The document discusses different statistical techniques used to test hypotheses, including chi-square tests, correlation coefficients, and regression analysis. Chi-square tests are used to determine if categorical data shows dependency between two classifications or if they are independent. Correlation coefficients measure the degree and direction of relationship between two variables. Regression analysis studies the functional relationship between variables and can be used to predict unknown dependent variable values from known independent variables.
1. A It is a proposition which can be put to a test
determining its validity
Goode And Halt
2. CHARACTERISTICS OF HYPOTHESIS
Conceptual clarity
Specificity
Testability
Availability of techniques
Theoretical relevance
Consistency
Objectivity
Simplicity
3. Needs/ Importance
It provides direction to research
It sensitizes the investigator to certain aspects of
situation
It is a guide to the thinking process
It places clear and specific goals before researcher
It enables the investigator to understand with greater
clarity his problem and its complex result
Its serves as a frameworks for drawing conclusion
It serves the function of linking together related facts
and information
4. Types Of Hypothesis
On the basis function
1. Descriptive Hypothesis
2. Relational Hypothesis
3. Casual Hypothesis
5. On the basis of Nature
1. Working Hypothesis
2. Null Hypothesis
3. Statistical Hypothesis
6. On the basis of level of abstraction
1. Common sense Hypothesis
2. Complex Hypothesis
3. Analytical Hypothesis
8. Testing Of Hypothesis
Making formal statement
Selection of significance level
Deciding the distribution to use
Selecting random sample and computing an
appropriate value
Calculation of probability
9.
10. Chi Square
It is a Non Parametric Test
It can be used to determine if categorical data shows
dependency or the two classification are independent
It is used to make comparisons between theoretical
population and actual data when categories are used
11. Test the goodness of fit
Test the significance of association between two
attributes
Test the homogeneity or the significance of population
variance
12. Characteristics
Based on frequencies and not on parameters like
mean and SD
Used for testing hypothesis and not for estimation
Applied to a complex contingency tables
No rigid assumptions
13. Steps
Calculate expected frequency
Obtain the difference between observed and expected
frequencies and find out the squares of differences
Add together all the fractions as per above steps
Ascertain the approximate value from the table at the
particular level of significance
Finally take the decision of accepting or rejecting of
hypothesis
14. CORRELATION COEFFICENT
It is a statistical technique used to measure the degree
and direction of relationship between two variables
Eg
Relationship between height and weights, rainfall and
yield of wheat, advertising and sales etc..
15. karl pearson coefficient of
correlation
Assumption
Linear relationship between variables
Cause and effect relationship
Normality
16. Spearman’s Rank Correlation
It uses ranks rather than actual observation and make
no assumption s about population from which actual
observations are drawn
17. Regression analysis
It studies the nature and extent of functional
relationship between two or more variables and to
estimate /predict unknown values of dependent
variable from the known values of independent
variables
18. Depended variable =Y
Independent variable =X
Eg
Sales are predicted on the basis of advertisement –
Sales is dependent
Advertising is independent
19. What is
measured ?
Degree and direction of
relationship between
variables
The nature and extent of
average relationship
between two or more
variables
Relative or
absolute
measure
Relative measure- shows
association between
variables
Forecasting
?
Not forecasting device It is forecasting device
Expression
0f
relations
hip
-1>r<+1 Y=a + bX
Y= a+ bX +cX2