StatCrunch logo (home)

Report Properties
Thumbnail:

from Flickr
Created: Oct 4, 2017
Share: yes
Views: 288
Tags:
 
Results in this report
 
Data sets in this report
None
 
Need help?
To copy selected text, right click to Copy or choose the Copy option under your browser's Edit menu. Text copied in this manner can be pasted directly into most documents with formatting maintained.
To copy selected graphs, right click on the graph to Copy. When pasting into a document, make sure to paste the graph content rather than a link to the graph. For example, to paste in MS Word choose Edit > Paste Special, and select the Device Independent Bitmap option.
You can now also Mail results and reports. The email may contain a simple link to the StatCrunch site or the complete output with data and graphics attached. In addition to being a great way to deliver output to someone else, this is also a great way to save your own hard copy. To try it out, simply click on the Mail link.
LSA levels and Breast CA- Week 7
Mail   Print   Twitter   Facebook

 

Introduction

Cancer is still an incurable disease and efforts continue to research and better understand the diverse types of cancer that exist. This study serves to analyze the nature of differences in average LSA measurements among 4 classifications of breast cancer. Group A acts as the control. Group B includes patients with benign breast disease. Group C includes those with primary breast cancer and Group D includes patients with recurrent metastatic breast cancer.

Methods

100 women were taken from each of these four groups. For each person in the sample, an LSA measurement was taken in mg/dl. The data collected is interval/ratio. This data will be analyzed using ANOVA to assess for any differences among the average amount of serum LSA across the four disease classification groups.  Tukey confidence intervals will be used to assess size of difference if differences exist per ANOVA. We have already established that the data meets the first assumption for use of ANOVA. The QQ plot provided shows that the points follow the line closely so normality can be assumed. Levene’s Test for homogeneity of Variance yields a p-value of 0.89 indicating that there is no evidence that variability is not constant. We can also assume independence.

 

Result 1: One Way ANOVA- Week 7   [Info]
Right click to copy

Levene's Test for Homogeneity of Variance

Test Statistic

DF 1

DF 2

P-value

0.20230997

3

396

0.8948

 

Analysis

Based on the results of the ANOVA F-test we have evidence that differences in average LSA amounts exist between at least two groups of breast cancer classification (F=96, p-value <0.0001).

Analysis of Variance results:
Responses: LSA
Factors: Group

Response statistics by factor

Group

n

Mean

Std. Dev.

Std. Error

A

100

16.249

2.684053

0.2684053

B

100

20.48

2.947932

0.2947932

C

100

19.976

3.0115978

0.30115978

D

100

23.292

3.1308398

0.31308398


ANOVA table

Source

DF

SS

MS

F-Stat

P-value

Group

3

2513.8239

837.94129

96.40839

<0.0001

Error

396

3441.8659

8.6915806

   

Total

399

5955.6898

     

 

Tukeys confidence intervals were used to determine which groups differ and ‘by how much’.  See below:

Tukey HSD results (95% level)
A subtracted from

 

Difference

Lower

Upper

P-value

B

4.231

3.1553289

5.3066711

<0.0001

C

3.727

2.6513289

4.8026711

<0.0001

D

7.043

5.9673289

8.1186711

<0.0001

B subtracted from

 

Difference

Lower

Upper

P-value

C

-0.504

-1.5796711

0.57167105

0.6216

D

2.812

1.7363289

3.8876711

<0.0001

C subtracted from

 

Difference

Lower

Upper

P-value

D

3.316

2.2403289

4.3916711

<0.0001

 

There are 6 pairwise comparisons. Interpretations as follows.

1.      Given the p-value <0.0001, we have evidence that the average LSA levels differ between the control group and those with benign breast cancer. With 95% confidence, we can estimate that the average amount of LSA is somewhere between 3.15 and 5.31 mg/dl higher in those with benign breast cancer then those without any form of breast cancer.

2.      Given the p-value of <0.0001, we have evidence that the average LSA levels differ between those with primary breast CA and those with no breast CA. With 95% confidence, we can estimate that the average LSA levels are somewhere between 2.65 and 4.8 mg/dl higher in those with primary breast cancer than those without breast CA.

3.      Given the p-value of <0.0001, we have evidence that the average LSA levels differ between those with recurrent metastatic breast cancer and those with no breast cancer. With 95% confidence, we can estimate that the average LSA levels are somewhere between 5.97 and 8.12 mg/dl higher in those with recurrent metastatic breast cancer than those without breast cancer.

4.      There is no evidence of a difference in average LSA levels between those with benign breast cancer and those with primary breast cancer.

5.      We have evidence of a difference in average LSA levels between those with benign breast cancer and those with recurrent metastatic breast cancer. With 95% confidence, we can estimate that the average LSA levels are somewhere between 1.7 and 3.89 mg/dl higher in those with recurrent metastatic breast cancer than those with benign breast cancer.

6.      We have evidence of a difference in average LSA levels between those with primary breast cancer and those with recurrent metastatic breast cancer. With 95% confidence, we can estimate that the average LSA level is somewhere between 2.24 and 4.39 mg/dl higher in those with recurrent metastatic breast cancer than those with primary breast cancer.

Discussion

Based on these results and statistical interpretations, we can safely say that average LSA levels are increased in those with breast cancer. It also appears that the levels are at their highest with recurrent metastatic breast cancer.

Conclusions/Further Study

As it has been proven that LSA levels are increased with breast cancer, further studies are warranted. These studies should assess if LSA can be considered an appropriate tool for diagnosing breast cancer. Moreover, studies should assess if following the trend in LSA levels in newly diagnosed breast cancer patients can help to track disease progress and possibly guide clinical decision making in treatment options.  Hopefully in the future new evidence-based practice will yield greater use for LSA test but for now LSA levels should be drawn regularly so that they may become part of the patient's permanent medical record for review or even for use to validate future studies.

HTML link:
<A href="https://www.statcrunch.com/5.0/viewreport.php?reportid=71920">LSA levels and Breast CA- Week 7</A>

Comments
Want to comment? Subscribe
Already a member? Sign in.
By nku.katie.waters
Oct 9, 2017

Hi Ashleigh,
Excellent job on your report! I glanced at your report and you seem to be on the right track. Your results and interpretations look great! Keep up the good work!
By ekilburn81
Oct 8, 2017

Great job on your report. I did the same topic. I found the topic very interesting. Breast cancer is a vicious disease that doesn't care who it affects. With the help of this research maybe we can start treating it earlier and better watch its progression. The women in our lives deserve it.
By ekilburn81
Oct 8, 2017

Great job on your report. I did the same topic. I found the topic very interesting. Breast cancer is a vicious disease that doesn't care who it affects. With the help of this research maybe we can start treating it earlier and better watch its progression. The women in our lives deserve it.
By danielle.hubbard85
Oct 6, 2017

This is a very interesting study. If LSA levels were proved through evidence based practice in diagnosing breast cancer would a break through this would be in diagnosing patients. Wouldn't that be great if women just needed their blood drawn to make sure they did not have a diagnosis of breast cancer. I would be interested to know what the false positives of this test would be. Great report!
By sadouskasm
Oct 5, 2017

Good job on your report. It would be great if this level could be used. It would be a great tool for breast cancer patients. I agree that it could help in deciding treatment options.

Michelle Cottingham

Always Learning