The document discusses using regression analysis for human resource (HR) forecasting. It begins with an overview of forecasting, describing it as predicting future needs based on historical data. Regression analysis determines the proportional relationship between two variables, such as production output and manpower needs. The document shows an example using data from a jeans manufacturer to develop a regression equation that can predict HR needs based on production targets. It concludes that HR forecasting helps businesses efficiently allocate resources and avoid overstaffing or understaffing while reducing costs.
2. Topics:
HR Forecasting (Regression Analysis Method)
Contents:
Part – A:
Forecasting Overview
Part –B:
Regression Analysis
Part –C:
Wrapping up
3. Part – A:
Forecasting Overview
Part –B:
Regression Analysis
Part –C:
Wrapping up
What is Forecasting?
Forecasting is the process of predicting the future event
based on historical data
It is the underlying basis of all business decisions
Production
Personnel
Inventory
Facilities
HR forecasting is the process of predicting about the
human resource requirement for a future event.
4. Methods of Forecasting
Trend Projection
Individual Judgment
Regression Analysis
Econometrics Model
Delphi Method
Nominal Group Technique
5. Simple Linear Regression Model
BxAy
Regression analysis method determines the relationship between two
variables which is directly and precisely proportional and measures the
change of one variable in response to other.
Regression Equation for HR forecasting
y = Manpower requirements
x = Production output
A = Minimum requirement (?)
B = Regression co-efficient (?)
Variables
Constant
Part – A:
Forecasting Overview
Part –B:
Regression Analysis
Part –C:
Wrapping up
7. Sl.
Jeans Production
in Thousand
(x)
Total Manpower
(y)
xy x²
1 20 200 4,000 400
2 35 320 11,200 1,225
3 45 400 18,000 2,025
4 60 510 30,600 3,600
5 70 550 38,500 4,900
N=5 Ʃx=230 Ʃy=1,980 Ʃxy=102,300 Ʃx²=12,150
Jeans Manufacturer’s Data - Production output
- Manpower
146.7
)46(512150
)396)(46(5102300
)(
))((
222
xNx
yxNxy
B
26.67)46(146.7396 xByA
N
y
y
N
x
x
46
5
230
396
5
1980
Simple Linear Regression Model
8. y =67.26 + 7.146x
0
100
200
300
400
500
600
0 20 40 60 80
Manpower
Jeans Production (Thousand Pcs)
Regression Analysis Graph
Workforce
Requirment
Linear (Workforce
Requirment)
A = Minimum requirement to run the plant.
B = (Regression co-efficient) Change of y in response to1 unit change of x.
So, if the production target of the industry is 80 thousand pcs of jeans, then the
forecasted manpower requirements
y = 67.26 + 7.146 (80)
= 639
A = 67.26
B = 7.146
x = 80
y = ?
Simple Linear Regression Model
BxAy
9. In a nut shell..
HR forecasting prevent overstaffing, understaffing. It reduces HR cost, it
helps to efficiently and effectively use of HR. It helps to make macro
business decision.
Most importantly HR forecasting works as a safeguard against company’s
manpower investment.
It is not possible to forecast anything hundred percent correctly. As well
Regression Analysis also need some error consideration.
Finally, HR forecasting is not a superficial issue. It needs huge focus
because it won't take long to collapse if you make a significant mistake in
forecasting.