BA Fourth Semester Honours Topic ChiSquare Test B asic Pervious knowledge required on Hypothesis Null and Alternative Errors and its types ID: 1047198
Download Presentation The PPT/PDF document "Binod Goswami’s Classes on Economet..." is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.
1. Binod Goswami’s Classes on Econometrics B.A. Fourth Semester Honours Topic- Chi-Square TestBasic Pervious knowledge required on-Hypothesis- Null and AlternativeErrors and its types Parametric and Nonparametric TestNominal and Categorical Variable 5/24/20211BG's Classes on econometrics
2. Hypothesis- Null and AlternativeHypothesis is a statement about a population.Ex- Mean weight of students of NGC is 46 kg and its standard deviation is 9It is an assumption made about parameter values.Validity of hypothesis is tested with the help of statistical techniques (CHI-square test, T-test,F-test) These test tells us whether hypothesis is to be accepted or to be rejected 5/24/20212BG's Classes on econometrics
3. Types of Hypothesis – Null hypothesis and Alternative hypothesisNull hypothesisNull hypothesis-a statistical hypothesis stated to test its validity is called null hypothesis. Denoted by H0 H0 is always tested on the basis of sample results and is ultimately either rejected or accepted. It is the hypothesis of no difference.If the population mean is then H0 is written as H0 : = 0 , 0 is a specified value of Similarly if and 1 are 2 the parameters of two populations , the null hypothesis is written as H0 : 1 = 2 5/24/20213BG's Classes on econometrics
4. Types of Hypothesis – Null hypothesis and Alternative hypothesisAlternative hypothesis- hypothesis accepted as a result of rejection of null hypothesis. Denoted as H1It is complementary to the null hypothesis if the null hypothesis is that the population has specified mean 0 (say) i.e. H0 : = 0 Then the alternative hypothesis may be H1 : 0H1 : > 0 H1 : < 0 5/24/20214BG's Classes on econometrics
5. H1 : 0Two tailed hypothesisH1 : > 0One tailed – Right tailed H1 : < 0 One tailed – Left tailed 5/24/20215BG's Classes on econometrics
6. Errors in Hypothesis TestingIn hypothesis testing, the decision to accept or reject of null hypothesis is taken on the basis of the sample result. The decision taken in this way may not be correct always. Thus Errors arise.There are 4 possibilities when a statistical hypothesis is tested 5/24/20216BG's Classes on econometrics
7. Reject H0 when it is actually true Type I error()Accept H0 when it is actually false Type II error() Accept H0 when it is actually true No errorReject H0 when it is actually false No error 5/24/20217BG's Classes on econometrics
8. Type I and Type II errors Accept H0Reject H0H0is true No error Type I error H0 is false Type II error No error 5/24/20218BG's Classes on econometrics