Bus　arrival　time　is　usually　estimated　using　the　boarding　time　of　the　first　passenger　at　each　station.　However,　boarding　time　data　are　not　recorded　in　certain　double-ticket　smart　card　systems.　As　many　passengers　usually　swipe　the　card　much　before　their　alighting,　the　first　or　the　average　alighting　time　cannot　represent　the　actual　bus　arrival　time,　either.　This　lack　of　data　creates　difficulties　in　correcting　bus　arrival　times.　This　paper　focused　on　developing　a　model　to　calculate　bus　arrival　time　that　combined　the　alighting　swiping　time　from　smart　card　data　with　the　actual　bus　arrival　time　by　the　manual　survey　data.　The　model　was　built　on　the　basis　of　the　frequency　distribution　and　the　regression　analysis.　The　swiping　time　distribution,　the　occupancy　and　the　seating　capacity　were　considered　as　the　key　factors　in　creating　a　method　to　calculate　bus　arrival　times.　With　1011　groups　of　smart　card　data　and　360　corresponding　records　from　a　manual　survey　of　bus　arrival　times,　the　research　data　were　divided　into　two　parts　stochastically,　a　training　set　and　a　test　set.　The　training　set　was　used　for　the　parameter　determination,　and　the　test　set　was　used　to　verify　the　model＇s　precision.　Furthermore,　the　regularity　of　the　time　differences　between　the　bus　arrival　times　and　the　card　swiping　times　was　analyzed　using　the　＂trend　line＂　of　the　last　swiping　time　distribution.　Results　from　the　test　set　achieved　mean　and　standard　error　rate　deviations　of　0.6%　and　3.8%,　respectively.　The　proposed　model　established　in　this　study　can　improve　bus　arrival　time　calculations　and　potentially　support　state　prediction　and　service　level　evaluations　for　bus　operations.　(C)　2016　Elsevier　Ltd.　All　rights　reserved.