Conclusions of similarity

In Section 3.3.1 we defined the p-value and briefly mentioned a common incorrect definition. We will return now to discuss why this leads to considerable misinterpretation. In the example of Section 3.3.1 we had observed a treatment difference of 5.4 mmHg with a p-value of 4.2 per cent and the proposed definition (incorrect) was that there is a 4.2 per cent probability that pj = 2 -The problem with this definition is the misinterpretation when the p-value is large. As an extreme case suppose that we ran a trial in hypertension with two patients per group and also suppose that even though in truth the true treatment 

It is all too common to see a conclusion that treatments are the same (or similar) simply on the back of a large p-value this is not necessarily the correct conclusion. Presentation of the 95 per cent confidence interval will provide a statement about the possible magnitude of the treatment difference. This can be inspected and only then can a conclusion of similarity be made if this interval is seen to exclude clinically important differences. We will return to a more formal approach to this in Chapter 12 where we will discuss equivalence and non-inferiority. 

---

James M. Schopf. I was interested in Dr. Given s conclusion of similarity of micrinite and fusinite. The petrologic associations of micrinite are even more difficult to associate with its origin as a result of forest conflagration. From its geologic occurrences it seems to me very unlikely that all fusain occurrences can be explained by forest fires. For this reason it is most appropriate to examine alternative methods by which fusain and micrinite could originate. 

The best way to attach the catalytic film to the porcelain was indicated by Professor Einstein s claim that According to the molecular kinetic theory, in a colloidal solution, there is no difference between a suspended particle and a molecule. Previous to this claim. Professor Jean Perrin, in his admirable study of the Brownian movement, had come to a qualified conclusion of similar nature. 

---