supervisor stops loading when the ratio of loaders to supervisors reaches 7: 1 . locter
knows that he will need temporary help when the forecasted average daily orders
exceed 300 . locter has frequently requested from two to four extra temporary workers
per day to guard against unexpected rush orders. if there was not enough work, he
would dismiss the extra people at noon after four hours of work.
the agency has not been pleased with locter’s practice of overhiring and has notified
elisko that it is changing its policy. from now on, if a person is dismissed before an
eight-hour assignment is completed, elisko will still be charged for an eight-hour day
plus mileage back to the agency for reassignment. this policy would go into effect the
following week.
paula brand, general manager, called jim locter to her office when she received the
notice from the agency. she told locter, “your staffing has to be better. this penalty could
cost us up to $300-$500 per week in labor cost for which we receive no benefit. why
can’t you schedule better?”
locter replied, “i agree that the staffing should be better, but i can’t do it accurately when
there are rush orders. by being able to layoff people at noon, i have been able to adjust
for the uncertain order schedule without cost to the company. of course the agency’s
new policy changes this.”
locter and brand contacted elisko’s controller, mitch berg regarding locter’s problem on
how to estimate the number of people needed each week. berg reasoned that locter
needed a quick solution until he could study the work flow. berg suggested a regression
analysis using the number of orders shipped as the independent variable and the number
of workers (permanent plus temporary) as the dependent variable. berg indicated that
data for the past year was available and that the analysis could be done quickly using
the accounting department’s computer system.
berg completed the two regression analyses that are presented below. the first regression
was based on the data for the entire year. the second regression excluded the weeks
when only the 10 permanent staff persons were used; these weeks were unusual and
appeared to be out of the relevant range.
locter was not familiar with regression analysis and, therefore, was unsure how to
implement this technique. he wondered which regression data he should employ, i.e.,
which one was better. when he recognized that the regression was based on actual
orders shipped by week, berg told him he could use the forecasted shipments for the
week to determine the number of workers needed.
regression equation:
w = a + bs
s = orders shipped