STATISTICS

Definition and meaning Definitions of Statistics have changed over the years as has the subject itself, always evolving to accommodate for new factual findings. Some of these definitions over the years are: Statistics is the science of counting. (A.L. Bowley) Seeing as this definition was fast becoming outdated, as statistics came to be known as more than just taking censuses or the counting of places or animals, A.L. Bowley redefined his position thus Statistics is the science of averages, since it had evolved to include data analysis and interpretation. Alas, statistics was in no way limited to average alone. There were many other statistical tools like measure of variation, measure of correlation, measures of independence and so on. Thus this definition also fell short of wholeness as it was weak and incomplete and was buried in the past from whence it came. Statistics is the science of estimates and probabilities. (Prof. Boddington) Trying to succeed where Bowley failed, the good professor came closer to the modern concept of statistics. However, statistics outgrew this definition as well, as there are some areas of statistics in which probability is not used. The definition that came closest to the modern accepted definition was; Statistics is the science of statistics is the method of judging collection, natural or social phenomena from the results obtained from the analysis or enumeration or collection of estimates. (W.I. King) But the most appropriate definition to modern times so far is: Statistics are the numerical statement of facts capable of analysis and interpretation and the science of statistics is the study of the principles and the methods applied in collecting, presenting, analysis and interpreting the numerical data in any field of inquiry. By this definition ergo, it means that statistics is the science comprising methods which are used in collection, analysis, interpretation and presentation of numerical data. These methods are used to draw conclusion about the population parameter. For example, if we want to have a study about the distribution of weights of students in a certain class. We will first collect the information on the weights which may be obtained from the records of the college or from the students directly. The large number of weight figures will confuse us. In this situation we may

arrange the weights in groups such as: 50 Kg to 60 Kg 60 Kg to 70 Kg and so on and find the number of students fall in each group. This step is called a presentation of data. We may still go further and compute the averages and some other measures which may give us complete description of the original data. Elements The elements statistics are population, sample and statistics inference. Population is the set of all items of interest in a statistical problem. It is quite usually very large and sometimes even overly large. Contrary to the conventional use of the word, population in statistics does not necessarily refer to a group of people. It may, for instance, refer to the diameters of ball bearings produced at a large plant. Even in situations, involving a population is called a parameter. Sample is a set of data drawn from the population. A descriptive measure of a sample is known as a statistic. We use statistics to make inferences about parameters. Because populations are almost always very large, investigating each member of the population would not be practical and would be very expensive. It is more convenient to take a sample from the population of interest and draw conclusions thereupon or make estimates about the entire population based of information provided by the sample. Statistics inference is the making of estimates, predictions or decisions about populations based on sample data. The conclusion and estimate are not always going to be correct. This is why a measure of reliability is built into the statistical inference. These measures are the confidence level and the significance level. The central statistics of the general linear model are the algebraic mean, variance, followed by the coefficients of covariance and correlation. The concepts of co relational analysis can be extended to include the coefficients of statistical significance as t and F, obtained in the course of computations of t-test and analysis of variance. These univariate and bivariate statistical methods are usually expressed by using the summation notation, but can be expressed as well by using the matrix algebra notation.

Characteristics Statistics are aggregates of facts: An individual isolated number cannot be called statistics. Statistics deal among groups and not individual data. For example, performing an analysis one a single car crash, childhood, etc. cannot be statistics. However, the collective of figures relating to crashes, childbirth, deaths, etc. over different periods or otherwise areas can be named statistics. Statistics are expressed numerically: Statistics are just the numerical arguments of facts. So, the arguments shown in numbers of decreased in order to numbers can be rated as statistics. For instance, ages of 4 persons might be termed as teenage, middle age and aged. They are never distrust, statements of facts, although it will not be named statistics since they are not numerically expressed. However, if these declarations of facts are expressed in numerical measurements, say, 12yrs, 25yrs and 56yrs. After that they will be named statistics of ages. Statistics can be affected by many causes: The statistical figures should be affected by a big number of factors. For instance, cost of items are affected by stock, need, import/export and tallness of people also are affected by tallness of their parents, etc. Statistics are numerated or approximated based on a sensible standard of accuracy: A fairly good standard of exactness is essential in both counting and estimation because there cannot be a regular standard of exactness that applies to all kinds of statistical studies. For instance, in measuring of weight, a fractional part of a gram can be neglected. But then in measuring nasal bone length, you cannot even ignore the smallest fraction of an inch. Statistical data must be comparable to each other: In order to make a legitimate comparison, the gathered data must be set in relationship to each other. In other words the data must be homogenous. For example, the ages of husbands and wives at the time of marriage is comparable and can be placed in relation to each other. Even so, the eye colour of students and their marks in mathematics cannot be equated because the eye colour of a person has no bearing with their intelligence level.

Functions

Statistics helps in the collection of appropriate quantitative data. Statistics helps us to effectively plan statistical inquiry in any field of study. Statistics helps us to provide a better understanding and also exact description of a phenomenon of nature. Statistics helps us to present complex data in a suitable tabular, diagrammatic and graphic form for better comprehension of data. Statistics helps us to draw valid inferences, along with a measure of their reliability about the population parameters from sample data. Statistics helps us to understand the nature and pattern of the variability of a phenomenon through quantitative observations.

Areas and Scope The following are a few of the many areas of business in which statistics can be helpful. Marketing and sales: Companies have lots of information on past contacts with customers and their results. These data can be retrieved for guidance on how and when to better reach customers or potential customers in the future. One example is the difficult decision of when a store should reduce or increase its prices.

Finance: mining of financial data can be useful in forming and evaluating strategies and hedging risk. In stock markets alone, there are many companies about 2900 listed on the New York exchange and about 4800 companies listed on the Nasdaq stock market.

Product design: what particular combination of features are customers ordering in larger than expected quantities. The answer could help you create product to a group of potential customers who would not take the trouble to place special orders.

Production: imagine a factory running 24/7 with thousands of partially completed units each with its bar code, being carefully tracked by the computer system.

Fraud detection: fraud can affect many area of business including consumer finance, insurance and net works.

Limitations Statistics deals only with groups and aggregates as statistics laws are true on average. Statistics are aggregates of facts. So single observations are not statistics, thus statistics cannot be performed on single data. Statistical analysis cannot be applied to heterogeneous data. The individual data must be relevant to each other. In other words, they must all come together in homogeneity. This means that you simply cannot perform statistics on data that have absolutely nothing to do with each other. If sufficient care is not exercised in collecting, analyzing and interpretation the data, statistical results might be misleading.

Statistics is of a technical nature. Although it is easy to interpret statistical data once you grasp the concept, one must first have quite the knowledge of statistics in order to do so, thus, only a person who has an expert knowledge of statistics can handle complex statistical data efficiently.

Some errors are possible in statistical decision making. Particularly the inferential statistics involves certain errors. We do not know whether an error has been committed or not. Therefore, provision must be made for errors all the time, but still, to what degree must the provisions be made, and how accurate will the data once the provisions are made? Statistical methods are best applicable on quantitative data. Not that they cant be applied to qualitative data, but they prove a more accurate method of analysis when dealing with data in quantitative form.

Statistics in business and management Marketing: Statistical analysis are frequently used in providing information for making decisions in the field of marketing it is necessary first to find out what can be sold and the ability to evolve suitable strategy, so that the goods sold to the ultimate consumer. A skilful analysis of data on production, purchasing power, man power, habits of compotators, habits of consumer, transportation cost should be consider to take any attempt to establish a new market. Production: In the field of production statistical data and method play a very important role. The decision concerning; what to produce? How to produce? When to produce? For whom to produce is based largely on statistical analysis. Finance: The financial organization discharging their finance function

effectively depend very heavily on statistical analysis of peat and tigers. Banking: Banking institutions have found it increasingly necessary to establish research department within their organization for the purpose of gathering and analysis information, not only regarding their own business but also regarding general economic situation and every segment of business in which they may have interest. Investment: Statistics greatly assists investors in making clear and valued judgment in his investment decision in selecting securities which are safe and have the best prospects of yielding a good income. Purchase: The purchase department, in discharging its function, makes use of statistical data to frame suitable purchase policies such as what to buy? What quantity to buy? What time to buy? Where to buy? From whom to buy? Accounting: Statistical data are also employed in accounting particularly in auditing function, the technique of sampling and destination is frequently used. Control: The management control process combines statistical and accounting method in making the overall budget for the coming year including sales, materials, labour and other costs and net profits and capital requirement.