Measures and Strengths of Association
Remember that while we may find two variables to be involved in a relationship, we also want to know the
strength of the association. Each type of variable has its own measure to determine this though. Three
measures will be discussed in this paper, Lambda, Gamma, and Pearson’s r.
Lambda
Lambda is a measure of association which should be used when both variables are nominal. Essentially
this means that knowing a person’s attribute on one variable will help you guess their attribute on the
other (Babbie et al., 2014).
Gamma
Gamma is used to explore the relationship between two ordinal variables. It can also be used to measure
association between one dichotomous nominal and one ordinal variable (Babbie et al., 2014, p. 227).
Unlike lambda, gamma indicates a strength of an association and a direction. The closer to -1.00 or +1.00,
the stronger the relationship, whereas the closer to 0 the weaker the relationship. You can determine the
direction of a relationship the following way:
A negative association is indicated by a negative sign. This means that as one variable increases the other
decreases- the variables are moving away from each other. For example, as social class increases, prejudice
decreases. On the other hand, a positive association, indicated by a plus or positive sign, means that both
variables change in the same direction, either increase or decrease. For example, as social class increases,
so too does prejudice or as social class decreases, so too does prejudice.
Correlation Coefficient- Pearson’s r
Pearson’s r, also known as the correlation coefficient, is the test measure used to determine the
association between interval/ratio variables. This measure is similar to Gamma in how it can be understood
and establish direction of association.
Value of Measures of Association
0.00
+ or - .01 to .09
+ or - .10 to .29
+ or - .30 to .99
Strength of Association
None- no assocation at all
Weak- uninteresting association
Moderate- worth making note of
Evidence of a strong association- extremely
interesting
Perfect- strongest association possible 1.00
Measures of Association in SPSS
Analyze – Descriptive Statistics – Crosstabs
Place your dependent variable in the Row and your independent variable in the Column. Click "Statistics"
to choose which test you will run for the measure/strength of association. You will select Lambda for
nominal variables, Gamma for ordinal variables (or one ordinal and one dichotomous nominal), or
Pearson’s r for interval/ratio variables.
Measures of Association in SPSS- Understanding Output
Lambda
The test above is looking at the relationship between one’s political affiliation and their race. We look at
the value .036, which is the measure when political party is the DV (see in table). This means that we can
improve our guessing of political affiliation by 4% if we know that person’s race. Based on our notes abo ...
Measures and Strengths of AssociationRemember that while w.docx
1. Measures and Strengths of Association
Remember that while we may find two variables to be involved
in a relationship, we also want to know the
strength of the association. Each type of variable has its own
measure to determine this though. Three
measures will be discussed in this paper, Lambda, Gamma, and
Pearson’s r.
Lambda
Lambda is a measure of association which should be used when
both variables are nominal. Essentially
this means that knowing a person’s attribute on one variable
will help you guess their attribute on the
other (Babbie et al., 2014).
Gamma
Gamma is used to explore the relationship between two ordinal
variables. It can also be used to measure
association between one dichotomous nominal and one ordinal
variable (Babbie et al., 2014, p. 227).
Unlike lambda, gamma indicates a strength of an association
and a direction. The closer to -1.00 or +1.00,
the stronger the relationship, whereas the closer to 0 the weaker
the relationship. You can determine the
direction of a relationship the following way:
A negative association is indicated by a negative sign. This
means that as one variable increases the other
decreases- the variables are moving away from each other. For
example, as social class increases, prejudice
decreases. On the other hand, a positive association, indicated
by a plus or positive sign, means that both
2. variables change in the same direction, either increase or
decrease. For example, as social class increases,
so too does prejudice or as social class decreases, so too does
prejudice.
Correlation Coefficient- Pearson’s r
Pearson’s r, also known as the correlation coefficient, is the test
measure used to determine the
association between interval/ratio variables. This measure is
similar to Gamma in how it can be understood
and establish direction of association.
Value of Measures of Association
0.00
+ or - .01 to .09
+ or - .10 to .29
+ or - .30 to .99
Strength of Association
None- no assocation at all
Weak- uninteresting association
Moderate- worth making note of
Evidence of a strong association- extremely
interesting
Perfect- strongest association possible 1.00
Measures of Association in SPSS
Analyze – Descriptive Statistics – Crosstabs
Place your dependent variable in the Row and your independent
variable in the Column. Click "Statistics"
to choose which test you will run for the measure/strength of
association. You will select Lambda for
3. nominal variables, Gamma for ordinal variables (or one ordinal
and one dichotomous nominal), or
Pearson’s r for interval/ratio variables.
Measures of Association in SPSS- Understanding Output
Lambda
The test above is looking at the relationship between one’s
political affiliation and their race. We look at
the value .036, which is the measure when political party is the
DV (see in table). This means that we can
improve our guessing of political affiliation by 4% if we know
that person’s race. Based on our notes above,
this is a pretty weak relationship and an uninteresting
association overall. Would we still continue? Yes,
maybe. It is important to note that this is one element of the
larger picture we are searching for.
Gamma
The relationship between one’s subjective class identification
and opinion on government welfare
spending is shown above. Gamma is used because both variables
are ordinal. The value of .071 means that
knowing a person’s subjective class status improves our
estimate of his/her opinion on government
welfare spending by 7%. Based on the chart above, this
relationship is weak. It is also not statistically
significant since .144>.05. Notice both IV and DV's codings
are consistent (all from low to high), thus the
4. positive sign of .071 indicates IV and DV are positively
associated, though not statistically significant.
Pearson’s r
For this test we are looking at the correlation between a
person’s age and the number of hours they spend
watching television. Keep in mind that the survey only
questioned adults over the age of 18. So, if you are
interested in seeing number of hours for children, this is not a
good data set for that. We want to square
the correlation here (.130 x .130) to determine the coefficient of
determination. This new measure = .0169.
We interpret this as approximately 2% of the variation in time
watching television is determined by a
person’s age.
Fast Forward Thinking
This data, coupled with the statistic from the test of
significance (ex. Chi-square, t Test, or ANOVA), will
help you to interpret your findings:
5. Mechanical Engineering Department
ME 406- Manufacturing and Design
Project A (Engineering Statistics and Manufacturing)
Title of the Project
Quality Control, Regression Analysis, and Models Fitting
Term 171
Class Section- xx
Project Team – Group X_X
xxxxxxxxx
Name 1 (Group Coordinator)
xxxxxxxxx
Name 2
xxxxxxxxx
Name 3
xxxxxxxxx
Name 4
Assigned on 13th November 2017
Due on 4th January 2018 (Before Exam starts)
Note Please Attempt each question as asked using the software
where ever mentioned. Full Report generated by
STATGRAPHICS Must be included in Problems 1 .All Excel
6. sheets be included in PROBLEMS where Excel has been used
such as in Q
Each problem should be started on separate page after pasting
the the problem statement at the top of the page. Your
Solution
will be typewritten.
A hard copy as (WORD +EXCELL SHEETS) be provided along
with a Hard copy in PDF format. Plus Software generated
reports
A soft copy as a CD (WORD +EXCELL SHEETS) be provided
along with a soft copy copy in PDF format. Plus Software
generated reports. CD Must have mentioned that it is
STSTISTICS PROJECT and it shoulf have All Project students
Name and ID mentioned on CD and a on a text file inside the
cD.
Project copies both word and PDF will be uploaded on WebCT
as will be explained later.
PROBLEM # 1 (1.5 point)
For alpha distribution
Find
7. a) Plot F(t) versus t/C for =0.05 , 0.1.0.15,0.2 ,0.25 and 0.3 (all
curves should be in one Figure for range of t/C varying from
(0+=0.05) to 4). Hint use Normal Distribution Function(select
True) of Excel subroutine for Z=-
b) Find pdf for t varying from -∞ to +∞ ,(note at t=0
function is undefined). Note
where
Z=-
c) Plot f(t) versus t/C for =0.05 , 0.1.0.15,0.2 ,0.25 and 0.3 .all
curves in one Figure for range of t/C varying from (0+=0.05)
to 4 . Hint use Normal Distribution Function (select False) of
Excel subroutine for Z=-
d) Median value of T, t0.5
e) Quantile, tp which is the solution of F(tp)=p .
f) Mode of T, (value of t where
PROBLEM # 2 (1.0 point) Use EXCEL and attach all
spreadsheet analysis with solution)
Fifty measurements of the ultimate tensile strength of wire are
8. given in the accompanying table.
a) Group the data and make an appropriate normalized
histogram (with total area of histogram be 1 ) to approximate
the PDF.
b) Calculate and for the distribution from the ungrouped data.
c) Using and from part b, draw a normal distribution through
the normalized histogram .histogram.
Ultimate Tensile Strength
103,779
102,325
102,325
103,799
102,906
104,651
105,377
100,145
104,796
105,087
104,796
103,799
103,197
106,395
106,831
10. 103,633
105,232
106,540
106,104
102,616
106,831
101,744
100,726
103,924
101,598
Source: Data from E. B. Haugen, Probabilistic Mechanical
Design Wiley, New York, 1980
(c) Determine the mean, median, and mode from the ungrouped
data.
(d) Determine the range and standard deviation from the
ungrouped data
(e) Plot the cumulative frequency distribution on normal-
probability paper, and determine the mean and standard
deviation.
(f), for the data given in Table .what are the 95 percent
confidence limits on the mean of the population?
11. PROBLEM # 3 (1.0 point) (Use EXCEL and attach all
spreadsheet analysis with solution)
Three sets of identical twenty five fatigue specimens were
tested at the three different level of stresses.. The number of
cycles to failure. The results are expressed as log, were as
follows.
TABLE 1: FATIGUE LIFE DATA
NUMBER OF CYCLES TO FAILURES
No.
S1
S2
S3
380 MPa
340 MPa
300 MPa
1
34200
125500
954000
2
16. )?
· What is the mean Ln of fatigue life ( μlnN) and its standard
deviation Ln of fatigue life (σlnN)?
· What are the Parameters of Lognormal distributions at
S1,S2and S3.
· Fit lognormal distribution to the data using linear regression
model using Excel or Use Statgraphics to fit the lognormal
models to data for each stress level and comment on how good
the fit is.
PROBLEM # 4 (1.5 point)
Q4. (a) The lifetime of a mechanical switch produced by a
company has been determined to have a population mean of μ =
2000 h and σ = 200 h. The temper of a phosphor bronze leaf
spring in the switch is changed slightly by the supplier. To
determine whether this has changed the product, a sample of
100 switches is tested to give the sample values and . Has there
been a change in the product? (0.75 point)
Q4. (b) A vendor of steel wire advertises a mean breaking load
of 10,000 lb. A sample of eight tests shows a mean breaking
load of 9250 lb and a standard deviation of 110 lb. Do our tests
support the vendor’s claim? (0.75 point)
17. PROBLEM # 5 Control Charts (1 point)
Problem 5-Refer your Text Book above ( See Ebook provided as
text book)- -Solve with appropriate calculations, tables and
charts
5.1-Problem 8.1 Parts (a) and (b) –P454
5.2 -Problem 8.28 Parts (a) and (b) –P470
PROBLEM # 6
Regression Analysis (MUST USE STATGRAPHICS_
ATTACH COMPLETE REPORT PLUS ONE PAGE SUMMARY
OF EACH FITTED MODEL) 2 points
Developing Cutting Forces Empirical Models of a Counter
Boring Process in Aluminum.
Counter boringis an operation to enlarge the hole made using
drilling. Counter boring or finish boring is a deep hole drilling
process that requires a work piece with a pre-existing bore.
Counter boring is used to enlarge the drilled hole to the proper
depth and machine a square shoulder on the bottom to secure
maximum clamping action from the faster. The drilling
used to produce a circular hole by removing solid metal. The
counter bore tool has a guide, called a pilot, which keep it
positioned correctly in the hole. Counter boring tools are often
used on low power machines were a small diameter solid
boring tool is used for the pre-bore and then a counter boring
18. tool is used to finish the job. Counter boring is also used when
there is a heat treat process required after the initial hole is
drilled or if a stepped hole is required.
Pilot of diameter d , which is the predrilled hole size in the
workpiece diameter of already drilled hole..
D Dia of the enlarged hole
Visit the link and download STATGRAPHICS FREE FOR 30
DAYS AND USE MULTIPLE REGRESSION MODULE (SEE
EXAMPLES ON WEBSITE) TO DEVELOP FOLLOWING
MODELS>
http://www.statgraphics.com/centurion-xvii
Regression Analysis http://www.statgraphics.com/regression-
analysis
And Quality Control Module (PROICESS CAPABILITY
BANALYSIS) from the link
http://www.statgraphics.com/process-capability-analysis
Following are the results of Cutting Forces measurements
experiments performed at KFUPM Workshop by Professor
Anwar K Sheikh. The results are being shared for regression
analysis learning objectives.
Cutting Force Fz as a Function of V,D,d and f
Fz
19. Newton
Speed , V
mm/minutes
Feed , f
Mm/revolution
d
mm
D
mm
Ln (FZ)
Ln(Speed)
Ln(feed)
Ln(D)
52
2463.007
0.03
3.5
6.5
3.951244
7.809138
-3.50656
1.252763
78
2463.007
0.05
48. Moment Mz as a Function of V,D,d and f
Mz Newton-meter
Speed , V
mm/minutes
Feed , f
Mm/ revolution
d
mm
D
mm
Ln (Mz)
Ln(Speed)
Ln(feed)
Ln(D)
39
2463.007
0.03
3.5
6.5
3.663562
7.809138
-3.50656
80. 9.5
18
6.476972
8.962757
-2.52573
2.251292
Using STATGRAPHICS -MULTIPLE LINEAR REGRESSION
MODULE develop the empirical model for cutting force Fz and
Torque (Moment) Mz can be writing as following
Proposed Model 1 Force (Model 1 F)
Proposed Model 1 Moments (Model 1 M)
Proposed Model 2 Force (Model 1 F) .In spread sheet create a
new column of val;ues.
Proposed Model 2 Moments (Model 1 M). In spread sheet
create a new column of values.
81. Find A,f ,b and c d e etc in Fz model using first data table ,and
Find B,d,e,f d using second Data table for each of the odel..
Write one page summary based upon completer regression
report generated by STATGRAPHICS for each fitted model .Its
goodness of fit as measured by R2 values and other important
coefficients tabulated and plotted in the report. (Attach PDF
copy of each full report of STATGRAPHICS output and your
EXCEL File used as input data.
c
b
a
V
D
f
A
Fz
´
´
´
=
f
e
d
V
84. 2
)
(
2
2
d
D
-
PLEASE LET ME KNOW IF YOU NEED ANY ADDITIONAL
INFO FROM ME. Please help I need a good grade.
In week 3, we used epsilons and 10-percent-point rule to
determine if a potential relationship between two variables is
worth examining further.
This week, we'll use tests of "measures of association" to figure
out the exact strength of a relationship between two variables.
In addition, we'll learn how to interpret SPSS outputs for
measures of association tests such as lambda, gamma, and
Pearson's r, along with other possible tests. Remember that
these tests are specific to the level of measurement that your
variables are. In other words, one test may not work in a
different relationship test. Here are the guidelines:
1. Both DV and IV are nominal variables: Lambda (when it is
85. not a 2X2 table)
1. If it is a 2X2 table: Phi
2. Both DV and IV are ordinal variables: Gamma
3. One variable ordinal AND the other variable dichotomous
nominal (like Yes/No, male/female, etc.): Gamma
1. One variable ordinal AND the other variable nominal (not
dichotomous, has more than 2 categories): Cramer’s V.
4. Both DV and IV are I/R variables: Pearson's r
To interpret the output:
Keep in mind measures of association is a statistical procedure
based on Proportional Reduction of Error (PRE). Thus the
format of interpretation will be:
......knowing the IV will reduce error in predicting the DV by
*%.
Please note: Don't just say "IV" and "DV" in your explanation.
You need to enter your variables names for IV and DV, and
replace * for the exact test value from the output. If the value of
Lambda is .34, then it will be interpreted as 34%.
Ok, now it is time for you to try! Be sure to test the strength of
association of your final project for this week's forum
discussion. You can download the class handout attached at the
bottom of the page, or Click here for details.