Embedded Files
involved in data collection procedures explicit. Issues such as failure to manage relationships in the field may affect the rigour of the work: this should be acknowledged by the researchers. In addition, there may be ethical issues to consider. Exercise 13 What data collection methods were used in the study described by King & Jensen? Are there any flaws in the data collection methods or the reporting of them? Make some notes and then turn to the discussion in Section 6. 3.11 Data analysis As data are analysed very differently in quantitative and qualitative studies, the two types of research will, again, be discussed separately. Quantitative data analysis Quantitative data are usually analysed using statistics. A full account of statistical analysis, (including the relevant mathematical calculations) cannot be given in this document. You may need someone with existing statistical knowledge to help you to understand research studies that have employed complicated statistical techniques such as multiple regression or factor analysis. page 28 Research awareness in nursing and midwifery: a workbook Statistics can be divided into two main types: descriptive statistics and inferential statistics. Before describing different types of statistics, however, it is necessary to discuss the concepts of levels of measurement and frequency distribution. Measurement is the assignment of categorization codes to data. There are four levels of measurement that can be applied to data: nominal, ordinal, interval and ratio. Nominal measurement is used for data that can be categorized by name only. In nominal measurement, although each category is assigned a numerical code or value, no category ranks higher or lower than another. Some examples are given below. Sex: 1. male; 2. female. Blood group: 1. O positive; 2. O negative; 3. A positive; 4. A negative; 5. B positive; 6. B negative; 7. AB positive; 8. AB negative. Ordinal measurement categorizes data by rank as well as name. The distance between the ranks cannot, however, be quantified precisely. The categorization of pain as mild = 1, moderate = 2 and severe = 3 can be used as an example: although severe pain is greater than moderate pain, we cannot say exactly how much greater it is. The next level is interval measurement. This is where there is a fixed numerical interval between each point on a scale but no meaningful zero point. The Intelligence Quotient test (like many educational and psychological tests) is based on an interval scale. A person scoring 120 scores higher than a person scoring 110 who, in turn, scores higher than a person scoring 100. The score of 110 is equidistant between the higher and the lower score but there is no meaningful zero on the scale (average intelligence is set at 100). The highest level of measurement is ratio measurement. This is the same as interval measurement except that there is a meaningful zero on the scale. Age can be categorized in terms of ratio measurement, a person who is 35 being half the age of someone who is 70. Ratio comparisons of this type cannot be made about interval data. Distinctions between different levels of measurement are important because they determine which statistical tests can be used on the data. This will be discussed in greater detail below. When critiquing research documents, you should decide whether the researchers have identified the levels of measurement appropriate to certain types of data. In particular, four- or five-point attitude scales ranging from “strongly agree” to “strongly disagree” are sometimes treated as if they are based on equal intervals. The resulting data may, thus, be treated as interval data When we wrote our first book, Fundamental Aspects of Research for Nurses (2010), we drew attention to the Prime Minister’s Commission on The Future of Nursing and Midwifery in England, published on 2 March 2010, which stated that nurses and midwives must renew their pledge to society to deliver high-quality, compassionate care, thus placing quality of care at the top of the healthcare agenda. We wrote our book for student nurses who were committed to taking the first steps in research awareness in light of both this report and the changes taking place within nurse education, namely the move to an allgraduate profession. From September 2012 all pre-registration nursing programmes will have a degree-level target, requiring students to understand, use and undertake research as a prerequisite for thinking innovatively to influence system design in healthcare, and to impact positively on service delivery. Of course, midwifery has been ahead of nursing in this respect, having made a similar move in 2010, so we are delighted to have broadened the scope of this book to embrace both nurses and midwives in a joint research enterprise! In the intervening two years, and with the change of government to a coalition in May 2010, the NHS has undergone some of the most radical restructuring in its history. The changes, completed in 2012, include the disassembling of the Strategic Health Authorities, the abolition of Primary Care Trusts, and the move by all NHS trusts to Foundation Trust status, with the commissioning of healthcare services becoming the responsibility of GPs working within Clinical Commissioning Groups (CCGs), overseen by the NHS Commissioning Board. With regard to education and training, a
Google Sites
Report abuse