CSM80006 LecW8 Managing Project Performance Statistics

CSM80006
ENGINEERING
PROJECT
MANAGEMENT
Managing Project Performance:
Statistics
Dr. Chai Chang Saar
cschai@swinburne.edu.my
E613
DULN004(Q) KP(JPS)5195/IPTS/1144 05 June 2004 Co. No. 497194-M
Intended Learning Outcomes
1. Identify statistical measures to improve productivity

for projects
2. Analyse statistical data effect on project productivity
3. Proffer solutions to project productivity statistics

Factor Analysis
A statistical method used to describe variability among observed, correlated
variables in terms of a potentially lower number of unobserved variables called factors.
• Example
Preparedness of Passenger Vehicle Delivery
“Preparedness” is not possible to measure directly (Latent Variable i.e.

unobserved; underlying)
“Preparedness” can be measured by ‘# of loaded car’, ‘Driver’, ‘Amount

of Fuel’
etc etc, and combined measure of these. (Observed Variable i.e.
Measure)

Factor Analysis
• Other Examples
 Customer
Satisfaction
 How deep is your

love?
 Sustainability
 Logistics Level
(Quality)

Factor Analysis
• Other Examples
 IQ (Intelligence Quotient) Test Verbal intelligence
Numerical intelligence
Spatial intelligence
Logical intelligence

Factor Analysis Aim
 Establishing a Scientific Analysis
 Identification of Causality i.e. ‘See through’ Insight in a Mechanism

homogeneous and heterogeneous
 Identification of Represent Variables i.e. Factors (Root)
 Identification of Factors’ Priorities aiming for Save Wastes and

Resource

Factor Analysis Aim

Ott and Longnecker, 2010)
Homogeneous vs Heterogeneous

Factor Analysis
 Logistics Level (quality)

Application of Factor Analysis
Step 1: Identification of Underlying Factors

Clusters variables into homogeneous sets
Step 2: Screening of Variables

Identifying groupings/representability
Step 3: Sampling of Variables

Building up a Hierarchy/Structure; Selective Variables to represent Entire Model
Step 4: Clustering of Objects

Step 1: Reviewing and Correcting the Structure

(The Johns Hopkins University and Elizabeth Garrett-Mayer 2006)
Factor Analysis Model

Factor Analysis Model

Covariance and Correlation (λ)
 Both describe the relations between variables: how they are related
Positively or Inversely
 Covariance
 Correlation
DULN004(Q) KP(JPS)5195/IPTS/1144 05 June 2004 Co. No. 497194-M (http://ci.columbia.edu/; Ott and Longnecker, 2010)
Covariance and Correlation (λ)
 Both describe the relations between variables: how they are related
Positively or Inversely
 Sample Covariance
Degree of freedom
Population Sample
 Sample Correlation Inferential Statistics
1, 2, 3, 4, 5
n-1 5-1
DULN004(Q) KP(JPS)5195/IPTS/1144 05 June 2004 Co. No. 497194-M (http://ci.columbia.edu/; Ott and Longnecker, 2010)
Correlation (r)
The correlation coefficient measures the strength of the
linear relationship between two quantitative variables. The
correlation coefficient is usually denoted as r.
two variables x and y collected from n individuals or objects

with means and standard deviations of the variables given
as and sx for the x-variable and and sy for the y-variable.
The correlation r between x and y is computed as:
DULN004(Q) KP(JPS)5195/IPTS/1144 05 June 2004 Co. No. 497194-M (Ott and Longnecker, 2010)
Correlation (r)
Correlation (r)
1. A positive value for r indicates a positive association between the two
variables, and a negative value for r indicates a negative association between
the two variables.
2. The value of r is a number between1 and1. When the value of r is very close to
1, the points in the scatterplot will lie close to a straight line.
3. Because the two variables are standardized in the calculation of r, the value of
r does not change if we alter the units of x or y. The same value of r will be
obtained no matter what units are used for x and y. Correlation is a unit-free
measure of association.
4. Correlation measures the degree of straight line relationship between two

variables. The correlation coefficient does not describe the closeness of the
points (x, y) to a curved relationship, no matter how strong the relationship.
Correlation (r)
Correlation (r)
Correlation = Causality???

Factor Analysis Methods

Factor Analysis Methods

Statistics
 Descriptive Statistics
Describe a Set of Data with index, such as mean; standard

deviation
 Inferential Statistics
Infer from a Sample of Data with index, such as MRA; T-test

Infer from a Sample Data what the Population might be.

Descriptive Analysis
Client
15% Academia
19%
Contracting
22%
Consulting
44%
70.0 66.1 66.4 66.4 66.4

64.0
62.1 61.0
60.0 56.9
50.0 45.8
42.5
40.0 Disagree
Undecided
29.8 30.9
30.0 27.6 Agree
25.7 25.5 25.5 25.5 25.7 Strongly Agree
20.0 17.1
11.7
10.0 8.1 8.1 8.1 8.1 8.1 8.1 8.1
0.0
1 2 3 4 5 6 7 8 9

Descriptive Analysis
1
38.9
26.4
25.2
5 2
42.1
9.4 35.6
26.2 24.8
19.7
12.0 17.122.6
8.7
19.0
22.4 22.4
27.9 28.6
30.8
40.4
Disagree
Undecided
4 3 Agree
Strongly Agree

Exploratory Factor Analysis
Rotated Component Matrixa
ITEM ITEM DEFINITION Component
1 2 3 4 5
TPSC1 Activity definition & Sequencing .589
TPSC2 Design Changes .823
TPSC3 Timely material delivery .747
TPSC4 Interim Payments .820
TPSC5 Meeting Estimated Time .792
QPSC1 Qualified & experienced personnel .869
QPSC2 Quality Assurance .829
QPSC3 Amount of rework required .803
QPSC4 Conformance to specification .863
CPSC1 Planning and Feasibility studies .827
CPSC2 Variation order costs .863
CPSC3 Architectural and Engineering Design .841
CPSC4 Equipment and Material costs .875
PPSC1 Flexibility to changes .907
PPSC2 Risk allocation .851
PPSC3 Payment mode .806
PPSC4 Price & Time certainty .835
SPSC1 Safety planning .738
SPSC2 Accident non-fatalities .801
SPSC3 Accident fatalities .774
SPSC4 Safety Monitoring and Control .818
Extraction Method: Principal Component Analysis.
Rotation Method: Varimax with Kaiser Normalization.
a. Rotation converged in 5 iterations.

(Ojoko et al., 2016)
Measurement Model (SEM)

Confirmatory Factor Model

Structural Model (AMOS)

Structural Model (Smart PLS)

(Enegbuma et al., 2014)
Reading Materials
Descriptive statistics is the term given to the analysis of data that helps describe,
show or summarize data in a meaningful way such that, for example, patterns
might emerge from the data. Descriptive statistics do not, however, allow us to
make conclusions beyond the data we have analysed or reach conclusions
regarding any hypotheses we might have made. They are simply a way to
describe our data.
Descriptive statistics are very important because if we simply presented our raw
data it would be hard to visualize what the data was showing, especially if there
was a lot of it. Descriptive statistics therefore enables us to present the data in a
more meaningful way, which allows simpler interpretation of the data. For
example, if we had the results of 100 pieces of students' coursework, we may be
interested in the overall performance of those students. We would also be
interested in the distribution or spread of the marks. Descriptive statistics allow us
to do this. How to properly describe data through statistics and graphs is an
important topic and discussed in other Laerd Statistics guides. Typically, there are
two general types of statistic that are used to describe data
(statistics.laerd.com)
Reading Materials
We have seen that descriptive statistics provide information about our immediate group of data. For example, we
could calculate the mean and standard deviation of the exam marks for the 100 students and this could provide
valuable information about this group of 100 students. Any group of data like this, which includes all the data you
are interested in, is called a population. A population can be small or large, as long as it includes all the data you
are interested in. For example, if you were only interested in the exam marks of 100 students, the 100 students
would represent your population. Descriptive statistics are applied to populations, and the properties of
populations, like the mean or standard deviation, are called parameters as they represent the whole population
(i.e., everybody you are interested in).
Often, however, you do not have access to the whole population you are interested in investigating, but only a
limited number of data instead. For example, you might be interested in the exam marks of all students in AUS. It
is not feasible to measure all exam marks of all students in the whole of AUS so you have to measure a smaller
sample of students (e.g., 100 students), which are used to represent the larger population of all students.
Properties of samples, such as the mean or standard deviation, are not called parameters, but statistics. Inferential
statistics are techniques that allow us to use these samples to make generalizations about the populations from
which the samples were drawn. It is, therefore, important that the sample accurately represents the population.
The process of achieving this is called sampling (sampling strategies are discussed in detail here on our sister
site). Inferential statistics arise out of the fact that sampling naturally incurs sampling error and thus a sample is not
expected to perfectly represent the population. The methods of inferential statistics are (1) the estimation of
parameter(s) and (2) testing of statistical hypotheses.
(statistics.laerd.com)
Logistics and Supply Chain Case Study:
Ford with Penske
• Steps
1) Map analysis of distribution centres
2) Delivery services defined into: daily, weekly, urgent stock ord
er
3) Collect data from all
4) Find the optimal option
5) Develop the best network option

Multiple Regression Analysis (MRA)
 Analysis Steps
1. Setting up Analysis Aims
2. Statistical Hypothesis or Model
3. Collecting and Analysing Data
4. Testing the Hypothesis

(Significance)
5. Drawing a Conclusion
 Three Questions to Regression Analysis
1. Testing Significance of Independent Variables on Dependent

Variable
2. Identifying the Most Significant Independent Variables
3. Estimating Dependent Variable



 Scatter Plot
A scatterplot is a useful summary of a set of bivariate data (two variables), usually drawn
before
working out a linear correlation coefficient or fitting a regression line. It gives a good visual picture
of the relationship between the two variables, and aids the interpretation of the correlation
coefficient or regression model. (stat.yale.edu)

 Scatter Plot

 Scatter Plot
1.Identify the functional relationship between independent and

dependent variables
2. Identify the correlations between independent variables to

predict
multicollinearity e.g. Weight by Height; Waist; Chest/Bust; Thigh
3. Identify the presence of unusual values (i.e. outlier

point)

 Scatter Plot

 Regression Models
Yi = aXi + b + ei
Y = dependent Variable
X = Independent
Variable
a = Regression Coefficient
b = Intercept
e = Error
 Regression Models
Y1 = aX1 + b + e1
Y2 = aX2 + b + e2
Y3 = aX3 + b + e3
Y4 = aX4 + b + e4
Y5 = aX5 + b + e5
Y6 = aX6 + b + e6
.
.
.
 Assumptions
1.Regression Coefficient a and b are parameter; constant

Not random, but fixed
2. Independent and dependent variables are on a linear function.
3. Independent variables: X is deterministic, not stochastic. Can be

Measured without errors.
4. Thus,,, Dependent variables: Y and Error: e are stochastic.

 Assumptions
5. Independent: errors (residuals) are independent. Do not affect

each other
6. Normality: errors (residuals) are normally distributed.
7. Homoscadicity: errors (residuals) have a constant variance*

 Terms
Deviation = Difference between the measured (observed) value

of a variable and some other value (e.g. Mean, Median, etc…)
Variation = Measures of how far a set of variables are spread

out from their certain value (mostly mean)

 Terms
Deviation = m(X) - xi Absolute Deviation = lm(X) - xil
m(X) is one of the central tendency of the group, i.e. mean; median
Variation = Average of the Squared Differences from the mean

= (m(X) - x1)^2+(m(X) - x2)^2+(m(X) - x3)^2…+(m(X) - xn)^2
n-1*
Standard Deviation (σ) = the Square Root of Variation

 Example

 Practice #1
Pick two students up as the representatives for the international competition
Hint? Mean; Deviation; Variation; SD

 Practice #2
200ml Milk Pack_ Quantitatively Defective or Acceptable?

permissible error: less than 4%





THANK YOU

CSM80006 LecW8 Managing Project Performance Statistics

Uploaded by

Document Information

Original Description:

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

CSM80006 LecW8 Managing Project Performance Statistics

Uploaded by

Copyright:

Available Formats

CSM80006

1. Identify statistical measures to improve productivity

DULN004(Q) KP(JPS)5195/IPTS/1144 05 June 2004 Co. No. 497194-M

Preparedness of Passenger Vehicle Delivery

“Preparedness” is not possible to measure directly (Latent Variable i.e.

“Preparedness” can be measured by ‘# of loaded car’, ‘Driver’, ‘Amount

DULN004(Q) KP(JPS)5195/IPTS/1144 05 June 2004 Co. No. 497194-M

 How deep is your

DULN004(Q) KP(JPS)5195/IPTS/1144 05 June 2004 Co. No. 497194-M

 IQ (Intelligence Quotient) Test Verbal intelligence

DULN004(Q) KP(JPS)5195/IPTS/1144 05 June 2004 Co. No. 497194-M

 Establishing a Scientific Analysis

 Identification of Causality i.e. ‘See through’ Insight in a Mechanism

 Identification of Represent Variables i.e. Factors (Root)

 Identification of Factors’ Priorities aiming for Save Wastes and

DULN004(Q) KP(JPS)5195/IPTS/1144 05 June 2004 Co. No. 497194-M

DULN004(Q) KP(JPS)5195/IPTS/1144 05 June 2004 Co. No. 497194-M

DULN004(Q) KP(JPS)5195/IPTS/1144 05 June 2004 Co. No. 497194-M

DULN004(Q) KP(JPS)5195/IPTS/1144 05 June 2004 Co. No. 497194-M

Step 1: Identification of Underlying Factors

Step 2: Screening of Variables

Step 3: Sampling of Variables

Step 4: Clustering of Objects

DULN004(Q) KP(JPS)5195/IPTS/1144 05 June 2004 Co. No. 497194-M

DULN004(Q) KP(JPS)5195/IPTS/1144 05 June 2004 Co. No. 497194-M

DULN004(Q) KP(JPS)5195/IPTS/1144 05 June 2004 Co. No. 497194-M

two variables x and y collected from n individuals or objects

4. Correlation measures the degree of straight line relationship between two

DULN004(Q) KP(JPS)5195/IPTS/1144 05 June 2004 Co. No. 497194-M

DULN004(Q) KP(JPS)5195/IPTS/1144 05 June 2004 Co. No. 497194-M

DULN004(Q) KP(JPS)5195/IPTS/1144 05 June 2004 Co. No. 497194-M

Describe a Set of Data with index, such as mean; standard

Infer from a Sample of Data with index, such as MRA; T-test

DULN004(Q) KP(JPS)5195/IPTS/1144 05 June 2004 Co. No. 497194-M

70.0 66.1 66.4 66.4 66.4

DULN004(Q) KP(JPS)5195/IPTS/1144 05 June 2004 Co. No. 497194-M

DULN004(Q) KP(JPS)5195/IPTS/1144 05 June 2004 Co. No. 497194-M

DULN004(Q) KP(JPS)5195/IPTS/1144 05 June 2004 Co. No. 497194-M

DULN004(Q) KP(JPS)5195/IPTS/1144 05 June 2004 Co. No. 497194-M

DULN004(Q) KP(JPS)5195/IPTS/1144 05 June 2004 Co. No. 497194-M

DULN004(Q) KP(JPS)5195/IPTS/1144 05 June 2004 Co. No. 497194-M

DULN004(Q) KP(JPS)5195/IPTS/1144 05 June 2004 Co. No. 497194-M

DULN004(Q) KP(JPS)5195/IPTS/1144 05 June 2004 Co. No. 497194-M

1. Setting up Analysis Aims

2. Statistical Hypothesis or Model

3. Collecting and Analysing Data

4. Testing the Hypothesis

 Three Questions to Regression Analysis

1. Testing Significance of Independent Variables on Dependent

2. Identifying the Most Significant Independent Variables

3. Estimating Dependent Variable

DULN004(Q) KP(JPS)5195/IPTS/1144 05 June 2004 Co. No. 497194-M

DULN004(Q) KP(JPS)5195/IPTS/1144 05 June 2004 Co. No. 497194-M

DULN004(Q) KP(JPS)5195/IPTS/1144 05 June 2004 Co. No. 497194-M

coefficient or regression model. (stat.yale.edu)

DULN004(Q) KP(JPS)5195/IPTS/1144 05 June 2004 Co. No. 497194-M

DULN004(Q) KP(JPS)5195/IPTS/1144 05 June 2004 Co. No. 497194-M

1.Identify the functional relationship between independent and

2. Identify the correlations between independent variables to

3. Identify the presence of unusual values (i.e. outlier

DULN004(Q) KP(JPS)5195/IPTS/1144 05 June 2004 Co. No. 497194-M

DULN004(Q) KP(JPS)5195/IPTS/1144 05 June 2004 Co. No. 497194-M

1.Regression Coefficient a and b are parameter; constant