212 JOURNAL OF THE SOCIETY OF COSMETIC CHEMISTS The statistician can only work as a junior member of a team he takes the ideas of others and helps them to put those ideas to work as efficiently as possible. At the start, therefore, this statistician acknowledges that most of the good ideas presented have originated in the first place from other people any nonsense is his own responsibility. We shall be confining ourselves to that important but limited field of investigation in which the research chemist seeks to supplement his own judgement about the sensory characteristics of the products he is dealing with by calling upon the judgement of other judges or members of panels who are available at short notice in the laboratory area or accessible to it. THE STATISTICIAN'S ROLE A statistician may be asked to provide some analysis of results obtained by going to outside groups of potential users of products scattered through- out the country on a nationwide basis. Such market research tests, market placement tests, consumer panel tests, call them what you will, have an unavoidable tendency to be time consuming, costly and difficult to organ- ise. The inevitable delays imposed by the problems of packaging for distribution over the whole country, of the distribution of product and the collection of reports are all difficult to accept at a time when commercial executives are breathing heavily down the formulator's neck. Some quick and simple approximations are absolutely necessary. On the other hand, the statistician has known of the opposite dangers the instant decision achieved by the chemist's own personal choice, which so often leads to expressions of acute surprise when larger scale tests fail to confirm the results from that sample of one. A very similar phenomenon concerns the use of the managing director's wife she rarely constitutes a very typical market for the products in question. In the first instance, the statistician may be required to advise on cheap and speedy versions of the national consumer panel of testers in the second instance he may be required to provide some systematic substitute for the one or two judgements by the cosmetic chemist and his colleagues at the next laboratory bench. From whichever direction the approach is made, we tend to end up with a small-scale sensory testing panel, in some cases composed entirely of the non-technical office or factory staff immediately available on the work site, in other cases composed of specially recruited outside groups of people called together for special sessions to some con-

SENSORY TESTING -- A STATISTICIAN'S APPROACtt 213 venient testing site, perhaps a local hall or a mobile caravan in a market place. The most likely starting point for the statistician in this field is to be confronted with some single judgement by a research worker and be asked to support it with an experiment designed to convince all concerned that this is a valid statement of fact. Alternatively, some point of dissension between two judgements occurs, and the statistician is brought in to devise a crucial test. The statistical line of attack is to request from the client full details of the experimental situation and to seek to devise a suitable and relevant testable hypothesis. For example, let us suppose that the research worker is interested in xvhether a difference in flavour exists between two batches of a peppermint oil for incorporation in a tooth preparation. He may be concerned to evaluate whether the addition of a bacteriostat to a cosmetic cream has caused a detectable change in its perfume. He may wish to evaluate the effect on colour of n-months' storage in plastic containers in comparison with storage in glass containers. THEORETICAL PROBABILITY CONSIDERATIONS All of these are clearly concerned with sensory difference testing. Sir Ronald Fisher (1) set out in some detail the statistical principles involved in setting such a testable hypothesis. He described in a classical reference "a lady who declares that, by tasting a cup of tea made with milk, she can discriminate whether the milk or the tea infusion was first added to the cup". The hypothesis to be tested was that she was unable to discriminate between the two forms of tea, and that her identification was, therefore, purely at random. The statistician calls this the null hypothesis. The experiment devised by Fisher was to offer the good lady eight cups of tea in turn, four being mixed in one way and four in the other. These were presented to her in a random order and she had to taste each of the eight and identify whether tea had been added to the milk or the milk added to the tea. On the null hypothesis (that is that her identification was made purely at random), the probability of her making a completely correct set of eight identifications, assuming she knew that there were four of each, would be 1 in 70. It is the statistician's approach to such matters to assume that, should such an unlikely event occur, then its occurrence should be taken to be evidence that the null hypothesis is not true. Thus, if Fisher's lady correctly identified all eight cups of tea, then she was not choosing at random.