ВУЗ:
Составители:
Рубрика:
is the interviewee’s perceptions that guide the conduct of the interview. In comparison, a respondent interview is one
where the interviewer directs the interview and the interviewee responds to the questions of the researcher.
Interviews may be conducted on a one-to-one basis, between you and a single participant. Such interviews are
most commonly conducted by meeting your participant ‘face to face’, but there may be some situations where you con-
duct an interview by telephone. There may be other situations where you conduct a semi-structured or in-depth inter-
view on a group basis, where you meet with a small number of participants to explore an aspect of your research
through a group discussion that you facilitate.
5. Questionnaire is a general term including all data collection techniques in which each person is asked to respond
to the same set of questions in a predetermined order.
The design of a questionnaire differs according to how it is administered, and in particular the amount of contact
you have with the respondents. Self-administered questionnaires are usually completed by the respondents. Such ques-
tionnaires are delivered and returned electronically using either email or the Internet (on-line questionnaires), posted to
respondents who return them by post after completion (postal or mail questionnaires), or delivered by hand to each re-
spondent and collected later (delivery and collection questionnaires). Responses to interviewer-administered question-
naires are recorded by the interviewer on the basis of each respondent’s answers. A growing number of surveys, par-
ticularly in the area of market research, contact respondents and administer questionnaires using the telephone. These
are known as telephone questionnaires. The final category, structured interviews (sometimes known as interview
schedules), refers to those questionnaires where interviewers physically meet respondents and ask the questions face to
face. These differ from semi-structured and in-depth interviews, as there is a defined schedule of questions, from which
interviewers should not deviate.
Prior to designing a questionnaire, you must know precisely what data you need to collect to answer your research
question(s). The validity and reliability of the data you collect depend largely on the design of your questions, the struc-
ture of your questionnaire, and the rigour of your pilot testing. When designing your questionnaire you should consider
the wording of individual questions prior to the order in which they appear. Questions can be divided into open and
closed. The six types of closed questions are list, category, ranking, rating (scale), quantity and grid. Wherever possible
closed questions should be pre-coded on your questionnaire to facilitate analysis. The order and flow of questions in the
questionnaire should be logical to the respondent. This can be assisted by filter questions and linking phrases. The ques-
tionnaire should be laid out so that it is easy to read and the responses are easy to fill in.
Questionnaires must be introduced carefully to the respondent to ensure a high response rate. For self-administered
questionnaires this should take the form of a covering letter; for interviewer-administered questions it will be done by
the interviewer. All questionnaires should be pilot tested prior to collecting data to assess the validity and likely reliabil-
ity of the questions. Administration of questionnaires needs to be appropriate to the type of questionnaire.
6. Virtually all research will involve some numerical data or contain data that could usefully be quantified to help
you answer your research question(s). Quantitative data refers to all such data and can be a product of all research
strategies. To be useful these data need to be analysed and interpreted.
Data for quantitative analysis can be collected and subsequently coded at different levels of numerical measure-
ment. The data type (precision of measurement) will constrain the data presentation, summary and analysis techniques
you can use.
Data are entered for computer analysis as a data matrix in which each column usually represents a variable and
each row a case. Your first variable should be a unique identifier to facilitate error checking.
All data should, with few exceptions, be recorded using numerical codes to facilitate analyses. Where possible you
should use existing coding schemes to enable comparisons.
For primary data you should include pre-set codes on the data collection form to minimise coding after collection.
For variables where responses are not known you will need to develop a codebook after data have been collected for the
first 50 to 100 cases. You should enter codes for all data values including missing data. The data matrix must be
checked for errors.
Your initial analysis should explore data using both tables and diagrams. Your choice of table or diagram will be
influenced by your research question(s) and objectives, the aspects of the data you wish to emphasise, and the level of
measurement at which the data were recorded. This may involve using:
− tables to show specific values;
− bar charts, multiple bar charts and histograms to show highest and lowest values;
− line graphs to show trends;
− pie charts and percentage component bar charts to show proportions;
− box plots to show distributions;
− scatter graphs to show relationships between variables.
Subsequent analyses will involve describing your data and exploring relationships using statistics, such as:
− the mean, median and mode to describe the central tendency;
− the inter-quartile range and the standard deviation to describe the dispersion;
− chi square to test whether two variables are significantly associated;
Страницы
- « первая
- ‹ предыдущая
- …
- 50
- 51
- 52
- 53
- 54
- …
- следующая ›
- последняя »
