One of the major concerns with detecting global climate change is the quality of the data. Climate data are extremely sensitive to errant values and outliers. Prior to analysis of these time series, it is important to remove outliers in a methodical manner. This study provides statistically derived bounds for the uncertainty associated with surface temperature and precipitation measurements and yields a baseline dataset for validation of climate models as well as for a variety of other climatological uses. A two-step procedure using objective analysis was used to identify outliers. The first step was a temporal check that determines if a particular monthly value is consistent with other monthly values for the same station. The second step utilizes six different spatial interpolation techniques to estimate each monthly time series. Each of the methods is ranked according to its respective correlation coefficients with the actual time series, and the technique with the highest correlation coefficie... Abstract One of the major concerns with detecting global climate change is the quality of the data. Climate data are extremely sensitive to errant values and outliers. Prior to analysis of these time series, it is important to remove outliers in a methodical manner. This study provides statistically derived bounds for the uncertainty associated with surface temperature and precipitation measurements and yields a baseline dataset for validation of climate models as well as for a variety of other climatological uses. A two-step procedure using objective analysis was used to identify outliers. The first step was a temporal check that determines if a particular monthly value is consistent with other monthly values for the same station. The second step utilizes six different spatial interpolation techniques to estimate each monthly time series. Each of the methods is ranked according to its respective correlation coefficients with the actual time series, and the technique with the highest correlation coefficie...