Hypothesis Testing
HYPOTHESIS TESTING
WHAT IS THIS HYPOTHESIS????
• In simple words it means a mere assumption or supposition to be proved of disproved.
• But, for a researcher it is a formal question that he intends to resolve.
• Example: I assume that 1) under stress and anxiety a person goes into depression.
2) It leads to aggressive behaviour.
Eg. : Students who get better counselling in a university will show a greater increase in creativity than students who were not counselled.
• So, the hypothesis should be capable of being verified and tested.
CHARACTERISTICS
• Should be clear and precise – inferences not reliable
• Capable of being tested
“ A hypothesis is testable if other deductions can be made from it which, in turn can be confirmed or disproved by observation.”
• Should be limited in scope and must be specific
• Should be stated in simple terms -understandable by all concerned.
• Must explain the facts that gave rise to the need for explanation.
BASIC CONCEPTS: NULL & ALTERNATIVE HYPOTHESIS
• If we are to compare two methods A & B and both are equally good, then this assumption is termed as null hypothesis(H0)
• If it is stated that method A is better than method B-alternative hypothesis(Ha)
LEVEL OF SIGNIFICANCE
• A very important concept in the context of hypothesis testing
• It is represented in a % age (usually 5%), which should be chosen with care, thought and reason.
• Implies H0 will be rejected when the sampling result(observed confidence) has a less than 0.05 probability of occurring if H0 is true.
• In simple words 5% level of significance means that researcher is willing to take as much as 5% risk of rejecting a null hypothesis when it happens to be true.
• It is the maximum level of probability of rejecting null hypothesis when it is true and is actually determined in advance before testing the hypothesis.
TYPES OF ERRORS
• TYPE I : It is denoted by α : α error
• TYPE II : It is denoted by β : β error
TYPE I & II
WHAT IS THIS HYPOTHESIS????
• In simple words it means a mere assumption or supposition to be proved of disproved.
• But, for a researcher it is a formal question that he intends to resolve.
• Example: I assume that 1) under stress and anxiety a person goes into depression.
2) It leads to aggressive behaviour.
Eg. : Students who get better counselling in a university will show a greater increase in creativity than students who were not counselled.
• So, the hypothesis should be capable of being verified and tested.
CHARACTERISTICS
• Should be clear and precise – inferences not reliable
• Capable of being tested
“ A hypothesis is testable if other deductions can be made from it which, in turn can be confirmed or disproved by observation.”
• Should be limited in scope and must be specific
• Should be stated in simple terms -understandable by all concerned.
• Must explain the facts that gave rise to the need for explanation.
BASIC CONCEPTS: NULL & ALTERNATIVE HYPOTHESIS
• If we are to compare two methods A & B and both are equally good, then this assumption is termed as null hypothesis(H0)
• If it is stated that method A is better than method B-alternative hypothesis(Ha)
LEVEL OF SIGNIFICANCE
• A very important concept in the context of hypothesis testing
• It is represented in a % age (usually 5%), which should be chosen with care, thought and reason.
• Implies H0 will be rejected when the sampling result(observed confidence) has a less than 0.05 probability of occurring if H0 is true.
• In simple words 5% level of significance means that researcher is willing to take as much as 5% risk of rejecting a null hypothesis when it happens to be true.
• It is the maximum level of probability of rejecting null hypothesis when it is true and is actually determined in advance before testing the hypothesis.
TYPES OF ERRORS
• TYPE I : It is denoted by α : α error
• TYPE II : It is denoted by β : β error
TYPE I & II