Statistics is the study of how to collect numerical information, its organization, in-depth analysis, and the eventual interpretation of numerical information from data (Longnecker, 2001). It is the science of learning from various data, and of measuring, communicating uncertainty, controlling phenomena, thus providing the navigation that is essential for the course taken by advances in science and society. Statisticians normally apply statistical thinking and the methods of statistics to a wide range of social, scientific, and business endeavors. The areas where statistics is applied include biology, economics, engineering, marketing, medicine, education, sports, public health, and psychology among many others (Rice, 2006). Many economic, military, social, and political decisions have to be made using statistical techniques. The techniques may include design of experiments to seek to gain approval of a drug that is newly manufactured. In the study of statistics, the various types are systematically introduced, and the evaluation of statistical results is probed.
Something to keep in mind regarding statistics is that statistics inferences are not more accurate than the data they are based on. If the data is accurate then, the inferences will also be accurate. Moreover, interpretation of statistical results should be done by someone who understands the various methods used. The subject matter being tackled must also be understood.
Various terms used to describe statistical information and data include individuals and variables. Individuals refer to the people and objects employed in the study. Variables are the various characteristics of the individual to be measured or observed. Variables encompass things like weight, height, size, length, distance, volume. For example, if we want to do a study about the people who have climbed Mt. Kilimanjaro, then the actual people who made it to the top in the study qualify to be individuals. The variables that can be measured from them or be observed might include weight, race, income levels, and gender.
n statistics variables may be quantitative or qualitative. A quantitative variable has a value or a certain numerical measurement for which operations such as addition, multiplication, division, and subtraction make sense. Elsewhere, a qualitative variable describes an individual into a category or group such as black or white, male or female, adult or child ( Longnecker, 2001). Other terms used include population data and sample data. In population data, the variable comes from each and every individual of interest. The survey is inclusive of all the individuals. In sample data, the variable is only from some of the individuals of interest. For example, if a TV station wants to know the proportion of TV viewers in New York who watch a new program on the station at least once a week and it asks a group of a thousand people in New York who watch the program. The individuals in the study are New York residents. The variable is the number of viewers of the newly launched program. The data comprises a sample. The a thousand people represent a specific sample from the entire population of New York. The variable being studied is quantitative in nature since it requires a specific number of people. The actual number of viewers will be given. The number of viewers determined represents the quantitative data that is of interest to the TV station.
In statistics, I have also learned the various sampling techniques. They include stratified, systematic, cluster, and convenience sampling techniques. In stratified sampling, the population being analyzed is divided into a common characteristic such as age, class, gender, or race (Marx et al., 2006). A random sample of each division is often taken according to their percentage of the population. For example, the information can be divided by race and a survey of a number of randomly selected individuals from each race is carried out. This is carried out often in the same proportion they occur in the overall population.
Systematic sampling is normally used when the elements of the population are arranged in a natural sequential order. For example, the analysis involving taking every third person coming out of the cafeteria and asking them some questions.
Cluster sampling is used extensively by governments and organizations involved in research. A sample of pre-existing sections or clusters is randomly selected. The sections often used are the geographic ones. This sampling technique uses population sample for a survey. Every member of the cluster is religiously included in the survey. An example of cluster sampling can be like to randomly select twenty-five schools and survey every student attending these schools.
As for convenience sampling, data used is conveniently and readily obtained. For example, one can be instructed to take a walk and survey the first fifty people that will be walking in their direction.
Statistics may be descriptive or inferential. Descriptive statistics are the numbers used to summarize and describe data (Marx et al., 2006). Data refer to information that has been collected from an experiment, a historical record, or a survey. In analyzing birth certificates of different people statistic night the percentage of certificates issued in Nairobi or the average age of the mothers of the children. Any other number chosen to compute also falls under the category of descriptive statistic for the data from which the statistic is computed. Descriptive statistics just describe different phenomena. They do not generalize beyond the data available. Examples of descriptive data include average salaries for various jobs in say Zambia or number of medical doctors in African countries. Analysis of such data will offer insight into African society and the pay structures in various occupations.
We also studied about inferential statistics. This type of statistics is concerned with drawing conclusions about a particular population from a sample (Longnecker, 2001). This is done through random sampling, followed by making informed inferences. These inferences are made about the mode, median and mean. Other aspects used are dispersion and standard deviation. For example, we can use inferential to make inference from the sample data what the population might be thinking. Thus, general conditions are used in the formulation of inferences.
In statistics, one has to formulate a hypothesis and test its efficacy. A hypothesis is essentially the existing relationship between variables (Marx et al., 2006). The two major types are null and alternative hypothesis. A null hypothesis predicts absence of a relationship between two variables for example “there is no relationship between income earned and education attained”. Alternative hypothesis states the actual expectation like “A large number of health professionals signify high-quality healthcare”. Hypothetical testing entail making decisions using data from a survey, experiment to whether the found evidence is enough to accept or not enough to support the hypothesis.
In data analysis and evaluation, the collected data is turned into meaningful information. Statistical data can be analyzed using graphs, making summary of statistical measures like mean and median (Longnecker, 2001). The variability of spread of the data encompassing range, standard deviation, and variance are employed. Methods employed in evaluation include establishing relationship between variables, modeling through use of linear regression, time series analysis.
The statistics course had great value. I now about the various types of statistics, where and how statistics and the various statistical sampling techniques. The knowledge gained can be applied comfortably in our daily lives enabling us live happy lives.
References
Longnecker, M., & Ott, R. (2001). An introduction to statistical methods and data analysis. ISBN-13, 854576151.
Marx, M. L., & Larsen, R. J. (2006). Introduction to mathematical statistics and its applications. Pearson/Prentice Hall.
Rice, J. (2006). Mathematical statistics and data analysis. Cengage Learning.
