Sampling with probabilities proportional to the variable of interest

To estimate the mean sojourn time, a sample of Tilburg fair visitors was asked for the duration of their stay on the fair grounds. The longer a visitor's sojourn, the larger his/her probability of being interviewed will be; therefore, longer sojourn times will be overrepresented in the sample. As a consequence, the arithmetic sample mean is not a suitable estimator. The paper places this problem against a theoretical background. As a better estimator the harmonic mean of the observed sojourn times is presented. In addition, a variance estimator is given. The properties of these estimators are difficult to derive analytically. Instead, their behaviour is studied in a number of examples.