Beruflich Dokumente
Kultur Dokumente
Hypothesis Testing
Hypothesis Testing ?
is assumption about Population
a) Average adult drinks 1.7 cups of coffee per day b) Not more than two percent of products we sell are defective.
2. A null hypothesis can only be rejected or failed to be rejected , it can not be accepted because of lack of evidence.
2. Alternative Hypothesis, denoted by H1, represents opposite of Null Hypothesis and holds true if Null Hypothesis is false.
3. Alternative Hypothesis states that mean of the population is < 6, > 6 or 6 grams.
Test Statistic
1. Value calculated from Sample Information is called as Test Statistic
2. Test statistic is compared with Critical Value, in order to reject or not to reject Null Hypothesis.
3. Critical values are obtained from Distribution Tables, against chosen level of Significance, i.e. 1,5 or 10.
Types Of Errors
1. Type I Error: Rejecting Null Hypothesis when it is true. For example incoming products are good but labeled as Defective. Producers risk error.
2. Type II Error: This type of error occurs, when null hypothesis is not rejected, when it actually should have been rejected. For example incoming products are defective but labeled as good.
2. If null hypothesis is established to test whether sample value, smaller or larger than Population value then entire risk is placed on either end of distribution curve.
3. This constitutes one tail test. If H0: > 20 mm, then H1: > 20
3. Rejection region shown in above distribution is always consistent with direction of inequality i.e. For H1: > 20, rejection region will be in right tail of the sampling distribution. For H1: < 20 rejection region will be in Left tail of the distribution.
2. Allowable error is divided in two equal parts one each for right & left tail of the distribution.
Thank you
15