may select all staff within a staffing category or select a subset of the staff. This approach alone, however, may not be sufficient to represent the views of all staff in the hospital.
  • Staff in particular areas/units. You may want to survey staff in particular hospital areas or units, such as OB/GYN, Emergency, Pharmacy, etc. The list below presents three examples of ways staff can be selected using this approach, listed in order from most to least representative of the entire hospital population:
    • A subset of staff from all areas/units (most representative).
    • All staff from some areas/units.
    • A subset of staff from some areas/units (least representative).
  • A combined approach. If possible, we recommend surveying staff using a combination of the two sample types just described. For example, you may be interested in surveying all nurses (a staffing category), but only a subset of staff from every hospital area (excluding nursing). Using a combination of sample types allows you either to oversample or selectively sample certain types of staff in an attempt to thoroughly represent the diversity of hospital staff.

Return to Contents

Determine Your Sample Size

The size of your sample will depend on whom you want to survey and your available resources. While your resources may limit the number of staff you can survey, the more staff you survey, the more likely you are to adequately represent your population.

To determine your sample size, think about your budget and how many responses you want to receive (i.e., your response goal). Because not everyone will respond, you can expect to receive completed surveys from about 30 percent to 50 percent of your sample. Therefore, to reach your response goal, your sample size should be at least twice the number of responses you want to receive. If the number of responses you eventually want to achieve is 200 completed surveys, be prepared to administer surveys to at least 400 staff members (an example of sample selection is presented at the end of this chapter).

Budget Considerations 

Your budget may determine the number of staff you can sample. To reach an adequate number of responses, you will need to send initial surveys as well as followup surveys to those who do not respond to the first survey. Your budget also should take into consideration additional costs for materials such as envelopes and postage, if you are mailing surveys.

Return to Contents

Compile Your Sample List

After you determine whom you want to survey and your sample size, compile a list of the staff from which to select your sample. When compiling your sample list, include several items of information for each staff member:

  • First and last name.
  • Internal hospital mailing address, or home or office addresses if surveys will be mailed.
  • E-mail address (if conducting a Web-based survey or using E-mail to send prenotification letters, Web survey hyperlinks, or reminders).
  • Hospital area/unit.
  • Staffing category or job title.

If you are selecting All staff in a particular staffing category, hospital area, or unit, no sampling is needed; so simply compile a list of all these staff. If you are selecting a subset or sample of staff from a particular staffing category, hospital area, or unit, you will need to use a method such as simple random sampling or systematic sampling.

Simple Random vs. Systematic Sampling

Simple random sampling involves selecting staff randomly, such that each staff member has an equal chance of being selected. Systematic sampling essentially involves selecting every Nth person from a population list. 

For example, if you have a list of 100 names in a particular group and need to select 25 to include in your sample, you would choose to begin at a random point on the list and then select every 4th staff member to compile your sample list.

Thus, if you began with the first person on the list, you would select the 4th, 8th, 12th, 16th, etc. staff member, up to the 100th staff member, compiling a total of 25 names in your sample list.

Return to Contents

Review and Fine-tune Your Sample

Once you have compiled your sample list, review the list to make sure it is appropriate to survey each staff member on the list. To the extent possible, ensure that this information is complete, up-to-date, and accurate. Points to check for include:

  • Staff on administrative or extended sick leave.
  • Staff who appear in more than one staffing category or hospital area/unit.
  • Staff who have moved to another hospital area/unit.
  • Staff who no longer work at the hospital.
  • Other changes that may affect the accuracy of your list of names or mailing addresses.

If you believe there are certain staff who should not receive the survey or that your records are not complete, selectively remove people from the list. If you remove someone from the list, add another staff member in her/his place.

Revising Your Sample

You may review your list and realize that you would like to survey an additional staffing category or hospital area that was not part of your initial sample. In this case, you will need to add to your list.

Selecting a Sample—An Example

Suppose you work in a 200-bed hospital with 1,400 staff members. Nursing is the single largest staffing category, with 1,000 staff. Smaller hospital areas or units have a combined total of 100 non-nursing staff, and larger hospital areas or units have a combined total of 300 non-nursing staff.

  • Determine Whom To Survey. You decide to survey a sample of nurses, all non-nursing staff from smaller hospital areas or units, and all non-nursing staff from the larger hospital areas or units. You therefore choose a combination approach to select your sample.
  • Determine Your Sample Size. Your response goal is 450 completed surveys, and this goal fits within your budget. Therefore, your sample size will be 900 staff members (expecting a 50% response rate).
  • Compile Your Sample List. Your final sample list of 900 staff members consists of:
    1. Nursing-From the total of 1,000 nurses, a sample of 500 nurses is selected (250 expected completes). The sample was selected as follows:
      1. A list of the 1,000 nurses was produced.
      2. Using systematic sampling, every other nurse on the list was selected to be included in the sample until 500 names were selected (1,000 total nurses divided by 500 nurses needed = every 2nd nurse).
    2. Smaller hospital areas or units—All 100 non-nursing staff (50 expected completes).
    3. Larger hospital areas or units—All 300 non-nursing staff (150 expected completes).
  • Review and Fine-Tune Your Sample. When verifying the contact information for the initial sample of 900 staff, you found that 25 staff no longer work for the hospital and should be dropped from the list. You may or may not want to replace these names. To replace the names, randomly select additional staff from the same staffing categories or hospital areas as the staff who were dropped.

Return to Contents
Proceed to Next Section

Current as of September 2004
Internet Citation: Selecting a Sample: User's Guide: Hospital Survey on Patient Safety Culture. September 2004. Agency for Healthcare Research and Quality, Rockville, MD. http://www.ahrq.gov/professionals/quality-patient-safety/patientsafetyculture/hospital/userguide/hospcult3.html