Safety Stock with a Fixed Lead Time

Lesson 19.2
12 minOpsida Teknoloji · Last reviewed: October 30, 2026

In one sentence

With a fixed lead time, safety stock covers the demand uncertainty that accumulates during replenishment without counting the average need again.

By the end of this lesson

  • Calculate the standard deviation of four-day demand from independent daily demand variability.
  • Find the safety stock and the average replenishment demand separately with the given service factor.
  • Separate the cycle service target from the share of units filled.
  • Refuse to apply the square-root rule directly to dependent or trending demand.

Why it matters

With a fixed lead time, safety stock covers the uncertainty about how much will be consumed until the moment the order is known to be ready for use. If the same quantity were consumed every day and replenishment really arrived in the same time, the average need would be enough. When daily demand varies, the average describes only the center point; in some replenishment periods higher consumption is seen. Safety stock is set aside for this difference. Putting the average demand back inside the safety stock counts the same need twice. Splitting the calculation first into average and uncertainty makes visible why the result arises and by which improvement it can be reduced.

If daily demands are independent and come from the same distribution, the variances of the days are added. Standard deviations are not added directly; the square root of the total variance is taken. As the lead time lengthens, the standard deviation of the uncertainty therefore grows with the square root of the time. This relation is not a law of nature to be applied to every demand series. If a product campaign raises several days together, if the days of the week differ markedly or if demand keeps growing, the simple assumption is questioned. The behavior of the data is examined before the calculation. A correct multiplication does not compensate for a wrong independence assumption; more records do not correct this error by themselves either.

The service factor z is related to the one-sided cycle service target chosen when the total demand of the replenishment period is represented by an approximately normal distribution. The given value z = 1.65 targets a cycle service of about 95%. This is not a promise that 95% of demand units will certainly be met or that exactly one shortage will occur in every twenty orders. The realized ratio varies with sampling. For the share of units filled, the size of the shortages is also needed. The coefficient of a two-sided confidence interval and the one-sided inventory protection factor do not serve the same purpose either; they are not used in place of each other by looking only at the similarity of the percentage.

In this lesson the lead time is exactly 4 days from the placing of the order to the usable acceptance of the material. A day means the working day on which demand data is kept. Mixing calendar days with working days distorts both the average and the protection period. If receiving inspection and internal transport are really inside this time, they are not added again; if they are outside, the scope is completed. Looking only at the time in the transport contract does not prove the fixed-replenishment assumption. The calculation result, together with the defined service target and the data conditions, is a policy input. To apply the ordering decision, inventory position, packaging and the movement record are also needed.

Formula

Average demand over the replenishment period (units) = Average daily demand (units/day) × L (days)

Demand variance over the replenishment period (units²) = Sum of the variances of L independent daily demands

Standard deviation over the replenishment period (units) = σd × √L

Safety stock (units) = z × σd × √L

Reorder point (units) = Average replenishment demand + Safety stock

Time base: σd is the deviation of one day's quantity in units

L is used as the number of one-day periods in the first variance term and as days in the time term

Kanban loop linking consumption, lead time and container quantityDrillingrefill 0.6 dayAssembly340 pcs/daySupermarket · 10 crates × 24 pcsWithdrawal cardProduction card340 × 0.6 = 204 pcs204 × (1 + 0.15) = 234.6 pcs234.6 ÷ 24 = 9.775 → 10
The figure contains a separate deterministic sizing: 340×0.6=204 units; adding 15% gives 234.6 units, rounded up to 10 containers with a container of 24 units. The 15% here is not the z factor or a cycle service probability; it does not replace the statistical safety calculation of 33 units. This dataset was generated synthetically for training; it does not represent a real business, employee or customer study.

Unlock the rest of this lesson with an Academy account

Create a free Academy account with your work email address; it can be used once it is approved.

  • Step-by-step instructions
  • Worked example with real numbers
  • Where the method misleads
  • Common mistakes
Create a free Academy account