Example: The production manager of a company needs to evaluate the performance of a new methodology of teaching to new hired workers. With the old methodology, the company has an average rate of 4 errors per worker in the first week of work. In a sample of 25 workers, it was applied the new methodology and it was observed that the average rate was 5 errors per week. With these information can we talk that there is significative difference between the old methodology and the new one?
click here to download the data
To use the tool Rate Test the user must follow these steps:
1. Access the menu:
Action 
Basic Statistics Rate Rate Tests
2. The following window will be shown;
3. In the field Data Set, we select between the options Complete Data or Summarized Data. In this case we summarized data, so we must select the option Summarized Data;
4. In the field Summarized Data we type the Mean Rate and the Sample Size. In this case, we type 5 and 25 respectively;
5. In Alternative Hypothesis we select among the options Not equal, Lower than or Greater than. In this case, we will test if the new methodology is better than the old one. That is, if the mean rate is lower than 4. So we select Lower than;
6. In thee field Null Hypothesis we type the null hypothesis of the test. In this example we type 4;
7. In the field Confidence Level we type the confidence level of the test. In this example we type 0.95 (95%);
8. In Show Results, we select between the options Current Cell or New Sheet. We suggest the option New Sheet because Action does not have the undo command;
REMARK: When choosing the option Current Cell the results will be printed from the cell where the cursor is. In this case, the user must put the cursor in an appropriate position previously (before step 1);
9. To finish, click Ok.
Results and Interpretation
Once the process is finished, the following results will be shown:
The p-value is 0.9938 > 0.05, só at a 5% significance level, we have no evidences that the mean rate of errors with the new methodology is lower than the mean rate of erros of the old one. So, we cannot tell the new methodology is better than the old one.
English
Português