< HTML>
A ONE-TIME OUTLIER PULSE IN A CROSS-SECTIONAL ANALYSIS
CAUTIONARY NOTE
Unless you deal with anomalies, such as unusual values, the estimates
of coefficients can be seriously biased. In this example, we illustrate the effect of one unusual value.
The data is 10 pairs of readings.
CLICK HERE TO VIEW SOME STANDARD REFECTIONS ON OUTLIERS.
CLICK HERE TO VIEW THE PLOT OF Y VERSUS X AND THE ESTIMATED MODEL PARAMETERS.
CLICK HERE TO VIEW THE PLOT OF Y VERSUS X AND THE ESTIMATED MODEL PARAMETERS (BOTH OLS AND ROBUST).
