Bota 302 Prac 3 Frequency & Normal Distribution Regression Analysis

You might also like

Download as pdf or txt
Download as pdf or txt
You are on page 1of 2

BOTA 302 BIOSTATISTICS PRACRICAL 3

FREQUENCY & NORMAL DISTRIBUTION, REGRESSION ANALYSIS

Frequency distribution
If a large number of measure or variable are made, the figures can be summarized in a frequency
distribution. The figures are first placed in numerical order and then grouped into frequency
classes. The form or pattern of a frequency distribution is shown by distribution in numerical form
but is more clearly recognized in a diagram such as a histogram. The height and weight of students
in class can be used to demonstrate a frequency and normal distribution.
Activity 1
The students in the class will be divided into groups. Half of the groups will take height (using a tape
measure in m) of 50 students picked at random. The remaining groups will take weight (measured in kg) of
equal number of students. Then;
(a) Convert your data into a frequency distribution using procedure described in lectures.
(b) Estimate mean, mode, median and standard deviation of frequency distribution above (1a)

Normal distribution
The Gaussian (also called bell-shaped or Normal) distribution is a very common one. The central
limit theorem (CLT) explains why many real-world variables follow a Gaussian distribution. In
non-mathematical language, the “CLT” says that, if we randomly sample a “large” number (say k)
of independent values from that random variable, the sum or mean of those k values, if collected
repeatedly, will have a normal distribution.

Activity 2
Using information obtained in 1a above draw a histogram showing the distribution of height and weight.

Regression analysis

Regression analysis describes the effect of one or more variables (independent variables) on a
single variable (dependent variable) by expressing the latter as a function of the former.
Independent variable: refers to the factor or treatment whose effect is to be measured. For
example, varied levels of fertilizer N applied in a maize trial, varied temperature regimes for insect
rearing, varied feed rates in animal nutrition trials, etc.
Dependent variable: represents measurement or observation made on an experimental unit that
has been subjected to a treatment. Examples;
 Yield of maize as affected by fertilizer N.
 Soil moisture content as affected by soil organic matter.
 Weight gain (kg) in animals as influenced by feed rations, etc.

We shall use the relationship between height and weight of students to demonstrate regression
analysis

Activity 3
Each group will select 20 students at random. The height and weight of the same student will
measured and entered in a table.

(a) Present data in table in form of a suitable diagram


(b) Compute and estimate the regression equation for your data

You might also like