Question

b) test statistic

c) RR

d) p-value

e) test decision

Answer 1

(b) Test Statistics: If we break the term into two-- test and statistic...it is better to understand. Statistic refers to a function of sample observations usually calculated to estimate some population parameter. Test hear refers to check the reliability of the statement i.e. the null hypothesis. So, test statistics is a function of sample observations which converts a number of sample observations into a single value for the investigator to check the reliability of the statement stated in null hypothesis.

(c) RR: RR stands for relative risk. Relative Risk refers to the odds of happening of an event in one group with respect to the other group. to calculate RR we need a dichotomous classification. It is the ratio of probability of occurring an event in one group to the probability of occurring of same event in the other group. It is usually calculated for disease occurring symptoms. For example: the relative risk of developing brain tumour (event) who have seizures (fits) (exposed group) versus who do not have seizures (non-exposed group) would be the probability of developing brain tumour for people having seizures divided by the probability of developing brain tumour for people not having seizures.

(d) p-value: p- value or probability value is used to test our initial statement or belief (i.e. the null hypothesis). If the p-value is less than the predetermined level of significance (alpha) then we reject the null hypothesis i.e our initial belief is proved to be wrong.It measures how compatible your data are with the null hypothesis. The p- value is calculated using p- value tables, spreadsheets or other statistical softwares. Two researchers considering different level of significance may come out with totally opposite results for the same hypothesis with same data and same p- value...thus, it is important to set level of significance before the experiment is done to avoid bias and confusion.

(e) Test decision: The decision taken regarding the null hypothesis or the initial statement with respect to p-value or the test statistic is called the test decision of a hypothesis testing procedure. It is the final stage of hypothesis testing where we conclude for null hypothesis to be true or untrue. With respect to the p-value, smaller the p-value stronger the evidence of having reject the null hypothesis.