Skip to main content

Table 2 Hypothesis testing summary

From: Prediction of probable backorder scenarios in the supply chain using Distributed Random Forest and Gradient Boosting Machine learning techniques

Question

Hypothesis

Result analysis

Decision

a) Are the products out of stock resulting backorders?

H0: n = 0; where n = Quantity of product in the stock

Ha: n ≥ 1

p-value < 2.2e−16, for α = 0.05

Alternative hypothesis is true

b) Were the most sold items per month producing back-ordered?

H0:\({Backorder}_{Yes}=\mathrm{n}\), n = Average number of products sold per month

p-value < 2.2e−16, for α = 0.05

The alternative hypothesis is true

c) Are the lead time factors producing backorders?

H0: \({Backorder}_{Yes}=\)\({factors}_{lead-time}.\)

p-value < 2.2e−16, for α  = 0.05

The alternative hypothesis is true

d) Are the forecasted demands of products resulting in backorders?

H0: \({Backorder}_{Yes}=\)\({Forecast}_{high}\)

p-value < 2.2e−16, for α  = 0.05

The alternative hypothesis is true