Parameter　calibration　is　the　precondition　of　the　application　of　micro　traffic　simulation　technology.　This　study　focuses　on　the　value　accessing　method　for　parameter　calibration　in　order　to　further　improve　the　parameter　calibration　process.　The　analysis　of　the　distribution　characteristics　of　each　parameter　calibration　results　shows　that　the　parameters　have　different　trends　in　the　process　of　gradual　iteration,　and　there　are　multiple　optimal　solutions　for　the　model　parameter　calibration　results.　In　this　paper,　the　dispersion　is　used　as　the　quantitative　analysis　index　of　the　concentration　degree　of　each　parameter　calibration　result,　and　the　parameter　value　of　the　model　is　determined　step　by　step　from　small　to　large　according　to　the　dispersion　degree.　Further　simulation　experiments　show　that　the　simulation　effect　of　the　proposed　method　is　better　than　that　of　the　traditional　method　and　much　better　than　the　default　parameter　value.　©　2019,　The　Editorial　Board　of　Journal　of　System　Simulation.　All　right　reserved.