The questionnaire is probably the most commonly used research method in psychology, and other social sciences. It is simple versatile and cost effective. They can provide quantitative or qualitative data depending on whether closed or open questions are used. Closed ended formats help to clarify the response required from the respondent, reducing ambiguous answers, however, they also rule out unexpected responses and create artificial, forced choices. Open-ended formats encourage the respondent to give detailed, personal information.
The reason for the continued use of closed questions in questionnaires is due to the fact that they can be easily analysed compared with open questions. In the case of questionnaires interviewer bias is reduced and respondents feel less inhibited when answering. Questionnaires are quantifiable and large sample sizes allow the researcher to generalise more easily. There are two main factors that determine how relevant data obtained from research is. Theories derived from research are evaluated and criticised in order to establish how relevant they are to everyday life. Research should be reliable and valid.
Reliability, when applied to psychological tests has two meanings. One refers to the stability of the test over time, known as test-retest reliability. It is measured by correlating data obtained from conducting a test on two separate occasions. If the data correlates closely then the test is said to be reliable. The second is known as internal consistency. Most researchers aim to make their tests as internally consistent as possible, meaning that if one part of a test is measuring one variable, in order for internal consistency to be high, the other parts of the test should be measuring the same variable. If internal consistency is low then the test cannot be measuring the same variables consistently.
Guilford (1956) and Nunnally (1978) argued that if a test is to be valid then its internal consistency must be high. (cited in Kline, 2000) However, Cattell (1977) argues that high internal consistency is contrary to validity. This is because all tests measure variables of some description and at least one item or subject in the test must be measured differently. A test is said to be valid if it measures what it claims to measure. There are various ways of showing whether a test is valid, however, unlike when testing reliability, there is no single type of validity coefficient for a test. As Vernon (1960) argued, a test is always valid for some purpose and therefore is more valid in some circumstances than in others (cited in Kline, 2000).
The term ‘face validity’ is used if a test appears to be measuring what it has claimed. There is no logical relationship between face validity and real validity. In some conditions there may be a positive correlation, however, in other cases face validity can be used in criticism. Face validity can increase the motivation of participants and encourage them to complete the tests accurately – essential if the test is to be valid (Kline, 2000) Psychology generally believes itself to be scientific, because, like science, it aims to gather knowledge and answer questions. However, the differences between the psychoanalytic approach
and the behaviourist approach means that defining psychology as a scientific discipline is not as straightforward. The psychoanalytic approach, adopted by Sigmund Freud (1856 – 1939) struggled to adopt a scientific method. This is due to the fact that the ‘workings of an unconscious mind’ is not an observable subject. The psychoanalytic theory also faces problems with replicability, reliability and empiricism. However, the behaviourist approach uses the scientific method very successfully.
Behaviourist research is characterised by rigorous control and replicability. Their theories are readily testable and their subject matter lends itself to testing. (Malim & Birch 1998) The preceding information would suggest that on the whole psychology is very close to being a scientific discipline. The four main aims of science are objective description of events, accurate prediction, reliable understanding and control of events. When conducting research psychologists always attempt to meet these guidelines, therefore aiming to research in a scientific manner.