Statistics and Research

Some writers refer to statistics as the technology of the scientific method. Since it has been noted that experimental and survey investigations are integral parts of the scientific method and further, that these procedures lead to the use of statistical techniques, such a conclusion is without a doubt a reasonable one. If this is so, then it is quite obvious that the research worker should become more intimately acquainted with the basic concepts and procedures which make up the body of statistical theory and methodology. More and more articles published in the various scientific journals contain statistical analyses in support of their arguments if the reader is not aware of the principles underlying these techniques, he is in no position to appreciate fully the validity of the conclusions drawn. 

The purpose of any experimental design is, of course, to provide the maximum amount of information about the effects to be studied. It is desirable, naturally, to keep the design as simple as possible while still performing an efficient job within the limitations of the budget of time and money provided for the study at hand. Fortunately, the most efficient designs are usually capable of simple analyses. This is one very important reason why the statistician should be consulted in the early stages of any proposed research project he can often supply a fairly simple design which is both efficient and economical. 

We have said that the purpose of any experimental design is to provide the maximum amount of information at minimum cost from this it is evident that the design of experiments is a subject which involves not only statistical methodology but also economic considerations. If a most efficient design is defined as one which provides the greatest amount of information, every experiment should incorporate both efficiency and economy into the design failure to do so may mean a poor design, and this means wasted time, effort, or money, perhaps all three. 

Before presenting examples of some of the statistical techniques commonly employed in food research, it is necessary to comment on the fundamental concepts and to outline briefly the methods of calculation. To do this, we will consider three major subdivisions of statistics (1) descriptive statistics (2) problems of estimation and (3) testing of hypotheses. The last two of these constitute what is generally referred to as problems of statistical inference, and it is with them that the statistician is usually concerned. 

Perhaps the simplest descriptive measure used in research is some sort of average. The term some sort of average is used because more 

---

Statistics and research do not yet connect ephedra use with adverse personal or social consequences. How-... 

Boston, MA Massachusetts Office of the Commissioner of Veterans Services, Agent Orange Program, Massachusetts Department of Public Health, Division of Health Statistics and Research. 

Statistics and Research Methods link on British Medical Journal (BMJ) site... 

Pharmacists also have a role as pharmacoeconomic analysts in comparing medications. Sometimes the investment in a more expensive medication reduces other costs to the HMO, but the data must be collected and tracked for these assumptions to be proved. To perform these analyses successfully, the pharmacist must be able to evaluate and interpret statistics and research articles. A sound understanding of pharmacoeconomic principles is also essential. 

The statistical and research section of the Bituminous Coal Institute, of Washington, D. C., collects data from all available sources concerning production, consumption, and exports of coal fuel equipment and production facilities. These statistics are included in the Bituminous Coal Annuah 39) and other publications of the society. 

The oil companies, Norwegian Oil and Gas Associations, the trade unions and the NPD enrolled statistics and research reports to underpin their views. 

A challenging task in material science as well as in pharmaceutical research is to custom tailor a compound s properties. George S. Hammond stated that the most fundamental and lasting objective of synthesis is not production of new compounds, but production of properties (Norris Award Lecture, 1968). The molecular structure of an organic or inorganic compound determines its properties. Nevertheless, methods for the direct prediction of a compound s properties based on its molecular structure are usually not available (Figure 8-1). Therefore, the establishment of Quantitative Structure-Property Relationships (QSPRs) and Quantitative Structure-Activity Relationships (QSARs) uses an indirect approach in order to tackle this problem. In the first step, numerical descriptors encoding information about the molecular structure are calculated for a set of compounds. Secondly, statistical and artificial neural network models are used to predict the property or activity of interest based on these descriptors or a suitable subset. 

Probability Theory.—To pursue our study of methods of operations research, a brief, although incomplete, and somewhat abstract, presentation of ideas from probability theory will be given. In part it shows that mathematical abstraction and rigor are also in the nature of operations research. Illustrations of this topic will be given in later sections. We then give a longer discussion of maximization and minimization methods and in turn illustrate the ideas in subsequent sections. Probability and statistics and optimization methods are two major sources of operations research tools. 

H. W. Kuhn and A. W. Tucker, Non-linear Programming, in J. Neyman, ed., Second Berkeley Symposium on Mathematical Statistics and Probability, University of California Press, Berkeley, 1951 Thomas L. Saaty, Mathematical Methods of Operations Research, McGraw-Hill Book Co., New York, 1959. 

Jonathan G. Levine, Office of Post-marketing and Statistical Science Immediate Office, Center for Drug Evaluation and Research, Food and Drug Administration Rockville, MD 20857, USA. 

Source Liu, B. The Quality of Life in the United States J970 Index, Rating, and Statistics, Midwest Research Institute. Kansas City. Mo.. 1973. 

Frequency domain performance has been analyzed with goodness-of-fit tests such as the Chi-square, Kolmogorov-Smirnov, and Wilcoxon Rank Sum tests. The studies by Young and Alward (14) and Hartigan et. al. (J 3) demonstrate the use of these tests for pesticide runoff and large-scale river basin modeling efforts, respectively, in conjunction with the paired-data tests. James and Burges ( 1 6 ) discuss the use of the above statistics and some additional tests in both the calibration and verification phases of model validation. They also discuss methods of data analysis for detection of errors this last topic needs additional research in order to consider uncertainties in the data which provide both the model input and the output to which model predictions are compared. 

Abecassis, V., Pompon, D. and Truan, G. (2000) High efficiency family shuffling based on multi-step PCR and in vivo DNA recombination in yeast statistical and functional analysis of a combinatorial library between human cytochrome P450 1A1 and 1A2. Nucleic Acids Research, 28, E88. 

Data from American Psychiatric Association. Diagnostic and Statistical Manual of Mental Disorders, 4th ed., Text Revision. Washington, DC American Psychiatric Association, 2000 382-401 Goldberg JF, Harrow M, eds. Bipolar Disorders Clinical Course and Outcome. Washington, DC American Psychiatric Press, 1999 and Goodnick PJ, ed. Mania Clinical and Research Perspectives. Washington, DC American Psychiatric Press, 1998. 

Peter Filzmoser was bom in 1968 in Weis, Austria. He studied applied mathematics at the Vienna University of Technology, Austria, where he wrote his doctoral thesis and habilitation, devoted to the field of multivariate statistics. His research led him to the area of robust statistics, resulting in many international collaborations and various scientific papers in this area. His interest in applications of robust methods resulted in the development of R software packages. J ( He was and is involved in the organization of several y scientific events devoted to robust statistics. Since... 

Center for Drug Evaluation and Research. Guideline for the Format and Content of the Clinical and Statistical Sections of an Application, FDA, Rockville, MD, 1998. 

Andrew P Grieve, Statistical and Consulting Centre, Pfizer Global Research and Development, Sandwich, UK... 

---