Many publications made private inquiries before presidential election, generally by means of questionnaires sent to subscribers and by telephone surveys. The principle common to all these inquiries was that they depended on quantity rather than quality little effort was made to reach representatives of all segments of the population. Still, the erroneous belief persisted that the greater the number of questionnaires, the more accurate the results would be. The record was held by the American monthly Literary Digest, which sent out millions of postcards with short and pointed questions before each election, and received many hundreds of thousands of replies. In fact, in 1932, the Literary Digest's forecast was off by only 1%. In view of such striking achievements, it seemed rather improper for the young American journlist, George Gallup, to claim that large numbers were irrelevant, and that equally accurate or better predictions could be made with a small but carefully selected sample of the population and a small team of skilled interviewers. In 1936, Gallup convinced thirty-five newspaper editors that his system was much cheaper than the customary mass inquiries and that it could provide surprisingly accurate predictions. The editors finally agreed. On condition that if Gallup's predictions were less accurate than those obtained by the tried method of the Literary Digest, he would have to refund the entire cost of the investigation. Although the Literary Digest broke its own record by obtaining two million replies to its electoral postcards that year, its prediction was wrong by 19%, whereas Gallup's was off by less than 1%. Suddenly Gallup's name was on everyone's lips. Not only was he the prophet of the moment, but it was generally conceded that he had founded a new and most important scientific method of prediction. He was showered with money and commissions, and the Gallup Poll becomes a common term for public opinion polls. Gallup usually samples his subjects according to six factors: state, size of community, age, sex, income, and political affiliation. From time to time, other factors may be considered, during time of war, for instance, the national origins of electors may be taken into account. Only when the composition of the electorate has been accurately determined can the purely arithmetical question -- how many people in each bracket must be interviewed -- be solved. Once this is done, laws of probability take over, and the more people interviewed, the more exact the estimates will be. However, above a certain maximum number of interviews, the accuracy increases by no more than a fractional percentage -- and where errors of up to 2% are permissible, a few thousand questionnaires will accurately reflect the opinions of the total United States electorate. Gallup's method of sampling the electorate was successful. Before Gallup, political predictions were no more than shots in the dark, and it is as a result of his achievement that today we can make truly scientific forecasts in this difficult field. How does the author like the common principle held in the pre-election poll?