HYPOTHESIS A hypothesis plural hypotheses is a statistical

HYPOTHESIS A hypothesis (plural hypotheses) is a statistical statement which has yet to be tested for its possible truthfulness. Classification of hypothesis Hypothesis can be classified in two categories: • Null Hypothesis • Alternative Hypothesis

Null Hypothesis

Procedure for Testing Hypothesis This procedure is described as follows: 1. 2. 3. 4. 5. Set up a hypothesis Set up a suitable Significance Level Setting a Test Criterion Doing Computations Making Decisions Types of Errors in Testing Hypothesis When a statistical hypothesis is tested, we can have the following possibilities: 1. 2. 3. 4. Hypothesis is true but our test rejects it. Hypothesis is false but our test accepts it. Hypothesis is true and our test accepts it. Hypothesis is false and our test rejects it. (Type I error) (Type II error) (Correct decision)

Since the calculated value of is less than the table value at 1% level of significance. Therefore, hypothesis is accepted. Hence the producers claim is not valid at 1% level of significance.

Example 5. Two types of drugs were used on 05 and 07 patients for reducing their weights. Drug A was imported and drug B indigenous. The decrease in the weights after using the drugs for six months was as follows: Drug A : 10 12 13 11 14 Drug B : 08 09 12 14 15 10 09

Solution. Let us take the null hypothesis that there is no significant difference in the efficacy of the two drugs. Applying t-test