Despite its importance and usefulness, the science of statistics is looked upon with suspicion. Quite often it is discredited, by people who do not know its real purpose and limitations. We often hear statements such as: “There are three types of lies: lies, damned lies, and statistics”. “Statistics can prove anything”. “Statistics cannot prove anything”. “Statistics are lies of the first order”. These are expressions of distrust in statistics. By distrust of statistics, we mean lack of confidence in statistical data, statistical methods and the conclusions drawn. You may ask, why distrust in statistics? Some of the important reasons for distrust in statistics are as follows:
1) Arguments based upon data are more convincing. But data can be manipulated according to wishes of an individual. To prove a particular point of view, sometimes arguments are supported by inaccurate data.
2) Even if correct figures are used, they may be incomplete and presented in such a manner that the reader is misled. Suppose, it has been found that the number of traffic accidents is lower in foggy weather than on clear weather days. It may be concluded that it is safer to drive in fog. The conclusion drawn is wrong. To arrive at a valid conclusion, we must take into account the difference between the rush of traffic under the two weather conditions.
3) Statistical data does not bear on their face the label of their quality. Sometimes even unintentionally inaccurate or incomplete data is used leading to faulty conclusions.
4) The statistical tools have their own limitations. The investigator must use them with precaution. But sometimes these tools or methods are handled by those who have little or no knowledge about them. As a result, by applying wrong methods to even correct and complete data, faulty conclusions may be obtained. This is not the fault of statistical methods, but of the persons who use them.
We may conclude by taking an illustration. Suppose a child cuts his finger with a knife. His parents started blaming the knife. Here the fault does not lie with the knife but with the child who misused the knife. It should be kept in mind that statistics neither proves anything nor disproves anything. It is only a tool (i.e. a method of approach) which should be used with caution and by those who are knowledgeable in the subject.
