In some data sets we do not observe values above or below a certain magnitude, due to a censoring or truncation mechanism. Examples : - A central bank intervenes to stop an exchange rate falling below or going above certain levels. - Dividends paid by a company may remain zero until earnings reach some threshold value. - A government imposes price controls on some goods. - A survey of only working women, ignoring non-working women.
In these situations, the observed data consists of a combinationof measurements of some underlying latent variable and observations that arise when the censoring/truncation mechanism is applied. 2