#### Statistics in Biology and Agriculture, Biology tutorial

Introduction:

The term Statistics is a well-known and accepted portion of modern world that is concern by getting an insight into the real world through means of the analysis of numerical relationships. It is employed in nearly all fields of human Endeavour. This is concerned with sports, public health, surveys, education, operations research, quality control, prediction and estimation.

Statistics and Biostatistics:

The term statistics is employed in two senses. It signifies to collections of quantitative information and to methods of handling that variety of data that is, expressive statistics. It as well signifies to the drawing of inferences regarding big groups on the basis of observations made on smaller one that is, inferential statistics.

Statistics, then, is to perform with approaches of collecting, organizing, summarizing and explaining quantifiable data and processes of drawing inferences and generalizing on them.  Whereas the word Biostatistics is employed when the data that are being examined employ statistical tools are derived from the fields of biological sciences: Pharmacy, Medicine, Biochemistry, Microbiology, Agricultural Sciences and other biology related regions.

Use of statistics in biology, agriculture and medicine:

Dissimilar to other fields of science like the physical sciences of physics and chemistry, variation is considered as a basic feature in natural sciences of biology, medicine and agriculture. Biostatistics assists to describe this natural variation inherent in such fields of natural sciences. For instance, variation might take place due to the age of population or might take place among individuals of a population due to genetic frame or diseases. Experimental design is a significant feature of biostatistics which explains on how to gather, classify, summarize and analyze data in such a way that valid and objective decisions or conclusions regarding the population can be drawn.

Variables:

To increase knowledge regarding secondly haphazard events, statistician gathers information for variables that explain the event. Thus, a variable is a characteristics trait which can suppose different value.

Variables can be categorized into two wide categories.

1) Qualitative variables

2) Quantitative variables

Qualitative variables: Qualitative variables are the variables which can be positioned into different categories, according to some trait or attribute. For instance, if subjects are categorized according to gender (that is, male or female) then the variable gender is qualitative.

Quantitative variables: These variables are numerical and can be ranked or ordered. For instance, the variable age is numerical, and people can be ordered or ranked according to the value of their ages.  Quantitative variables can be classified into two:

a) Discrete Variables: These can be assigned values like 0,1,2,3 (integers) and are stated to be variables which suppose values that can be counted. Illustrations comprise number of children in a family, number of birds in a pen, number of trees in a garden and so on.

b) Continuous variables: It can suppose all values between any particular values. They are obtained by measuring. This concern to variables like length, height, weight, yield, temperature and time, which can be thought of as capable of supposing any value in certain interval of values.

Sampling:

If a set of observations is gathered from a population, the population mean (μ), population variance (σ2) and population standard deviation (σ) can be calculated from it as the properties of the population. In situation of a sample, the parameters which explain it are the sample mean (x), sample variance (s2) and sample standard deviation (s). As the sample is a part of the population, the parameters of the sample symbolize an estimation of the true parameters of the population. Thus, sampling is a random method of choosing a sample from a population chosen for study.

Sample:

A sample is a subgroup of the population chosen for study. If a sample is selected at random from a population, it is stated to be an unbiased sample. That is, the sample for most of the portions is representative of the population.  However when a sample is chosen wrongly, it might be a biased sample if some kind of systematic error has been made in the choice of the subjects. Though, the sample should be random in order to form valid inferences regarding the population.

Importance of Sample or Sampling:

A sample is employed to acquire information regarding a population for some reasons:

1) It saves the researcher money and time.

2) It facilitates the researcher to acquire information which he or she might not be capable to get or else.

3) It facilitates the researcher to get more explained information regarding a specific subject.

Sampling Methods:

In order to get unbiased samples, some of the sampling processes or methods have been built up.  The most familiar processes are random, systematic, stratified and clustered sampling.

Random sampling:

Random sampling is the purest type of probability sampling. Every member of the population consists of an equivalent and known chance of being chosen. If there are very huge populations, it is frequently difficult or not possible to recognize each and every member of the population, therefore the pool of accessible subjects becomes biased.

Stratified Sampling:

A stratified sample is a sample acquired by dividing the population into subgroups, termed as strata, according to different homogenous features and then choosing members from each stratum for the sample.  For instance, you can group the items on basis of their size, age, color and so on. The benefit of stratified sampling is that it raises precision because all kinds of groups are represented via stratification and a heterogeneous population is build up into a homogenous one.

Cluster Sampling:

A cluster sample is a sample acquired by choosing a pre-existing or natural group, termed as a Cluster and by using the members in the cluster for the sample. For instance a habitat, or a big area or field is splitted into smaller units and a number of such units are randomly chosen and employed as a sample.

There are three benefits to using a cluster sample rather than other kinds of sample:

a) A cluster sample can decrease the cost.

b) It can make field work simpler.

c) It is suitable.

The main demerit of cluster sampling is that the elements in a cluster might not encompass the similar variations in characteristics as elements chosen individually from the population.

Systematic or Skip sampling:

This process comprises taking an item as a sample from a bigger population at regular intervals.  For instance, when sampling from the poultry farm, every third or fifth or tenth chick coming out of the cage is taken and comprised in the sample.

This is completed after the first number is chosen at random for counting to begin.

Proportionate Sampling:

Proportionate Sampling is a sampling strategy (that is, a process for gathering participants for a study) employed if the population is composed of some subgroups which are very much different in number. The number of participants from each and every subgroup is found out by their number relative to the whole population.

Sampling Distribution:

It is a probability distribution of a statistic acquired via a large number of samples drawn from a particular population. The sampling distribution of a given population is the distribution of frequencies of a range of dissimilar outcomes which could possibly take place for a statistic of a population.

For instance, assume that you wanted to determine the sampling distribution of SAT scores for all U.S. high school students in a particular year. To do so, you would take repeated random samples of high school students from the general population and then calculate the average test score for each and every sample. The distribution of such sample means would give you with the sampling distribution for the average SAT test score.

Tutorsglobe: A way to secure high grade in your curriculum (Online Tutoring)