STAT 220 Linear Regression Project: Cancer Risk and Smoking Habits

This project, conducted for STAT 220, investigates the correlation between smoking habits and the incidence of various cancers, including bladder, lung, and kidney cancer, using statistical methods. The analysis involves descriptive statistics, including mean, median, standard deviation, and the creation of histograms and boxplots to understand data distribution. Correlation and regression analyses are performed to determine the linear relationships between the number of cigarettes smoked and cancer cases, with a focus on identifying significant relationships and potential for predictive modeling. The project concludes with a summary of the findings, highlighting the relative risks associated with smoking and cancer incidence, and the potential use of the developed models for predicting cancer cases. The project also adheres to the provided assignment brief which includes creating graphs, charts, and a presentation. Proper APA formatting is used throughout the paper. The study found significant correlations between smoking and cancer, particularly lung and bladder cancer, with regression models developed to predict the number of cancer cases based on smoking habits.

Does smoking increase the chance of
lung cancer along with other forms of
cancer in the U.S.?
Name:
Institution:

Descriptive statistics
On average people smoke 24.914 cigarettes.
On average there are 4.121 cases of bladder cancer, 19.653 cases of lung cancer
2.7945 cases of kidney cancer and 2.7945 cases of kidney cancer.
Lung cancer has the highest cases among the smokers and Kidney cancer cases is least
among the smokers (Keller, 2015).

Correlation
40302010
30
20
10
0
40302010
30
20
10
0
BLAD
CIG
LUNG
KID LEUK
Scatterplot of BLAD, LUNG, KID, LEUK vs CIG Strong positive correlation between
bladder cancer and number of cigars
smoked. R = 0.701, p-value < .05
(Keller, 2015)
Strong positive correlation between
lung cancer and number of cigars
smoked. R = 0.697, p-value < .05
Strong positive correlation between
kidney cancer and number of cigars
smoked. R = 0.487, p-value < .05
There is no linear relationship between
leukemia and number of cigar smoked.
R = -0.068, p-value = 0.698

Regression
• There is a significant linear relationship between number of cigarettes
smoked and bladder cancer
 BLAD = 1.086 + 0.1218 CIG
• There is a significant linear relationship between number of cigarettes
smoked and lung cancer
 LUNG = 6.47 + 0.5291 CIG
There is no linear relationship between number of cigarettes
smoked and leukemia
These two models could be used to predict the bladder cancer cases and
lung cancer cases.

Conclusion
The developed two models can be used to make number of
cancer cases for respective cancer forms.
 Lung cancer is the highest form of cancer among the cigarette
smokers.
Kidney cancer cases is lower among the cigarette smokers in US.
For non significant relationship, the average for the cancer cases
could be used as reference or predicted value for all the smokers
level.

References
Cohen, P., West, S. G., & Aiken, L. S. (2014). Applied multiple
regression/correlation analysis for the behavioral sciences (2nd ed.).
Psychology Press.
Keller, G. (2015). Statistics for Management and Economics, Abbreviated. Cengage
Learning.