Correlation Analysis (Biostatistics)ppt.

Correlation Analysis (Biostatistics)ppt.

• 1.
  CORRELATION ANALYSIS Genetics &Biostatistics Presented by Kajal Kashyap M.Sc. Zoology R.G. P.G. College, Meerut [email protected]
• 2.
  INTRODUCTION The concept ofcorrelation analysis and term correlation originated with Galton in 1888. “In biostatistics correlation is used to estimate the strength of a relationship between to variables.”
• 3.
  Types of correlation 1.On the basis of degree of correlation • Positive correlation • Negative correlation 2. On the basis of number of variables • Simple correlation • Partial correlation • Multiple correlation 3. On the basis of linearity • Linear correlation • Non – linear correlation
• 4.
  On the basisof degree of correlation 1. Positive correlation:- “Is a relationship between two variable in which both variable move in some direction. Example :- Price increse then Demand increse. 2. Negative correlation:- Is a relationship between two variables in which one variable increse or the other decrease. Example :- Price increse and Demand decreased
• 5.
  On the basisof number of variable 1. Simple correlation:- In a Simple correlation the relationship between two variable such as intelligence of Students and their performence (marks) in the examination. 2. Parietal correlation:- When three or more variable are taken but relationship between any two of the variable is studied, assuming other variable as constent. Example:- Suppose, Under constent temperature we study the relationship between the amount of rainfall and wheat yield. 3. Multiple correlation:- When we study the relationship among three or more variable, then it is called Multiple correlation. Example:- We study the relationship between rainfall, temperature and yield of wheat.
• 6.
  On the basisof linearity 1. Linear correlation:- If the ratio of change of two variable X and Y remains constent throughout, then they are said to be linearity correlation. Example:- When everytime supply of a commodity rises by 20% as often as it’s price rises by 10%, then such as two variable have Linear relationships. 2. Non – linear correlation:- Is defined When the ratio of variations between two given variable change.
• 7.
  Methods of measureof correlation The three different Methods of measuring correlation between two variables are 1. Scatter diagram Method 2. Karl Pearson’s correlation coefficient method 3. Spearman’s rank correlation coefficient
• 8.
  SCATTER DIAGRAM METHOD •Scatter diagram is the simple method of analyzing relationship between two variables. • It is a graphic representation of degree and direction of correlation between two variables. • Say we take two variables X and Y form n number of samples and plot X1 against Y1 as a dot (.) in the XY – plane, the diagram of dots so obtained is known as Scatter diagram or dot diagram. • Placement of dots on the graph reveals whether the change in the variables are in the same direction or in opposite direction.
• 9.
  ■ Merits ofScatter diagram ● It is a simple method. ● It is easy to understand. ● It first step in studying relation between two variable. ■ Demerits of Scatter diagram ● It gives just an idea about the direction of correlation. ● It is just a qualitative methods. ● This method is suitable for small number of observations.
• 10.
  Karl pearson’s correlationcoefficient method • Karl pearson was the first person to give a methematical formula for measuring the degree of relationship between two variables in 1890. • It is the most popular and widely used. • It is denoted by ‘r’. • Correlation can be measured only when the relationship between two sets of variable can be expresed by a straigted line. • Coefficient of correlation is the degree to which two variables are inter-related.
• 11.
  ■ Merits ofkarl pearson ● Karl pearson method gives us exact measure of degree of correlation between two variables. ● It provide on idea about the direction of correlation between two variables. ■ Demarits of karl pearson ● It between two variables assumes linear relationship. ● It use only which have quantitative measurements.
• 12.
  Spearman’s rank correlation coefficient •Spearman’s rank correlation method is used for qualitative Variable such as intelligence, honesty, ability, beauty, colour etc. • Correlation coefficient between any two of such qualitative Variables cannot be calculated by karl pearson method. ■ Merits of rank correlation ● It is simple to understand and easy to apply. ● These Variables measured quantitatively ■ Demerits of rank correlation ● This method can be used only for small number of observation.
• 13.
  Importance of correlation Thestudy of correlation is of great significance in practical life because of the following reasion. • The study of correlation enable us to know the nature, direction and degree of relationship between two or more variable. • Correlation studies help us to estimate the change in the value of the variable as a result of change in the value of related variable. This is called Regression analysis. • It help in marking predication. • It help in promoting the research. • It facilitates the decision making in the bussiness world. • Correlation analysis helps us in understanding the behaviour of certain events under specific circumstances.
• 14.
  REFERENCE • “BIOSTATISTICS” thethird revised edition of “Veer bala rastogi”. • Some data collect from google. • Picture collect from book. • Science/methods-of-measurements-of-correlation/