JessupJamesBIAComprehensiveAssignmentFINAL

James Jessup Analytics | Winter Park, FL 32792 | www.jamesjessup.com
Medical Malpractice Claims Analysis
Business Intelligence Analytics Comprehensive Assignment
JAMES JESSUP
1.27.2015

CONTENTS
INTRODUCTION……………………………….………………….…………………………….3
TESTS AND TERMS USED……………………………………………………………………3
CORRELATIONS………………………….…..……………………………..………………….4
AMOUNT………………………………………………………………………………………….5
SEVERITY………………………………………………………………………………………..5
AGE………………………………………………………………………………………………..6
ATTORNEY RETENTION…………………………………..…………………………………..7
MARITAL STATUS…………………………………………………………….………………..7
SPECIALTY………………………………………………………………………………..……..9
INSURANCE…………………………………………………………………………………....10
GENDER……………………………………………………………………..………...……….11
MULTIPLE LINEAR REGRESSION…………………………………………………..……..11
CONCLUSION……………………………………………………………………….………....12
APPENDIX………………………………………………………………………………………13
REFERENCES…………………………………………………………….……………………22

Medical Malpractice Analysis
Introduction
Medical Malpractice payouts totaled $3.73 Billion in 2013. (Gower, 2014) To
better understand the factors affecting the amounts of these payouts, data was
collected including variables such as the payout amount, severity of the
claimants’ injuries and specialty of the physician. This paper describes the
methodologies and insights generated from analysis of this data.
Tests and Terms Used
Pooled Variance t-Test- This test is used to compare two samples from a
population that has a similar variance. It will determine whether there is a
significant difference between the two groups, by comparing the likelihood that
the selected sample is significantly different by random chance, or by actual
difference. (Comparing Two Independent Means, 2015)
Z Test for the Difference Between Two Proportions- This test is
appropriate to determine whether the difference between two proportions is
significant. It is recommended when the following conditions are met:
• The sampling method for each population is simple random sampling.
• The samples are independent.
• Each sample includes at least 10 successes and 10 failures. (Some texts
say that 5 successes and 5 failures are enough.)
• Each population is at least 10 times as big as its sample. (Hypothesis
Test, 2015)
NOTE: The sample size requirement was not met for some tests in this paper.
This decreases the reliability of the results. Given that the findings were
generally to fail to reject the null hypotheses, and that there was no significant
difference, the outcomes were not generally affected by the small sample
size.
Correlations- Correlation Analysis provides a quick look at whether or not two
variables are correlated. While correlation does not demonstrate causation, it
isn't always necessary to find causation; often, correlation is enough to note on
its own. Correlation shows the strength and the direction of numerical variables,
Positive correlation shows both variables move together in the same direction.
Negative correlation occurs when one variable rises as the other falls
Multiple Linear Regression- “Multiple linear regression attempts to model the
relationship between two or more explanatory variables and a response variable

by fitting a linear equation to observed data. Every value of the independent
variable x is associated with a value of the dependent variable y.” (Multiple Linear
Regression, 2015)
In this report, the Payout Amount is the dependent variable. The independent
variables will attempt to shape the dependent variable. The Regression Equation
will map out how this shaping looks.
Significance- This reports mentions “significance” may times. There are data
points that stand out above the others. These spikes in the data draw attention to
themselves. This report describes these spikes as “Noteworthy.” Some of these
Noteworthy points are also statistically significant. This means they have met the
statistical measure of significance and it is not considered by chance that they
are different, but rather by the intervention of some variable. Noteworthy items
are worth paying attention to. Significant items compel attention.
Unless otherwise noted, they Hypothesized Difference between two groups or
proportions is 0, and the Level of Significance if .05 to indicate a 95% Level of
Confidence. This means we can be approximately 95% certain that the results of
these hypothesis tests are not from chance.
Correlations
A Correlation Matrix was created for the Numerical Variables. Categorical
variables can be worked into this matrix if the can be translated in a binary
fashion, (i.e. Attorney/ No Attorney; Male/Female, etc.)
Amount Severity Age Attorney
Amount 1.00
Severity 0.39 1.00
Age -0.06 0.27 1.00
Attorney 0.27 0.34 -0.10 1.00
Gender -0.08 -0.06 -0.14 0.00
Figure 1.1 shows the Correlation Matrix.
If r = +.70 or higher Very strong positive relationship
+.40 to +.69 Strong positive relationship
+.30 to +.39 Moderate positive relationship
+.20 to +.29 weak positive relationship
+.01 to +.19 No or negligible relationship
-.01 to -.19 No or negligible relationship
-.20 to -.29 weak negative relationship
-.30 to -.39 Moderate negative relationship
-.40 to -.69 Strong negative relationship
-.70 or higherVery strong negative relationship (Pearson’s r Correlation, 2015)

Given these correlations and these definitions, the data demonstrates:
• Moderately positive correlation between Amount/ Severity, and Severity/
Attorney
• Weak Positive correlation between Age/ Severity and Attorney/ Amount
• The other variables failed to demonstrate significant correlation.
Amount
The Payout Amounts ranged from $1550 to $926,500. The average
amount was $91,044.
Figure 2.1 shows a histogram of the distribution.
The Payout Amount is treated as the Dependent Variable for the purposes of this
report. It can be expressed as a measure of the Independent Variables using
Regression Analysis. This calculation is featured in the Multiple Linear
Regression section.
The dependent variable is the item of interest. In this case, it will be most
important for insurance companies to find out which factors affect the Payout
Amount, and how they affect it. The other variables will be treated as
independent variables.
Severity
Figure 3.1 shows that as Severity increases, so does Payout (as represented by
the black line.) The size of the bubble represents the number of cases with that
Severity.
Severity has a significant impact on the Payout Amount. The greater the Severity,
the greater the Payout Amount.
11
5
13
5
1323
45
2
1

$(100,000)

$-‐

$100,000

$200,000

$300,000

$400,000

$500,000

0
1
2
3
4
5
6
7
8
9

Payout
Amount

Severity

Payouts
increase
with
Severity

The slope of the black line is approximately 30,586, which means that as the
Severity increases by 1, the average Payout increases by $30,586.
Age
There is a weak correlation between Age and Severity. This is demonstrated by
the black trend line in Figure 4.1
Figure 4.1
Given that Severity increases with age, it is counterintuitive that the
Payout Amount does not increase with age, and yet this is precisely what Figure
4.2 shows.
Figure 4.2
0

20

40

60

80

100

0
2
4
6
8
10

Age
in
years

Severity

Severity
increases
with
Age

Age

Linear
(Age)

0

200000

400000

600000

800000

1000000

0
10
20
30
40
50
60
70
80
90
100

Payout
Amounf
(dollars)

Age

Payout
Amount
is
Normally
Distributed

Attorney Retention
The data for Attorney usage was split between Attorney and No Attorney and
summarized (See Figure 5.1 Summary Table.) A simple ratio was developed
between the two groups. Since there were 78 instances of Attorney Usage and
40 of No Attorney, the ratio was approximately 2:1. The rest of the variables'
ratios were calculated. Most of them were similar to this 2:1 ratio. The ones that
were not were flagged for further examination.
One of the most significant differences was the Average Amount. A Pooled
Variance t-Test determined there was a significant difference between these two
amounts. When an Attorney was used, an average of $122,478 was awarded.
When No Attorney was used, this figure was $29,750. This difference is
significant. (See Figure 5.2)
The only other significance was found in the proportion of Family Practice clients
retaining legal council. A Z-Test for the Difference in Two Proportions
demonstrated a significant gap between the groups. People with Family Practice
issues are 16 times more likely to retain Attorneys. (See Figure 5.3)
Marital Status
Marital Status was provided in five codes (0,1,2,3,4). No definition of these
codes was provided; Some of them could be deduced, and these deductions will
be explained.
Marital Status
0 1 2 3 4
Count 6 22 71 2 17
Avg Amount $246,500 $95,347 $87,527 $28,000 $52,722
Severity 6.00 4.64 4.85 8.00 3.47
Age 39.50 26.91 47.08 79.00 42.59
Atty % 83% 59% 70% 100% 47%
Gender (% Male) 67% 27% 38% 0% 59%
Figure 6.1 Items of interest are noted in yellow. Items of Significance are noted in
red.
Code 0 (Married/Separated?) had a significantly larger Payout Amount. Their
average was $246,500, compared to the group average of $91,044.
The severity of this group was higher than average, but not significantly so (6,
compared to an average of 4.72)
The use of Attorneys was also higher in this group.

Code 1 has a lower average age as the distinctive factor. While not significant, it
is notable. This leads us to believe this group is "Single."
Code 2 (Married?) was undistinguished from the averages, which is indicative
that they comprise and define what "average" is. This was the largest group, with
an average age of 47.
Code 3 was estimated to be the "Widowed" group. The severity was significantly
higher in this group, an 8 compared to an average of 4.72. While the severity was
significant, the payout was he least among all the groups. This fact is
counterintuitive, given the severity, and this group was 100% represented by
Attorneys. The other interesting factor was the significantly advanced age of the
group (average 79) and the 100% Female group. These factors led to the belief
that this is the "Widowed" group. There were only 2 members of this group. A
larger data set would provide more convincing results.
Code 4 (Divorced?) Was also undistinguished. This was part of what led the
belief/ confusion between Married/Separated/Divorced. These groups are
believed to have similar demographics, though the Divorced group is assumed to
have a higher rate of attorney usage.
SIDE NOTE: An argument could be made for identifying these groups based on
age (Chronologically, it makes sense that a person would be Single, Married,
Separated, Divorced, Widowed)
This would identify the groups as
0-Married
1- Single
2-Divorced
3-Widowed
4-Separated
As this is not the main focus of this paper, more concentration was placed in
other areas.

Specialty
Dissecting the data by Specialty produced a few significant results, but not
as many as expected. (See Figure 7.1)
Figure 7.2
Dermatology produced significantly larger payouts that other Specialties.
Other noteworthy (but not significant) payouts were generated by Neurology/
Neurosurgery, OBGYN, and Pediatrics. Thoracic Surgery stood out as generating
lower payouts, though there was a small sample size and insufficient data to
make significant assumptions.
Pathology produced significantly more severe problems (8 compared to an
average of 4.75). Cardiology also produced significant differences in Severity (7
compared to the average of 4.75). The other specialties contributed to the
average without distinguishing themselves. (See Figure 7.3)

$-‐

$100,000

$200,000

$300,000

$400,000

$500,000

Payout
by
Specialty

Figure 7.3 Severity by Specialty
Pediatrics had a lower average age. This makes sense, given the
specialty, but is worth noting, so the data does not contribute to errors in common
sense.
It should be noted that some specialties retain attorneys at greater rates
than others. Cardiology, Neurology/Neurosurgery, Pediatrics, Physical Medicine
and Thoracic Surgery all had a 100% retention rate for attorneys.
Pediatrics stands out among the group. While not significant in any area
other than age, they are noteworthy in several areas, and for this reason, I
recommend gathering more data. This group gets a larger payout, universally
retains attorneys, and is younger than other groups. This bears further study to
gather more detailed data about their risk.
Insurance
Analyzing the data based on insurance did not produce any significant
results. (See Figure 8.1) A Pooled Variance t-test was employed to determine
significance for numerical data. No significant differences were found. Using the
Z-Test for the Difference Between Proportions, no significant differences were
found.
That said, it is worth noting that Private insurance bearers have an average
payout of $131,787, compared to the average of $80,593. This group also retains
Attorneys at a rate of 76.4%, compared to the average of 68%.
People using Workers Compensation use Attorneys 100% of the time, and
receive an average payout of $108,833.
0.00

1.00

2.00

3.00

4.00

5.00

6.00

7.00

8.00

Dermatology

Pediatrics

Urological

Neurology/
OBGYN

Emergency

Pathology

General
Surgery

Family
Practice

Orthopedic

Internal

Cardiology

Plastic
Surgeon

Ophthamology

Resident

Physical

Radiology

Anesthesiology

Occupational

Thoracic
Surgery

Severity
by
Specialty

Gender
The data was segregated by gender. To get a quick snapshot of possible
targets for additional analysis, a summary table was created (Figure 9.1). From
this, we calculated the ratios for Male to Female. We calculated this for all
variables to see if there were any that stood out above the rest. There were two
variables that did so.
More Males than Females were rated a "7" in Severity, resulting in a
higher than normal ratio. We ran this through a Z Test for the Difference in Two
Proportions and discovered a significant difference in this rate. Significantly more
Males than Females are rated a 7 in Severity. (See Figure 9.2)
No other significant variations were found with regards to gender.
NOTE: It is worth noting that some medical specialties are gender-specific. While
reviewing data, it's critical to keep the "big picture" in mind, and not become lost
in the details. For instance, from a data standpoint, it may appear notable that
there are 0 males who have initiated malpractice proceedings based on OBGYN
specialties. From a practical standpoint, this is self-apparent. Common sense is
always applicable.
Multiple Regression
The formula to calculate the Payout amount is:
Amount =- 3313.8140 + 29321.8816 * Severity - 1238.5624 * Age +
42729.0233 * Private Attorney - 9542.5526 * Marital Status
Severity is the strongest factor influencing Payout amount, and in fact, the only
factor that is considered significant. (See Figure 10.1)
Age appears to have a negative factor on payout amount. See Figure 4.2 and
note the declining black line.
Representation by an Attorney has a positive impact in payout amount.
Marital status is correlated to Payout Amount as well, but since this data was
categorical, it is not entirely appropriate to value it monetarily. That said, it DOES
play a role. While not necessarily causal, there IS a relationship there that
deserves consideration, if not further study.

Conclusion
The largest contributing factor to Payout Amount is Severity. The
Specialty is most likely the second most important factor, but with the number of
specialties and the small sample size, more data would be needed to determine
the extent of that interaction.
Attorney retention is also an important factor in payout amount. The
retention of an attorney adds an average of $92,728 to the Payout Amount.
Age and Marital Status may play causal roles in the retention of an
Attorney.
Recommendations:
Some of these variables appear correlated. Since Age is related to
Severity, there may be causation there. Marital status may be related to Attorney
Usage. The causalities are unknown at this point, but deserve to be considered
for future research.
Evaluate the risk of Malpractice Claims based on the following ranking of
criteria:
History of Claims
Severity of Past Claims
Specialty
Client Demographics
Age
Marital Status
Attorney on Retainer
Settling claims before attorneys are involved would be less costly. Avoiding
actions that could result in Malpractice Claims would be even more so.
Premiums charged by Malpractice Insurance Companies will need to take this
risk into consideration and be adjusted accordingly. Applications could be
developed that evaluate a Doctor’s patients, analyze the risk, and assign an
appropriate risk premium. This would allocate the risk more accurately, which will
help make insurance companies more profitable.

Appendix

Amount Severity Age Attorney
Amount 1.00
Severity 0.39 1.00
Age -0.06 0.27 1.00
Private
Attorney 0.27 0.34
-
0.10 1.00
Gender -0.08 -0.06
-
0.14 0.00

Figure
1.1

Correlation
Matrix

Histogram
No# of valid cases 117
Results for layer #1
Frequency distribution of 926500
926500 Count Cumulative Count Percent Cumulative Percent
Up To 1550 1. 1. 0.00855 0.00855
1550 To 4999 20. 21. 0.17094 0.17949
4999 To 14000 21. 42. 0.17949 0.35897
14000 To 23125 18. 60. 0.15385 0.51282
23125 To 61500 20. 80. 0.17094 0.68376
61500 To 160750 19. 99. 0.16239 0.84615
More 18. 117. 0.15385 1.

Figure
2.1
Histogram
of
Payout
Amount
values.

0

5

10

15

20

Up
To

1550

1550
To

4999

4999
To

14000

14000
To

23125

23125
To

61500

61500
To

160750

More

Count

Payout
Amount
Values


Figure
3.1

Figure
4.1

Figure
4.2

0

20

40

60

80

100

0
2
4
6
8
10

Age
in
years

Severity

Severity
increases
with
Age

Age

Linear
(Age)

0

200000

400000

600000

800000

1000000

0
10
20
30
40
50
60
70
80
90
100

Payout
Amounf
(dollars)

Age

Payout
Amount
is
Normally
Distributed


No Attorney Yes Attorney
Number 40 78
Average Amount $29,750 $122,478
Age 45.325 41.55128205
Severity
1 0 1
2 0 2
3 26 19
4 9 14
5 2 11
6 0 5
7 0 13
8 1 4
9 2 9
Marital Status
1 9 13
2 21 50
3 0 2
4 9 8
Insurance
Private 12 39
None 0 0
Medicare/Medicaid 6 10
Unknown 16 20
Male 16 31
Female 24 47
Specialty
Anesthesiology 11 2
Cardiology 0 4
Dermatology 1 1
Emergency Medicine 3 4
Family Practice 1 16
General Surgery 3 11
Internal Medicine 5 3
Neurology/Neurosurgery 0 7
OBGYN 5 8
Occupational Medicine 1 0
Ophthalmology 2 3
Orthopedic Surgery 1 10
Pathology 1 0
Pediatrics 0 2
Physical Medicine 0 1
Plastic Surgeon 1 1
Radiology 2 1
Resident 1 2
Thoracic Surgery 0 1
Urological Surgery 2 1
Figure
5.1
Summary
Table
of
Attorney
compared
to
No
Attorney


t Test for Differences in Two Means
Data
Hypothesized Difference 0
Level of Significance 0.05
No Atty Payout Amount
Sample Size 40
Sample Mean 29750
Sample Standard Deviation 65379
Atty Payout Amount
Sample Size 78
Sample Mean 122478
Sample Standard Deviation 189738
Intermediate Calculations
Population 1 Sample Degrees
of Freedom 39
Population 2 Sample Degrees
of Freedom 77
Total Degrees of Freedom 116
Pooled Variance
2533397
6703.336
2
Difference in Sample Means
-
92728.00
00
t Test Statistic -2.9957
Two-Tail Test
Lower Critical Value -1.9806
Upper Critical Value 1.9806
p-Value 0.0033
Reject the null hypothesis
Figure
5.2
Pooled
Variance
t-‐Test
of

Payout
amount.
Attorney
vs
No
Attorney

Z Test for the Difference in Two
Proportions
Data
No Atty
Number of Successes 1
Sample Size 40
Atty
Sample Size 78
Group 1 Proportion 0.0250
Difference in Two
Proportions
-
0.1801
Average Proportion 0.1441
Z Test Statistic
-
2.6376
Two-Tail Test
Lower Critical Value
-
1.9600
p-Value 0.0083
Reject the null
hypothesis

Figure
5.3
Z-‐Test
for
the
Difference
in

Two
Proportions
Family
Practice

Attorney
vs
No
Attorney

Marital Status
0 1 2 3 4
Count 6 22 71 2 17
Avg Amount $246,500 $95,347 $87,527 $28,000 $52,722
Severity 6.00 4.64 4.85 8.00 3.47
Age 39.50 26.91 47.08 79.00 42.59
Atty % 83% 59% 70% 100% 47%
Gender (% Male) 67% 27% 38% 0% 59%
Figure
6.1
Marital
Status
Summary
Table

NOTEWORTHY
SIGNIFICANT
Specialty
Count Avg Amt
Avg
Severity
Avg
Age sumAtty
Dermatology 2 $466,500 5.50 29.0 1.0
Pediatrics 2 $250,250 5.00 24.5 2.0
Urological Surgery 3 $187,329 4.33 51.3 1.0
Neurology/Neurosurgery 7 $182,244 5.43 43.9 7.0
OBGYN 13 $149,833 4.00 36.3 8.0
Emergency Medicine 7 $120,607 5.14 31.4 4.0
Pathology 1 $96,180 8.00 44.0 0.0
General Surgery 14 $87,492 5.93 47.4 11.0
Family Practice 17 $87,352 5.00 37.7 16.0
Orthopedic Surgery 11 $56,121 4.00 38.0 10.0
Internal Medicine 8 $51,850 5.63 57.0 3.0
Cardiology 4 $51,375 7.00 57.8 4.0
Plastic Surgeon 2 $42,750 4.50 50.0 1.0
Ophthalmology 5 $38,830 4.60 50.6 3.0
Resident 3 $36,583 4.00 28.3 2.0
Physical Medicine 1 $27,000 3.00 37.0 1.0
Radiology 3 $23,620 4.00 46.7 1.0
Anesthesiology 13 $10,275 2.92 49.3 2.0
Occupational Medicine 1 $9,000 3.00 54.0 0.0
Thoracic Surgery 1 $6,500 4.00 31.0 1.0
Mean $99,085 4.75 42.3 3.9
Std
Dev $109,640 1.29 10.10 4.32
Figure
7.1
Summary
of
Data
by
Specialty


Figure
7.2
Payout
Amount
by
Specialty

Figure
7.3
Severity
by
Specialty

Medicare/
Medicaid
No
Insurance Private Unknown
Workers
Compensation
Count 16 12 51 36 3
Avg Amount $56,677 $42,307 $131,787 $63,364 $108,833
Severity 5.25 3.666666667 4.725490196 4.805555556 5
Age 54.625 33.91666667 39.68627451 45.55555556 36.33333333
Private Atty 10 6 39 20 3
% Male 0.25 0.166666667 0.333333333 0.638888889 0.333333333
Ratio Atty 0.625 0.5 0.764705882 0.555555556 1
Figure
8.1
Summary
of
Data
sorted
by
Insurance

$-‐

$100,000

$200,000

$300,000

$400,000

$500,000

Payout
by
Specialty

0.00

1.00

2.00

3.00

4.00

5.00

6.00

7.00

8.00

Dermatology

Pediatrics

Urological

Neurology/
OBGYN

Emergency

Pathology

General
Surgery

Family
Practice

Orthopedic

Internal

Cardiology

Plastic
Surgeon

Ophthamology

Resident

Physical

Radiology

Anesthesiology

Occupational

Thoracic
Surgery

Severity
by
Specialty


Female Male Ratio
Number 71 47 0.7
Average Amount $80,175 $107,466 1.3
Age 40.81690141 45.87234043 1.1
Severity
1 1 0 0.0
2 2 0 0.0
3 26 19 0.7
4 14 9 0.6
5 10 3 0.3
6 4 1 0.3
7 4 9 2.3
8 3 2 0.7
9 7 4 0.6
Marital Status
1 16 6 0.4
2 44 27 0.6
3 2 0 0.0
4 7 10 1.4
Insurance
Private 34 17 0.5
None 0 0
Medicare/Medicaid 12 4 0.3
Unknown 13 23 1.8
Atty 47 31 0.7
No Atty
Anesthesiology 6 7 1.2
Cardiology 3 1 0.3
Dermatology 1 1 1.0
Emergency Medicine 2 5 2.5
Family Practice 9 8 0.9
General Surgery 10 4 0.4
Internal Medicine 4 4 1.0
Neurology/Neurosurgery 3 4 1.3
OBGYN 13 0 0.0
Occupational Medicine 1 0 0.0
Ophthalmology 4 1 0.3
Orthopedic Surgery 4 7 1.8
Pathology 1 0 0.0
Pediatrics 2 0 0.0
Physical Medicine 1 0 0.0
Plastic Surgeon 2 0 0.0
Radiology 0 3
Resident 2 1 0.5
Thoracic Surgery 1 0 0.0
Urological Surgery 2 1 0.5
Figure
9.1
Summary
of
Gender
and
Ratios

Z Test for the Difference in Two
Proportions
Data
Female ranked 7
Sample Size 71
Male ranked 7
Sample Size 47
Difference in Two Proportions
-
0.1352
Average Proportion 0.1102
Z Test Statistic
-
2.2955
Two-Tail Test
Lower Critical Value
-
1.9600
p-Value 0.0217
Reject the null hypothesis
Figure
9.2
Comparing
7s
between
Male
and
Female


Linear Regression
Regression
Statistics
R 0.44103
R Square 0.19451
Adjusted R
Square 0.166
S
150,229.
33334
Total number of
observations 118
Amount =- 3313.8140 + 29321.8816 * Severity - 1238.5624 * Age + 42729.0233 * Private
Attorney - 9542.5526 * Marital Status
ANOVA
d.f. SS MS F
p-
level
Regression 4.
6.15838
E+11
1.5396E+
11 6.82177
0.000
06
Residual 113.
2.55028
E+12
2.25689E
+10
Total 117.
3.16612
E+12
Coefficie
nts
Standard
Error LCL UCL t Stat
p-
level
H0 (2%)
rejected?
Intercept
-
3,313.81
402
53,812.3
0135
-
130,300.1
4529
123,672.
51724
-
0.061
58
0.95
101 No
Severity
29,321.8
8155
7,788.96
797
10,941.46
59
47,702.2
9721
3.764
54
0.00
027 Yes
Age
-
1,238.56
238
856.7260
2
-
3,260.265
44
783.1406
7
-
1.445
69
0.15
103 No
Private Attorney
42,729.0
2333
31,737.7
2026
-
32,165.68
582
117,623.
73247
1.346
32
0.18
089 No
Marital Status
-
9,542.55
255
14,890.5
2921
-
44,681.24
069
25,596.1
3559
-
0.640
85
0.52
292 No
T (2%) 2.3598
LCL - Lower value of a reliable interval (LCL)
UCL - Upper value of a reliable interval (UCL)
Figure
10.1
Multiple
Linear
Regression
Calculations

References
Comparing Two Independent Means - Unpooled and Pooled. (n.d.). Retrieved
January 27, 2015, from https://onlinecourses.science.psu.edu/stat200/node/60
Gower, J. (2014, February 19). 2014 Medical Malpractice Payout Analysis -
Diederich Healthcare. Retrieved January 27, 2015, from
http://www.diederichhealthcare.com/the-standard/2014-medical-malpractice-
payout-analysis/
Hypothesis Test: Difference Between Proportions. (n.d.). Retrieved January 27,
2015, from http://stattrek.com/hypothesis-test/difference-in-proportions.aspx
Multiple Linear Regression. (n.d.). Retrieved January 27, 2015, from
http://www.stat.yale.edu/Courses/1997-98/101/linmult.htm
Pearson’s r Correlation – A Rule of Thumb. (n.d.). Retrieved January 27, 2015,
from http://faculty.quinnipiac.edu/libarts/polsci/Statistics.html

THANK YOU.
FOR MORE INFORMATION CONTACT: JAMES JESSUP
JJESSUP@FULLSAIL.COM

JessupJamesBIAComprehensiveAssignmentFINAL

More Related Content

Viewers also liked (18)

Similar to JessupJamesBIAComprehensiveAssignmentFINAL (18)

JessupJamesBIAComprehensiveAssignmentFINAL