Lessons Learnt in Statistics
Statistics refers to scientific study of analyzing and collecting data, mostly, in large quantities for purposes of inferring positions in a while from those in representative sample. It is concerned with the scientific techniques of organizing, collecting, analyzing and interpreting information with the purpose of making and describing informed decisions (Descriptive statistics, n.d). Statistics are subdivided into 2 major subdivisions; descriptive statistics, n.d). Statistics can be divided into major subdivisions: descriptive statistics (dealing with presentation of numerical data or facts either in tabular or graphical form) and inferential statistics (involving techniques that make inferences based on the entire population on the basis of observations made on samples collected. The study of statistics is also worth learning, especially for those aspiring to undertake different kinds of research projects in future as the acquired level of lessons and knowledge learnt is quite overwhelming.
This major describes main features of collecting information quantitatively, (Mann, 1995) or quantitative description itself. The aim is to summarize sample data instead of using it to learn about the population the data sample is assumed to represent. This is an implication that descriptive statistics is not developed based on the theory of probability (Dodge, 2003).
Descriptive statistics is a presentation of the learner with measures which are used to describe given sets of data including the measure of dispersion and variability of the variables (which includes variance (or standard deviation), maximum and minimum variables values, kurtosis and skewness) as well as measure of central tendency (comprised of mean, media and mode) of variables (Descriptive statistics, n.d). Descriptive statistics is applicable in univariate, statistical (involving description of distribution of a single variable which includes the central tendency) and bivariate analysis (Babbie, 2009; Trochim, 2006).
This is applied best in testing of certain hypothesis. It is used in description of system procedures which are applied in process of drawing conclusions from datasets that are obtained from systems affected by random variation. This is inclusive of random sampling, random experimentation as well as observational errors (Dodge, 2003; Upton, 2008). Propositions made on population are based on data obtained from a population of interest through random sampling. Inferential statistics has 2 major kinds of errors which are the result of the means that is used in conducting the process. These errors are: sampling error (random error and chance) and sample bias (constant error as a result of inadequate design).
Hypothesis Development and Testing
The key of statistics at all times is a hypothesis. So as to prove whether or not the hypothesis is worth, it is tested at the end of the process. The process of hypothesis development starts with identification of research question. A good topic of research is one that changes focus from that of a general area of interest to a narrow and more defined issue (Hypothesis Development and Testing, n.d). The question of research can be formulated based on general issue of interest area, the issues the researcher wants to explore as well as the importance of issues.
This is then followed by the hypothesis of the formulation. A hypothesis is supposed to be understood in terms that are simple, like a statement showing relationship between 2 variables that the researcher has an intention of studying. Often, they are thought as predictions that can confirm a given theory if confirmed or proven. After formulation of the hypothesis, the process of testing starts immediately. This is supposed to start with identification of dependent and independent variables that can be used for purposes of testing the hypothesis. The values of the variable dependent which can be used to test the hypothesis. Values of the dependent variable are predicted from independent variable. The independent variable is therefore presumed on the cause of the study.
While identifying the dependent and independent variables, it is vital to take into consideration the question of cause. Cause is defined as the event like change in a variable resulting in occurrence of another event. The dependent variable is then looked at as a trend of time selecting it as an indicator. So as to test relationship between the independent and dependent variable, a researcher is supposed to make a scatter report I excel and correlation coefficients are recorded.
Selection of an Appropriate Statistical Test
This is a very preeminent process in analysis of research data. Using the wrong statistical tests can be witness in instances where parametric statistical tests are used in testing data not in compliance with normal distribution or paired tests that are used for unpaired data. So as to select the ideal statistical test, a researcher is supposed to consider the type of data involved whether it follows normal distribution or not and lastly, the objectives of the study (Manly, McDonald & Thomas, 1992).
Evaluation of Statistical Results
After collection and analysis of data, it is important to do an evaluation of the validity of statistical data. Evaluation of statistical results can be used in analysis and interpretation of categorical or numerical data. To do this, all relevant data for a given sample and parameter needs to be pooled. This is an implication that all data obtained should be used in the calculation of statistical parameters. The standard deviation observed and sample mean are calculated. Evaluation of statistical data involves identification of P-value of any given data. The value is responsible for measuring difference between null baseline or hypothesis and the alternative hypothesis that is being tested. The P-value makes it possible for the researcher to establish whether null hypothesis can be valid or not. The researcher has to select appropriate statistical tool in order to facilitate the process of evaluation. The kind of statistical tool to be used depends on the kind of statistical data that needs to be evaluated (Veves, n.d)
Statistics has helped learners to a great length by acquitting them with basic skills and knowledge which are as highlighted above. In a nutshell, knowledge acquired in statistics familiarizes the learner with terminologies used in the field. The learner is able to graphically represent data and understand the basic distributions of frequency. Knowledge acquired in inferential and descriptive statistics equips the learner with professional knowledge on how to measure central tendency of a given set or group of data or ungrouped data. Lastly, the learner is able to evaluate skewness and dispersion of a given set or group if data and/or ungrouped data.
This essay was written by an expert at PremiumEssays.net. We offer quality and unique essay writing services to help you achieve the best results on your academics. Place an order with us today and we will deliver an essay that meets your expectations.
Babbie, E.R. (2009). The Practice of Social Research (12th Ed.). Wadsworth.
Descriptive statistics. (n.d.). 16th January 2014. Retrieved from http://www.acad.polyu.edu.hk/~ machanck/lectnotes/c1_des1
Descriptive statistics. (n.d.). 16th January 2014. Retrieved from http://www.investopedia.com/ terms/d/descriptive_statistics.asp#axzz2DxCoTnMM
Dodge, Y. (2003). The Oxford Dictionary of Statistical Terms.
Hypothesis development and testing. (n.d.). 16th January 2014. Retrieved from http://www.ssdan.net/kidscount/modules/osborn_hypothesis
Manly, B. F., McDonald, L., & Thomas, D. L. (1992). Resource selection by animals: statistical design and analysis for field studies. Springer.
Mann, P.S. (1995). Introductory Statistics (2nd Ed.).
Trochim, W.M. K. (2006). “Descriptive statistics”. Research Methods Knowledge Base. Retrieved 16January 2014.
Upton, G., Cook, I. (2008) Oxford Dictionary of Statistics
Veves, A. (n.d.). Evaluating the Quality of Data Through Statistical Analysis. 16th January 2014. Retrieved from https://www.acfas.org/Physicians/Content.aspx?id=674
Yang, Y. (1999). An evaluation of statistical approaches to text categorization. Information retrieval, 1(1-2), 69-90.