Utilization of Statistics in the Academe
A widespread agreement in the scientific community has emerged over the greater importance of statistics in the academe. This emerged from the understanding that the collection, representation and processing of data has far more applications in the modern society. Now, the consensus is the emphasis on building an understanding of concepts and processes in statistics and encouragement of teachers and students to develop awareness of the importance of the capability to evaluate the range of statistical data they face in the academe and their daily lives (Moore, 1997).
This requires the placement of statistics in the wider academic and societal context instead of limiting it to the classroom or professions directly utilizing statistics. In many educational systems, the use of statistics is only marginal and integrated into math courses that deal with statistics in a formal manner and often from an abstract perspective. The result is minimal emphasis on the derivation of meaning of the statistical concepts and interpretation of statistical data. Statistical knowledge assumed practical use in the academe, particularly in the area of research.
The courses offering statistics are those requiring research as part of the curriculum. However, statistics has assumed a wider role in the academe as it has grown in importance in society. The appreciation of the important role of statistics in the academe coincides with the developments in the perspective and practical use of statistics in this context. A wider view of the logical features of administrators of educational institutions, teachers and students reflects on the utilization of statistics in the academe.
The development of statistical reasoning to allow the perception and interpretation of a phenomenon in an objective manner also comprises a determinant of the utilization of statistics in the academe. The discussion considers the different uses of statistics in the academe based on the new consensus and considers the actual utilization of statistics in the academe to generalize conclusions on the topic. Concept of Statistics in the Academe A common understanding of statistics in the academe is the aggregate processes of gathering, representing and analyzing data (Weiss & Hassett, 1991).
As a separate discipline, statistics covers the design of data collection instruments keeping into consideration the use of measures to reflect variables. The summary or synthesis of information to support understanding of an object, case or situation is also another statistical process. The derivation of conclusions comprises another process. Estimation of characteristic gaps and prediction of future occurrences are also within the ambit of statistics. (David, Pisani & Purves, 1997) These processes find use in the academe due to the link with the forms or phases of learning. Statistics has two general branches depending on the purpose.
One is descriptive statistics, which is the process of organizing and presenting data to provide information on objects or situations (DeGroot & Schervish, 2001). This finds application in almost all course curriculums because many areas of study seek to inform. However, descriptive statistics are only able to provide information and not necessarily the derivation of conclusions. The other branch emerged, inferential statistics, to address this weakness. Inferential statistics is the process of estimating, predicting and deciding on populations based on information from a sample (Casella & Berger, 2001).
This also finds application in the different areas of learning, particularly in the treatment of data to derive meaning for application in actions or practical processes. The wide use of statistics in learning led to the significance of statistics as a tool in various academic disciplines including education, engineering, medicine, physics, psychology and sociology. Apart from classroom learning, statistics also provide uses in different areas of society such as the management and decision-making in business firms, policy development for industries, and effective practice in governance.
Due to the widespread use of statistics, the development and practice of statistical thinking is important even with a limited use of statistical methods. Since knowledge of statistics commences in the academe, understanding the uses of statistics in the context of the academe becomes important as a determinant not only of its use in this area but also greater implication on the further use of statistics in the societal context as an offshoot of academic learning. Education reflects on the society so that the appreciation and use of statistics in the academe has implications on the role of statistics in society.
(Abelson, 1995; Tijms, 2004) As a tool, understanding the uses of statistics in the academe also points to the benefits derived by the academe from statistics together with the issues or areas for improvement. This is necessary to enhance the role of statistics in education and realize the wider implication of statistics in societal life. Developments in the Integration of Statistics in the Academe Statistics first emerged in philosophy with efforts to use probability statistics (Tijms, 2004) in proving the existence of God (Hald, 1990).
John Arbuthnott was the first to employ probability calculations to reject the null hypothesis based on the existence of a small probability from data. De Moivre expanded the use of probability statistics on the phenomenon of chance relative to design in 1718. Then again, in 1802, Paley attempted to use statistical measures of the occurrences of God in nature to substantiate arguments of the existence of God. (Hald, 1998) The use of statistics expanded to the natural sciences when Charles Darwin introduced the theory of natural selection, which involved a very high degree of improbability.
Although, his arguments led to conclusion of improbability instead of probability, it was apparent that statistical methods have achieved use in the natural sciences. Moreover, many arguments emerged in the natural sciences such as Richard Bentley’s argument in favor of probability of the existence of God to support design over chance by citing the alignment of the planets as unexplainable solely by chance. The arguments became richer as Isaac Newton contributed his explanation of the likelihood that the alignment of the planets and natural occurrences happened by choice and not by chance.
(Heyde & Seneta, 2001) However, the use of statistics largely revolved around the issue of the existence of God by using occurrences in nature. The significance of statistics expanded into the social sciences as many attempted to explain political phenomenon using statistical tools. Laplace and Quetelet were student and teacher that employed statistical explanations in politics by tutoring royalty (Johnson & Kotz, 1997). There was need for royalty to understand the present and predict the future in order to make strategic political decisions. The prediction of the future is difficult because of a number of variables.
However, by using probability statistics over these variables, it becomes easier to understand options and responses to likely occurrences in politics. This involved statistical application in the social context. During the 1900s, statistics became a part of formal education as a part of mathematical courses. While this formalized the inclusion of statistics in the academe, this also made statistics a largely abstract learning. The normal distribution curve emerged as introduced by Quetelet (David & Edwards, 2001) but its application was in an abstract setting such as using theoretical data to explain occurrences.
The exception is the use of statistics in research since the data handled came from empirical situations. The integration of statistics in the academe influenced mathematical courses and areas of study requiring research. It was only recently, with the common agreement on the wider use of statistics in a wider societal context that statistics received greater recognition, in terms of its utilization, in the academe. Utilization of Statistics in the Academe The use of statistics in the academe is two-fold. One is as an area of learning.
The other is a tool in administering educational institutions. These uses of statistics in the academe reflect the wider perspectives of the role of statistics in learning and in managing learning institutions. Statistical education emerged to reflect the use of statistics as an area of learning (Bryce, 2002). Education statistics emerged as a term encompassing the role of statistics in the areas of education, such as supporting learning and administration of learning institutions (Kotz & Johnson, 1997). Statistics Education
Statistics deserves a central role in the learning curriculum. This finds support in the wide reflection of statistics in the domain of natural science, social science, and technology. This requires strong literacy in statistics. Statistics also finds specific expression in various curriculum topics based on the understanding of statistics as involving not only number and geometric representations but also as a process (Kotz, & Johnson, 1997). Statistics is not a self-contained area of study but rather linked to different learning contexts (Snee, 1993).
Teaching and learning statistics requires a clear understanding of the different uses and importance of statistics in different fields. Statistics comprise a basic course and a specific application in different courses (Cobb, 2007). As a basic course, statistics learning includes descriptive statistics, a limited understanding of probability, and inferential statistics (Blumberg, 2001). The issue emerges in learning probability. Probability refers to the likelihood of occurrence of an object or phenomenon that supports the predictive value of statistics (Tijms, 2004).
Apart from the limited discussion of probability in basic statistical course, a recommendation is expansion of traditional concepts of probability to encompass random variation instead of focusing solely on formal probability. (Ballman, 1997) Many educators of statistics in the area of research emphasize on the process of data collection, modeling of variation, graphical presentation, design of data collection instruments, problem resolution, and system enhancements but with little stress on the probabilistic contexts (Hogg, 1991; Moore, 1997).
The result is courses and textbooks that commence statistics learning from data analysis instead of deriving inferences by applying probability theories. Although, statistics learning still involves concept of probability, these may not be enough to support student understanding of variation and its role in statistics. Moore (1997) specified the need to select the basic concepts of probability necessary in furthering statistical thinking. There is need to understand variation and its quantification to support a more learned use of statistics.
Konold and Kazak (2008) further explained that existing courses in statistics do not fully support the development of students of conceptual knowledge and intuitive skills needed to support effective statistical reasoning. This is a use of statistics not thoroughly explored in the academe. Ballman (1997) suggested that prioritizing an in-depth understanding of statistical concepts such as probability and the development of reasoning skills tied to a contextual perspective furthers the impact of statistics learning beyond the course.
Focusing on random variation and its importance in statistics would support this objective. An explanation for the selection of the topics taught in basic statistics subjects is the functional perspective of statistics relative to the course (Blumberg, 2001). Since courses such as economics, business and education have particular use of statistics, the basic statistics subjects only focused on ensuring the adoption of these functions by focusing on knowledge of descriptive statistics to interpret numbers and inferential statistics to fill in unknown aspects of data.
In the case of business courses, statistics serves a mathematical purpose in measuring variables and filling in the missing characteristics of a particular population or phenomenon. However, there is a limited appreciation of probability and more so the concept of random variation and its implications on the data and interpretation of data. The functional perspective towards the inclusion of statistics subjects in different course curriculums may serve the purpose of providing students with the knowledge they need to complete courses. However, this limits the use of statistics in furthering learning.
If statistics were to assume a central role in the learning outcomes and processes in educational institutions to ensure wider utilization in the social context, then there is need to focus on intuition and reasoning provided by studying random variation as learning contributions of statistics (Ballman, 1997). Apart from comprising a basic subject, statistics also find strong use in research. Curriculums requiring completion of research projects include statistics courses on the design of data collection instruments such as survey questionnaires and experimental methods.
While statistics subject as prerequisite of research focus on the research design, data collection and data analysis, data collection is often a neglected area in practical exercises. Mackisack (1994) stressed on the importance of students of research to experience data collection in the learning setting before conducting actual research, especially in experimental studies. However, many basic courses in statistics do not provide practical exercises in actual data gathering due to time constraints or the greater focus on concepts in statistics and the analysis of data (Anderson-Cook & Dorai-Raj, 2001).
While statistics has a strong appreciation in the field of research, there are areas of weakness, such as the development of practical knowledge on using statistics from actual experience. Limited practical knowledge on statistics hampers the utilization of statistics in the academe and in the professional context (Blumberg, 2001). Many students perceive statistics as a theoretical exercise without practical value (Hogg, 1991). One compelling reason is the lack of practical experience on statistics in taking statistics subjects.
Even if students know the concepts, there is a gap between conceptual knowledge and practical application (Batanero, 1994). Many students taking research subjects, as part of the curriculum, experience difficulties in conducting the practical aspects of research such as data collection. The difficult experience creates a negative perception of statistics so that after the research course, the conscious use of statistics as an area of learning and learning tool ceases.
Relative to teachers, the lack of practical aspect of statistics makes it more difficult to achieve learning outcomes. Statistics is in itself an area of learning as well as a support tool for learning in different areas. It is difficult to develop appreciation of statistics without its practice aspect. The concept of probability would receive better appreciation as a concept but appreciation of its practical use involves actual experience of probability or realization of actual experience of probability.
Many teachers are unable to connect theory and practice in teaching statistics. This leads to a limited appreciation of statistics on the part of students and limited achievement of learning goals on the part teachers and learning institutions. This undermines the value of statistics, not only as a learning tool but also as a tool in continuous learning beyond the academe and in the practice of professions (Romero et al. , 1995). The practical aspect of statistics is a useful tool but implemented in a limited sense in the academe.
The practical aspect of statistics is an area for improvement in the utilization of statistics in the academe. Statistics also finds utilization in objective articulation and decision-making in different fields. Objectivity is important in the academe because this has implications on the ability to harness facts, which are then necessary to support decisions and actions. Even the areas of study not formally requiring research as a course also have use for statistics as a means of achieving objectivity not only the derivation of data but also in the use of data to support decision-making.
Although there is common understanding that absolute objectivity requires balance with the subjectivity of interpretation, statistics ensures objectivity of data to ensure a certain degree of objectivity in decision-making. This use found expression in statistical decision theory. This has close relations to decision-making on risks and risk analysis (Gigerenzer, 2002) with high application in the learning outcomes of courses involving random variability such as engineering, business and medicine.
In the area of engineering, risk decision-making finds support from statistics in providing the probability of risk in the different options of the various areas of a project. In business, risk decision-making is important in the management of operations and implementation of strategies. In medicine, risk decision-making finds support in statistics in deciding over alternative treatments and other interventions. However, not many textbooks in these courses mention or discuss in-depth statistical decision theory.
Many curriculums also include basic statistics in the curriculum but fail to incorporate the theory in the statistics subjects. (Bordley, 2001) The result is the limited utilization of statistics in different courses when statistics can provide groundwork for risk decision-making applicable not only in achieving effective learning outcomes but also in developing the foundation for the effective transition into professional practice. Education Statistics
Apart from the utilization of statistics in learning, statistics also has use in deriving statistical data on various aspects of the academe to identify problems and the corresponding areas for improvement. The core use of statistics in education statistics is the measurement of performance (Gal & Garfield, 1997). Athanassopoulos and Shale (1997) explained that statistics supports the evaluation of the performance of educational institutions based on its vision and goals and the comparative performance of educational institutions relative to educational policies or standards.
By deriving statistical data on cost efficiency and outcome efficiency, the data was able to provide information on the issues of administrative accountability, value for monetary investments, and cost controls. Using performance measures on cost efficiency and outcome efficiency showed that six out of the forty-five universities in the United Kingdom had satisfactory performance. Various performance measures have emerged focusing on different aspects of performance. The emergence of these statistical measures comprises valuable tools to the academe in evaluating its performance.
Interpretation of statistical data clarifies the problem faced by educational institutions as well as point to the areas for improvement. Webster and Braswell (2006) explained the use of statistics in the evaluation of curriculum effectiveness. The study compared two reading curriculums in terms of the extent that these generate measurable reading outcomes. The study employed three reading assessment tests to measure the learning outcomes from the two reading curriculums. Results showed different measures of reading outcomes in using the different tests.
Although different results emerged from the tests, these reflected the extent of reading outcomes derived from the curriculum. In addition, the study also showed the existence of curriculum bias, with some tests biased towards a particular curriculum depending on the alignment between the learning outcomes of the reading curriculum and the aspects measured by the test. Using more than one test provides a better idea of the performance of a curriculum. Albert (2000) used statistical measures to assess the effectiveness of lessons in inferential statistics.
This showed the areas of strengths and weaknesses of the lessons and teaching methods. An area for improvement is enhancing the quality of data used in the classroom (Finzer et al. , 2007)The National Center for Education Statistics (1999) employed statistics in determining teacher performance by considering teaching quality in the public school setting, particularly preparedness in integrating technology in teaching. A self-assessment survey showed that close to half of the teachers surveyed considered themselves not full prepared in integrating technology in teaching.
This implied a problem on the part of teaching that deserved resolution to ensure the quality of education. Villar and Alegre (2008) discussed the role of statistics in measuring the professional development of teachers in the online context. Results showed that lessons on online curriculum development and online teaching strategies positively and strongly contributed to the professional development of teachers. Statistical measures determine the performance of teachers and teaching competence to support improvements in teaching practices in the academe (Everson & Garfield, 2008).
Miller, Imrie and Cox (1998) discussed the utilization of statistics in measuring student performance through tests, assignment and other evaluation measures to come up with a grade for the course. The grade is a single digit but this has statistics written all over it. The grade determines the relative ranking of the student in class. The grade also has various components or measures such as a portion for tests, recitations, assignments, and other measures of learning. The utilization of statistics in measuring the performance of students comprises the most obvious application and benefit of statistics to the academe.
Again, the purpose of employing statistics in student performance is to assess learning outcomes and areas that might require improvement such as the learning process, teaching strategy or the curriculum. Conclusion The developments in the perspective of statistics led to two uses of statistics in the academe. One is the utilization of statistics in statistics education. This involves the perspective of statistics as a distinct area of learning and statistics as a support for learning. As a distinct area of learning, statistics contributes informative and inferential value to objects, cases or situations.
As support for learning in the different courses, statistics contributes instrument design, data collection and data analysis tools particularly in the area of research. A broader use of the statistics in the academe is the development of intuitive skills and statistical reasoning. However, there is varied utilization of statistics in the academe. Common practice is the integration of basic statistics in courses but only limited statistical tools for research. A neglected area is the utilization of statistics to foster intuitive skills and statistical reasoning to support of practical benefits such as in risk decision-making.
The other is the utilization of statistics in education statistics or the use of statistics to derive data measuring performance of educational institutions, curriculums, teachers and students. The utilization of statistical measures focuses on determining performance relative to standards to point out problem areas and areas for improvement. The extent of use of statistics in the academe has implications on developments in education and furtherance of the role of statistics in the wider societal context.
Abelson, R. P. (1995). Statistics as principled argument. Hillsdale, NJ: Erlbaum.
Albert, J. (2000). Using a sample survey project to assess the teaching of statistical inference. Journal of Statistics Education, 8(1). Retrieved February 1, 2009, from http://www.amstat.org/publications/jse/secure/v8n1/albert.cfmSample Essay of Edusson.com