In this section, you will hear part of a lecture on research methods. The passag

In this section, you will hear part of a lecture on research methods. The passage will be read twice. For questions 21 -30, complete the sentences and notes in no more than three words for each answer. Remember to write the answers on the answer sheet.
    Good afternoon, ladies and gentlemen. Welcome to this auxiliary lecture on research methods. This lecture is not aimed specifically at one particular course but is a general lecture that will be relevant to any student who must conduct research into a topic for his or her course. For most of you, this will be the research that you need to do in order to write your dissertations and thesis.
    It has been said that first world societies are no longer industrial societies but information societies. That is, our major problems and tasks no longer mainly centre on the production of goods and services necessary for survival and comfort, but rather require a prompt and accurate flow of information on preferences, needs and behaviour. This is why surveys today are regarded as being so important.
    What, then, is a survey? Today the word survey is used most often to describe a method of gathering information from a sample of individuals. This way, the results can be projected from the sample to the larger population.
    An important consideration at the start is to decide how large a survey to perform. The sample size required for a survey partly depends on the statistical quality needed, and the size of the total population of the area in question.
    I’d like now to look at some of the types of surveys available to us, and the focus here will be on methods for surveying individuals and companies. Mail, telephone interview, and in person in interview surveys are the most common types of surveys. In person interviews can be conducted in offices, homes or on the street.
    Mail surveys are relatively cheap to conduct, but obtaining a decent response rate is the major problem with them. Mail surveys are usually most effective when directed at particular groups, such as subscribers to a specialized magazine or members of a professional association.
    Telephone interviews are an efficient method of collecting some types of data and are being used increasingly. They lend themselves particularly well to situations where timeliness is a factor and the length of the survey is limited. For students such as you, though, cost will be an issue. In person interviews in a respondent’s home or office are good when complex information is to be collected, but they can involve a great deal of travelling around. Street interviews are also useful as they are easy to do, but the sampling is not very scientific. We also need to look at the content of surveys, which can focus on opinions and attitudes or on factual characteristics or behaviour. Many surveys combine two types of questions: open ended questions, for example, " why do you feel that way?" or closed, for example, "Do you approve or disapprove?" Questionnaires may be very brief, consisting of a few questions, and take five minutes or less-or they can be quite long-requiring an hour or more of the respondent’s time. Also because changes in attitudes or behaviour cannot be reliably ascertained from a single interview, some surveys employ a " panel design," in which the same respondents are interviewed on two or more occasions.
    There are also certain ethics to be looked at in conducting surveys. Some of you will realize that the information you compile is probably of value to companies operating in that particular sector. Therefore, you must always bear in mind a few guidelines.     Surveys should be carried out solely to compile statistical information about a subject. They should not be designed to produce predetermined results or as a ruse for marketing and similar activities. The industry standard for all reputable survey organizations is that individual respondents should never be identified when survey findings are reported. All of the survey’s results should be presented in completely anonymous summaries, such as statistical tables and charts.