Critically Evaluating Quantitative Research - Assignment Example

?Critically Evaluating Quantitative Research The ification and categories of variables There are two types of variables, according to the UNESCOadvisory for the conduct of social research. Variable may be classified either as quantitative and continuous, or qualitative and discrete. A quantitative or continuous variable is one in which the variates differ in magnitude; examples of these are income, age, GNP, and so forth. On the other hand, a qualitative or discrete variable is one where the variates differ in kind rather than in magnitude, such as marital status, gender, nationality, and so on (UNESCO, 2011). The use of the terms “quantitative” and “qualitative” in categorizing variables should not be mistaken with the use of these same terms to describe research approaches. The quantitative and qualitative variables described below both occur within quantitative research; qualitative research takes into account no such variables because it deals with explanation and interpretation of phenomena and do not categorize information in the form of variables (Hopkins, 2008; Hunter & Leahey, 2008; UNESCO, 2011). Quantitative or continuous variables may be classified as interval-scale, continuous ordinal, or ratio-scale. Interval-scale variables have order and equal intervals, are linear, and may assume positive or negative values. Continuous-ordinal variables may or may not be linear (i.e., it may be exponential, logarithmic or other monotonic transformation); they therefore lose their interval-scale property, and the observations are therefore best expressed by their ranks which is the only certain parameter. Ratio-scale variables are continuous positive measurements on a nonlinear scale, such as the growth of bacterial population; in such a case, the population grows or multiplies at a ratio, for equal time intervals (UNESCO, 2011). Qualitative or discrete variables are also known as categorical values. Any one particular discrete variable can only assume a finite number of values, categories or codes. Discrete variables may be classified as either: (1) nominal, (2) ordinal, (3) dummy, (4) preference, and (5) multiple response variables (UNESCO, 2011). How measurement is performed in quantitative research Here the word “measurement” is taken to mean the quantification of empirically observed information. The process of measurement may involve different procedures, depending upon the thing being measured (Gay, 1996). Variables in the physical sciences or areas of inquiry are usually measured according to a deterministic or positivist manner; this means that the measurements obtained are detectable and verifiable by the five senses, so they are more or less objective (Kincheloe, 1998; Colwell, 2006; Palmo, Weikel & Borsos, 2006; Hammersley & Atkinson, 2007) . On the other hand, measurements of variables that have a bearing in the social sciences are usually probabilistic in nature, which means that the actual measure may only be conjectured at with a certain degree of accuracy that is less than 100 per cent, and therefore prone to some subjectivity in the determination. An example of this is psychometrics, the field of study that measures the social and psychological attributes pertaining to certain phenomena (Rust & Golombok, 1999; Rao & Sinharay, 2007; Furr & Bacharach, 2008). Since the attributes measured are essentially internal processes that occur in the mind, they may be observed only from their external manifestations, or what are thought to be such, and from thence rendered into measurable quantities qualified by probability. Measurement is therefore indirect rather than direct (Kincheloe, 1998; Colwell, 2006). For directly observable things, measurement is straightforward, needing only physical counting or the use of such measuring tools as gauges, scales or meters. For those quantities that may not be directly measured, there are different approaches. One is the use of proxies (e.g. stand-ins); these are manifestations other than the variable being actually measured, that are regarded are such reliable substitutes as to be ideal stand-ins (Lewis-Bech, Bryman & Liao, 2004; Wahlberg, 2009). For instance, the age of a tree may not be directly measured if the time it was not plant was not a matter of record. Therefore, researchers resort to measuring the number of tree rings to determine its age. The width of the tree rings are also used as a proxy for the ambient conditions in the environment at various stages in the past, whether there was more or less rainfall than average, or whether the growing seasons were warmer or cooler than usual (Vaganov, Hughes & Shashkin, 2006). Changes in the environment or cataclysmic events are also measured in the substrata of the earth or layers on mountainsides (Huggett, R J, 1997). The use of such proxies should be discerned with care, however. The best proxies are those that have been established by clear and convincing relationships between the proxy and the thing actually being measured. There are times, however, when the relationship is one that is not invariable and which may change over time. In market research, for instance, the amount of total consumption is often taken as a proxy measure of consumer wealth, and vice versa (Mayer, 1972; Owen, 1986). However, consumer purchases are likewise influenced by the amount of credit made available, and the confidence of the consuming public to spend. Therefore, it is entirely possible that at certain extreme situations, credit or confidence may actually have a greater impact upon consumption than the wealth of the consumers. Another example is the use of key performance indicators, which are proxies for organizational success (Ng, Kee & Brannan, 2011), and the quantification of political risk based on the modelling of multiple dependent sources (Clark & Tunaru,2003), which essentially differs from another quantified model for political risk developed specifically for power plant projects (Sachs, et al.,2008a) and infrastructure projects in certain regions (Sachs, et al., 2008b). How quantification is a social practice used to serve organisational and political purposes The particular allure of quantification is that it lends credence to what is sometimes an incredible position. This is because the provision of quantitative evidence is generally taken to make a more convincing argument than mere narrative (Kane, 1995; Abela, 2008; Conrad & Serlin, 2011). People generally perceive quantified data as objective data, and therefore not subject to the interpretation of a subjective mind. In actuality, quantification is not seen as so far divorced from qualitative assessments. “It amounts to substituting equations for descriptions and quantities for qualities; yet the shift from qualitative to quantitative reasoning is in no sense a jettisoning of philosophy. On the contrary, it marks a decisive advance” for mathematics (Bachelard, 1984, p.68). There is therefore a strong link between quantification and qualification, and that quantitative information may be constructed in support of a previously-arrived-at qualitative conclusion. How this may be convincingly done is by manipulation in different, marginally acceptable, ways bordering on falsification (Chalmers, 1998, p.59). One way can be in the manner of classification or a real, empirical data. “A classification is a spatial, temporal, or spatio-temporal segmentation of the world.” (Bowker, 1999, p.10). Classification systems have the following attributes: (pp.10-12) (1) There are consistent, unique, classificatory principles in operation. However, people disagree about their nature, they may ignore or misunderstand them, or routinely confuse different and even contradictory principles (Bowker, 1999). (2) The categories are mutually exclusive. However, mutual exclusivity is often impossible in practice, partly also because of the ambivalence and disagreement about the coverage of objects in a category (Bowker, 1999). (3) The system is complete, providing total coverage of the world it describes. However, there may be meritorious reasons for excluding certain possible inclusions that would make the system more comprehensive (Bowker, 1999). No one classification scheme organizes reality for everyone (Bowker, 1999, p.41). The example given here is that while traffic light systems organize traffic flow with the use of red (stop) and green (go), these do not affect the blind for whom a different system must be used. “[T]here is more at stake – epistemologically, politically, and ethically – in the day-to-day work of building classification systems and producing and maintaining standards than in abstract arguments about representation” (Bowker, 1999, p.10). Because of the vagueness of the nature of certain variables, they may be used in a wide range of instances to support a variety of theories. Chalmers (p.59-86) relates how Karl Popper (1979) pointed out how the induction process sometimes leads to false conclusions, when a specific, testable prediction is constructed around a theory, but the premise of the test is either logically skewed or misleading. “Falsificationists freely admit that observation is guided by and presupposes theory” (Chalmers, 1998, p.60). In the case of organizations or political entities which have an interest in advancing their own views or advocacies – “ theories” – the classification and quantification of information in many cases is more self-serving because their design is dictated by strong partial interests. It is not in every case that such design is fraudulent; for instance, the business firm exercises some discretion in choosing aspects of the accounting system (i.e., accrual over cash basis, accelerated over straight line depreciation, etc.) which would tend to project its accounts in a more favourable light (Chen & Hsu, 2008). Occasionally, this exercise of prerogative, exceeds the imprecise boundaries of propriety such that investors are misled by the figures, as in the case of Enron and, more recently, Lehman Brothers and the banking industry in general (New York Times, 2011a). In other areas of organizational performance, the arbitrariness of identifying and measuring key intangible performance indicators also has encountered some controversy (Ng, Kee & Brannan, 2011). Government likewise tends to make use of quantitative manipulations to present its performance in a better light. The recent bailout schemes of the U.S. president which Congress repeatedly refused to pass comprise one such case, where the items in the same set of appropriations are classified as necessary expenses by the executive, but labelled as exorbitant by the legislature, with each proffering their own seemingly irrefutable arguments (New York Times, 2011b). References Abela, A V 2008 Advanced Presentations by Design: Creating Communication That Drives Action. Pfeiffer: A Wiley Imprint, San Francisco, CA Bachelard, G 1984 The New Scientific Spirit. Beacon Press, Boston Bowker, G C & Star, S L 1999 Sorting Things Out: Classification and Its Consequences. MIT Press, Cambridge, Mass. Chalmers, A F 1998 What Is This Thing Called Science? Open University Press, Buckingham Chen, J-H & Hsu, S. C 2008 “Quantifying Impact Factors of Corporate Financing: Engineering Consulting Firms.” Journal of Management in Engineering, Apr 2008, Vol. 24 Issue 2, p96-104; DOI: 10.1061/(ASCE)0742-597X(2008)24:2(96) Clark, E & Tunaru, R 2003 “Quantification of Political Risk with Multiple Dependent Sources.” Journal of Economics & Finance, Summer2003, Vol. 27 Issue 2, p125 Colwell, R 2006 MENC Handbook of Research Methodologies. Oxford University Press, New York Conrad, C F & Serlin, R C 2011 The SAGE Handbook for Research in Education: Pursuing Ideas as the Keystone of Exemplary Inquiry. 2nd edition. SAGE Publications, Inc., Thousand Oaks, California Furr, R M & Bacharach, V R 2008 Psychometrics: An Introduction. Sage Publications Gay, L R 1996 Educational research: Competencies for analysis and application. Merrill, Upper Saddle River, NJ Hammersley, M & Atkinson, P 2007 Ethnography: Principles in Practice. Routledge, Abingdon, Oxon Hopkins, W G 2008 “Quantitative Research Design, Perspectives/Research Resources,” Sportscience, vol. 4, issue 1. Accessed 20 January 2012 from http://www.sportsci.org/jour/0001/wghdesign.html Huggett, R J 1997 Environmental Change: The Evolving Ecosphere. Routledge, London Hunter, L & Leahey, E 2008. "Collaborative Research in Sociology: Trends and Contributing Factors," American Sociologist vol. 39, pp. 290–306 Kane, E 1995 Seeing for Yourself: Research Handbook for Girls’ Education in Africa. Economic Development Institute of the World Bank. The World Bank, Washington D.C. Kincheloe, J L 1998 How Do We Tell the Workers? The Socioeconomic Foundations of Work and Vocational Education. Westview Press, Cumnor Hill, Oxford Kuhn, T S 1961 “The Function of Measurement in Modern Physical Science”, in The Road Since Structure: Philosophical Essays, 1970 to 1993, Kuhn, T S; Conant, J; & Haugeland, J (eds.), 2000, University of Chicago Press, Chicago Lewis-Beck, M S; Bryman, A; Liao, R F 2004 The Sage Encyclopedia of Social Science Research Methods: Vol.1. SAGE Publications Ltd., London Mayer, T 1972 Permanent Income, Wealth, and Consumption. University of California Press. Los Angeles, CA New York Times 2011a “Lehman Brothers Holdings, Inc.” New York Times. 26 August 2011. Accessed 20 January 2012 from http://topics.nytimes.com/top/news/business/companies/lehman_brothers_holdings_inc/index.html New York Times 2011b “Economic Stimulus – Obama Jobs Bills” New York Times, 24 Oct 2011. Accessed 20 January 2012 from http://topics.nytimes.com/top/reference/timestopics/subjects/u/united_states_economy/economic_stimulus/index.html Ng, H S; Kee, D M H; Brannan, M 2011 “The Role of Key Intangible Performance Indicators for Organisational Success.” Proceedings of the International Conference on Intellectual Capital, Knowledge Management & Organizational Learning, p779-787 Owen, D 1986 Money, Wealth, and Expenditure: Integrated Modelling of Consumption and Portfolio Behaviour. Cambridge University Press, Cambridge Palmo, A J; Weikel, W J; & Borsos, D P 2006 Foundations of Mental Health Counselling. Charles C. Thomas, Publisher Ltd., Springfield, Illinois Rao, C R & Sinharay, S 2007 Psychometrics. North-Holland, an imprint of Elsevier B.V., Amsterdam, The Netherlands Rust , J & Golombok, S 1999 Modern Psychometrics: The Science of Psychological Assessment, 2nd Edition. Routledge, London Sachs, T; Dalla Rosa, A; Tiong, R K L 2008 “Case Study on Quantifying the Impact of Political Risks on Demand and Pricing in a Power Project.” Journal of Structured Finance, Summer 2008, Vol. 14 Issue 2, p77-84 Sachs, T; Tiong, R & Wagner, D 2008 “The Quantification and Financial Impact of Political Risk Perceptions on Infrastructure Projects in Asia.” Journal of Structured Finance, Winter 2008, Vol. 13 Issue 4, p80-104 UNESCO 2011 “Types of Variables” IDAMS Advisory Guide. Accessed 20 January 2012 from http://www.unesco.org/webworld/idams/advguide/Chapt1_3.htm Wahlberg, A Driver Behaviour and Accident Research Methodology: Unresolved Problems. Ashgate Publishing, Farnham, Surrey Vaganov, E A; Hughes, M K; & Shaskin, V 2006 Growth Dynamics of Conifer Tree Rings: Images of Past and Future Environments. Springer Berlin Heidelberg New York Read More