Probability of Time Loss and Non-time Loss Accidents

From the table below, I am trying to evaluate the probability of the following: time loss, non-time loss and fatalities. How could I accomplish it please?


Year Work Orders Months Unsafe Incidents Time-Loss Non-Time Loss Fatalities
Year 1 8,082 12 3 0 1 0
Year 2 9,000 12 2 0 0 0
Year 3 10,766 12 11 0 0 0
Year 4 11,533 12 8 0 0 0
Total 39,381 48 24 0 1 0

Thank you.

This is really more of a statistics problem than an excel problem? What I mean is this board isn't really the right place to ask this question--you probably want to go ask some statisticians.

Based on what you've got I've done some simple things and attached them.

Anyway, there's only four data points, but I noticed the relationship between work order and incidents is not linear; ie, the probability of an event doubles or triples once you cross about 10,000 work orders. If I had to hypothesize, then I'm going to guess the push to meet production leads to safety getting compromised.

I appreciate very much your help.

Originally Posted by shg

Please Login or Register  to view this content.

You can't calculate probability, but you can calculate the upper and lower limits of a confidence interval for some specified confidence.

In F11 and copy across,

= IF(F9 = 0, "(none)", 2 * $C$9 / CHIINV(Confidence / 2, 2 * F9) )

That says there is no upper limit to the confidence interval that a time loss accident will occur, as none have occurred to date.

In F12 and copy across,

=IF(F9 = 0, $C$9 / -LN(1-Confidence), 2 * $C$9 / CHIINV((1-Confidence) / 2, 2 * (F9 + 1) ) )

That says that with 50% confidence (the value in C2), the low limit of a time loss accident is 56,815 work orders.

---------- Post added at 02:20 PM ---------- Previous post was at 02:19 PM ----------

Super! Your calculations point me the right direction. Thank you.