Instruments that measure cloud base height at the Atmospheric Radiation Measurement (ARM) Program site in Lamont and Blackwell Oklahoma are examined. These instruments include, the Micropulse Lidar, Belfort Laser Ceilometer, Vaisala Ceilometer, and Millimeter-Wavelength Cloud Radar. Instruments at the ARM sites record information regarding cloud radiative forcing and feedback effects, variables that represent a great amount of uncertainty in climate prediction. However, flawed observations and dissimilarities in instrument performance when reporting cloud types hinder our ability to fully understand these processes. Also, users of ARM data assume these instruments are interchangeable, but this may not be the case. The purpose of this paper is to address the observed differences between these instruments under different atmospheric conditions and cloud types both qualitatively and statistically, and to test a method that may be useful to identify outliers. Qualitative analysis revealed that the Micropulse Lidar is superior in reporting high cloud bases and jagged cloud bases, but inferior to both ceilometers when reporting low clouds. However, statistical results were inconclusive, due to large standard deviations encountered in all cloud episodes. Histograms used to identify outliers gave reasonable results when cloud bases were visibly similar, but resulted in skewed or bimodal distributions for other cases. These results are discussed for observations taken during the Spring 2000 Cloud Intensive Observing Period.