Professional Documents
Culture Documents
Overview
Working
with Data
Graphing, Statistics
Regression / Curve Fitting
Confidence / Correlation
Time
Series
Indexes
Lecture 4-2
Business Forecasting
Forecasting does not mean Estimating. It is a Prediction
Prediction
Price of Material
Availability & Cost of Labor
Market Demand/Price
Cost of Construction
Business forecasting involves extrapolation of past data into the future
by using
Linear or Non-linear curves
Mathematical relationships
Business forecasting periods/term
Short 2 Years
Medium 2 - 5 Years
Long Range > 5 Years
Lecture 4-3
CE-591-Cost Engineering and Control
Graphical Analysis
Descriptive Statistics
Collect/Organize/Analyze Data
Summarize/Present
Draw Conclusions/Make Decisions
Type of Data
Discrete
Continuous
Raw Data Communicates Little Information
Lecture 4-4
Graphical Analysis
A
Lecture 4-5
Obs
Rel Freq
Cum Freq
12.3512.75
12.7513.15
13.1513.55
1
6
33
0.003
0.019
0.102
0.003
0.022
0.124
13.5513.95
51
0.157
0.281
13.9514.35
14.3514.75
121
50
0.373
0.154
0.654
0.808
14.7515.15
44
0.136
0.944
15.1515.65
13
0.040
0.984
15.6516.05
5
324
0.016
1.000
1.000
Lecture 4-6
Example
Price range of $12.35-$12.75 is called
interval
End numbers (12.35 and 12.75) are called
limits
Size of the interval = 12.75-12.35 = 0.40
First Mid-point = [(12.35+12.75)/2] = 12.55
Graphical representation of relativefrequency is called histograms
Lecture 4-7
Graphical Presentation
Lecture 4-8
Frequency Curves
Joining the
midpoints of
histogram cells
creates frequency
curves
Lecture 4-9
Example 1
Lecture 4-10
Mean
Average
n
x + x +L+ xn
x= 1 2
=
n
i =1
x
n
Lecture 4-11
Lecture 4-12
Standard Deviation
Amount
Mean
(x x)
n
s=
Variance
n 1
Deviation
Lecture 4-13
Example 2
Find the mean, median, mode, range, standard deviation
and variance for the following set of data.
(a) 3,5,2,6,5,9,5,1,7,6
(b) 41.6, 38.7, 40.3, 39.5, 38.9
(c) 2, -1, 0, 4, 6, 6, 8, 3, 2
Lecture 4-14
the Data
Visual Interpretation
Apply Judgment
Lecture 4-15
Mathematical Model
Lecture 4-16
Example
Lecture 4-17
Why Graph?
Visual
Lecture 4-18
Regression Analysis
Least Squares
Minimize
Lecture 4-20
= a + bx
x 2 y x xy
a=
2
n x 2 ( x )
b=
n xy x y
2
n x 2 ( x )
The
Example 3
Lecture 4-22
Curvilinear Regression
Non-Linear Relationships
Curvilinear
Regression
y = ab x
Exponential
y = ax b
Power
Polynomial
y = a + b1 x + b2 x 2 + b3 x 3 +L+ b p x p ..
CE-591-Cost Engineering and Control
Lecture 4-24
Transformation
(Power Equation Model)
loga =
b=
Lecture 4-25
Lecture 4-26
Example 4 (1/4)
Y (10 ) Manhours
10
510
30
210
100
190
150
125
300
71
Lecture 4-27
Example 4 (2/4)
Solution
(log x)2
log x
log y
10
510
1.0000
2.7076
1.0000
2.7076
30
210
1.4771
2.3222
2.1819
3.4302
100
190
2.0000
2.2788
4.0000
4.5575
150
125
2.1761
2.0969
4.7354
4.5631
300
71
2.4771
1.8513
6.1361
4.5858
9.1303
11.2567
18.0534
19.8441
log x log y
Lecture 4-28
Example 4 (3/4)
Finding a and b
log a =
=
n ( log x ) 2 ( log x ) 2
(18 .0534 )(11 .2567 ) ( 9 .1303 )(19 .8441 )
b=
=
n ( log x ) 2 ( log x ) 2
5 (19 .8441 ) ( 9 .1303 )(11 .2567 )
5 (18 .0534 ) ( 9 .1303 ) 2
= 3 .1921
= 0 .5152
Lecture 4-29
Example 4 (4/4)
Lecture 4-30
Correlation
Correlation
Lecture 4-32
Correlation
Quantitative
r=
Measure
xy x y
n x ( x ) n y ( y )
1/ 2
1
Farther from 0, Stronger Correlation
-1r
Lecture 4-33
Example 5
Find
the
correlation of the
following data
(from example 3)
(Hint: use the
calculations done
for example 3)
CE-591-Cost Engineering and Control
Lecture 4-34
Cost Index
Ic
C c = C r
Ir
CE-591-Cost Engineering and Control
Cc = desired cost
Cr = reference cost
Ir = Index correspond to Cr
Ic = Index correspond to Cc
Lecture 4-36
Example 6
of
a
700,000-ft2
warehouse is planned for a future
period. Several years ago a similar
warehouse was constructed for a unit
estimate of $162.50 when index was
118. The index for the construction
period is forecast as 143. Forecast the
construction cost per ft2
Construction
Lecture 4-37
Arithmetic Development of
Indices
Arithmetic development of indices are of different types
(1)
Adding cost and dividing by their number
(2)
Adding the cost reciprocals and dividing by their
number
(3)
Multiplying the cost and extracting the root indicated by
their number
(4)
Ranking the cost and selecting the median value
(5)
Selecting the mode cost
(6)
Adding actual costs of each year and taking the ratio of
those sums
CE-591-Cost Engineering and Control
Lecture 4-38
Lecture 4-39
Change Rate
Figuring
I
r = e
I b
Using
1/ n
1 100
I e = I b 1 +
100
Lecture 4-40
Change Rate
Lecture 4-41
Example 7
Lecture 4-42
Example 7
Lecture 4-43
Example 8
Lecture 4-44
Example 8 Solution
Material
0*
Laser glass
$26,117
$24,027
$22,345
$21,228
Steel tubing
1913
2008
2129
2278
Al extrusion
418
426
439
456
Printed circuits
637
643
656
657
Harness cable
2103
2124
2134
2305
Glass tubing
4317
4187
4103
4185
$35,505
$33,415
$31,806
$31,119
100.0
94.1
89.6
87.6
Total
Index, %
* Benchmark Period
Lecture 4-45
Indexes
Basis
Lecture 4-46
Sample
Listing
of
Indices
Lecture 4-47
Summary
Objective
- Forecasting
Methods for Working with Data
Graphing, Statistics, Regression
Data
Lecture 4-48