Taking　the　commuters＇　travel　mode　choice　behaviors　as　the　research　subject,　we　assume　that　there　are　three　possible　travel　modes　of　transit　mode,　solo-driving　mode　and　park-and-ride　mode.　Without　loss　of　generality,　the　travel　time　for　transit　mode　is　assumed　fixed　while　the　travel　time　for　other　two　modes　are　assumed　stochastic.　With　this　consideration,　we　first　establish　the　travel　mode　choice　models　and　compared　the　difference　between　the　optimal　choices　in　different　scenarios　under　the　framework　of　cumulative　prospect　theory　(CPT)　and　expected　utility　theory　(EUT),　respectively.　Then,　the　empirical　investigation　is　conducted　to　verify　the　previous　theoretical　results.　The　empirical　results　show　that,　the　individuals＇　decisions　change　with　the　scenarios,　and　they　are　consistent　with　the　choices　under　the　framework　of　CPT.　In　this　sense,　the　transportation　administrators　should　manage　and　optimize　the　road　resources　based　on　individuals＇　risk　preferences.　©　2016,　Editorial　Board　of　Journal　of　Systems　Engineering　Society　of　China.　All　right　reserved.