Determining the risk of accidental ignition of flammable mixtures is a topic of tremendous importance in industry and aviation safety. The concept of minimum ignition energy (MIE) has traditionally formed the basis for studying ignition hazards of fuels. In recent years, however, the viewpoint of ignition as a statistical phenomenon has formed the basis for studying ignition, as this approach appears to be more consistent with the inherent variability in engineering test data. We have developed a very low energy capacitive spark ignition system to produce short sparks with fixed lengths of 1 to 2 mm. The ignition system is used to perform spark ignition tests in lean hydrogen- oxygen-argon test mixtures over a range of spark energies. The test results are analyzed using statistical tools to obtain probability distributions for ignition versus spark energy, demonstrating the statistical nature of ignition. The results also show that small changes in the hydrogen concentration lead to large changes in the ignition energy and dramatically different flame characteristics. A second low-energy spark ignition system is also developed to generate longer sparks with varying lengths up to 10 mm. A second set of ignition tests is performed in one of the test mixtures using a large range of spark energies and lengths. The results are analyzed to obtain a probability distribution for ignition versus the spark energy per unit spark length. Preliminary results show that a single threshold MIE value does not exist, and that the energy per unit length may be a more appropriate parameter for quantifying the risk of ignition.