STATISTICS BSC303

Statistical data is used for better management in every industry in our society. It is critical for conducting scientific research, and vital to managing finance.

A knowledge of statistics can help you at work, in your studies, and in your private life. A lack of understanding at least basic statistics, can be a disadvantage in today's workplace.

This course may not make you into a statistician, but it will provide the most essential knowledge and skills required by consultants, researchers and managers across a wide variety of disciplines.

Distance Education Course -Introduction to Statistics

Strengthen your scientific and life sciences career with this course in Statistics.
Learn how to interpret data sets, and how to prove your point based on scientifically proven methods.
Take your time and learn statistics properly -being self paced is a big advantage when tackling a subject that many people find difficult.

If you want to develop scientifically-based research studies, this is your starting point.

COURSE STRUCTURE
There are 10 lessons as follows:

Introduction
Distributions
Measures of central tendency
The Normal curve and Percentiles and Standard Scores
Correlation
Regression
Inferential Statistics
The t Test
Analysis of variance
Chi square test

Each lesson culminates in an assignment which is submitted to the school, marked by the school's tutors and returned to you with any relevant suggestions, comments, and if necessary, extra reading.

AIMS

Become familiar with different statistical terms and the elementary representation of statistical data.
Become familia with distributions, and the application of distributions in processing data.
Apply measures of central tendency in solving research questions
Demonstrate and explain the normal curve, percentiles and standard scores.
Explain methods of correlation that describes the relationship between two variables.
Make predictions with regression equations.
Determine how much error to expect when making the predictions.
Explain the basic concepts of underlying the use of statistics to make inferences.
Analyze the difference between the means of two groups with the t Test.
Describe the use of ANOVA (Analysis of Variance) in analysing the difference between two or more groups.
Apply the concept of Non Parametric Statistics.

Statistics are a key element of scientific research and are also widely used in social, psychological and business research. Statistics are needed to define how information (data) must be correctly collected to provide accurate and reliable information on the facts or processes being researched.

Statistics allow complex information to be presented in fairly simple formats and allows others to assess the reliability of the data and of the calculations based on the data.

Data refer to numeric or quantitative information. That means that any qualitative data, such as colour, taste, smell, sounds, appreciations, feelings, must be converted into quantitative data before being analysed statistically. This is an important consideration in social sciences research when preparing experiments.

How to Collect Statistical Data

There are two main types of data -qualitative and quantitative. Statistical data is quantative!

Quantitative Data -Quantitative data is data that can be number crunched such as quantities, volumes, measurements etc. The number of herb species that occur in alpine conditions or the average crop yield from a citrus species.

Qualitative Data -Qualitative data is data that is difficult to be measured in numbers, and often is an attempt to explain why something occurs. For example: why that certain citrus species will only yield so much in any given year.

In reality the two go hand in hand and is very rare that a study would not encompass both types of data. Doing so will add depth to your study and it is recommended that students use more than one technique to collect data.

Data Sampling

You will need to be familiar with data sampling techniques, because regardless of whether you are collecting qualitative or quantitative data it is likely that you will not be able access the entire population. This information can be found in any standard statistical textbook. Below is some basic information regarding sampling.

Remember: The sample size (termed n in statistics) and the scope of sampling must be large enough to reliably represent the population. A sample refers to a small group of the population being studied.

The experiment or sampling should be repeated several times, to remove bias and random effects on the population. Many experiments are set up in replicated blocks which repeat the treatment or parameter being assessed. If comparing two populations, such as ‘treated and untreated’ populations, then representative samples need to be measured from each of the populations, ie: the treated and the control population.

Sampling Method	Description
Simple random sampling	The objective is to select a sample (n) out the population (N) in such a way the each case has an equal chance of being selected. To obtain this we may use a random number generator, a mechanical tool to select the sample (such as the way numbers are drawn in lotteries) or a table of random numbers.
Systematic Random Sampling	This is method of systematically selecting our subset from a randomly ordered population. To do this you must first list the population in a random order. Then decide what sample size you need and divide the population by this number. Eg if you need 30 out of a population of 300, you will pick every 10^th unit., third, randomly pick a number between 1 …. k. Starting with your random number (eg: 3) you then start with 3 and pick every 10^th number after 3.

Stratified Random Sample	This method of sampling is very similar to simple random sampling. First we divide the population into homogenous subgroups from which we then take a random sub sample. For example if we had access to results from an ornithological survey, we might first divide the results up into bird species, and then take a sample from each group of bird species.
Cluster Random Sampling	The purpose of cluster random sampling is to save the effort involved in trying to obtain samples which are spread out over a wide geographic area. To do this you first separate the population into groups (clusters) usually along geographic boundaries that make sense. Randomly select k number of clusters to sample. Sample each of these
Quota Sampling	This is an example of non-probability sampling. It is open to criticism that it is not possible to tell if the results are representative. Before sampling in this method, a quota is decided such as the number and type that is to be sampled.
Convenience Sampling	This is also a non probability sampling method. Basically the research subjects are selected due to convenience. As with quota sampling the data must be treated with caution.

Regardless of which approach you use, of utmost importance is that you plan and prepare prior to collection of any data. This will help ensure that data is valid and reliable.

Enrol, Study, and Learn to collect and analyze Statistical data as a critical tool in industry, management, research -anywhere.