A sample of 3014 steelworkers was selected to find out if th

A sample of 3,014 steelworkers was selected to find out if they will go on strike on Monday. 53.2% of those in the sample said they would go out on strike. Since the number sampled is large and those advocating a strike constitute over 50%, can we assume that the majority of all steelworkers favor a strike?

Solution

Statistics hopes that samples look like whole populations. The sample is described by a typical, central value: an average, mean, or median. The sample also has a \"spread\" or range about the average: a standard deviation. Normally, about two-thirds of the group will lie within one standard deviation of the average, and about 95% lives within two standard deviations. Is the sample size big enough? I prefer sampling until there\'s not much change in medians. Then I over-sample to be sure.