Final Data Analysis Project - Statistics 390:M1
Start Assignment
Due Apr 19 by 11:59pm
Points 80
Submitting a file upload
Available Apr 8 at 12am - Apr 19 at 11:59pm
FINAL DATA ANALYSIS PAPER Spring 2024, Statistics 390: Section MA
TOTAL: 80 points
Data Analysis Project/Methods Paper: Due Date: Fri. April 19, 2024 11:59 p.m. Requirements – Compile a data set of 20 points (observations, cases, study subjects, etc.) or more with two (2) quantitative variables (2 variables are needed). Insert in APPENDIX PART VII. (5 points)
Goal: Apply Methods learned from Statistics and SAS Programming to the SAME data set gathered or provided by a reliable source used in Homework Assignments no. 1, 2, 3 and 4 or NEW DATA SET but repeat all the homework assignments and include in the final project (Examples: https://www.kaggle.com//datasets (https://www.kaggle.com/datasets) ; www.census.gov (http://www.census.gov) ; www.cdc.gov (http://www.cdc.gov) ; etc. please no Wikipedia! Thank you!).
(Length: pages narrative; Tables-Charts-Figures separate) Final Paper Due: Fri. 04/19/2024 Submit to ASSIGNMENTS ON CANVAS by 11:59 p.m.
INCLUDE SEPARATE COVER PAGE TO INCLUDE:
Project Title
Submitted to:
Lynn A. Agre, MPH, PhD
Statistics 390: Section M1
April 19, 2024
By:
Student Name
RU Student ID No.
1. Abstract n = 150 words - brief description of proposed study (from univariate analysis) at least 5 sentences. (Total: 5 points)
Example Lead Sentence for the Abstract Summary: This study will investigate the relationship between x and y variables. This research will explore how x affects y. This analysis will explore the association between x and y.
1. Introduction/Background: Brief (at least 1 page) (Total: 5 points)
1. State the problem based on preponderance of evidence (at least two 2 literature citations). Literature Review - summarized in two or three paragraphs. Reliable sources are located on https://www.libraries.rutgers.edu/indexes/google_scholar (https://www.libraries.rutgers.edu/indexes/google_scholar)
2. Who or what is the unit of analysis – what is the topic being studied?
3. Where are the data collected, including the location (country) and source website.
4. When are the data collected – what time frame, i.e. year, months, etc.
1. Methods (at least 2 pages) (Total: 10 points)
Describe the data – i.e. Who or what is the unit of analysis—what is being compared (such as US States) and then the two variables –such as percent poverty by US State and percent unemployed by US State. Provide the data table.)
Please note: Describe methods briefly (what is being calculated, such as mean is weighted average) from all four (4) previous homework assignments plus current PROC REG and PROC GLM.
Formulas need to be included for THREE Hypothesis Tests
(cut and paste from lecture slides)
Hypotheses: – quantify by setting a threshold value, i.e. >, <, =
NOTE: Formulate 3 Hypotheses one each for a different method
1. From Homework No. 1: (5 points)
PROC MEANS
PROC FREQ
PROC UNIVARIATE
Cut and Paste SAS Code and Results4/9/24, 1:12 PM
1. From Homework No. 2: (5 points)
PROC MEANS t test
RECODE using IF, THEN STATEMENT
PROC FREQ re: Cross-Tabulations
PROC CORR
Cut and Paste SAS Code and Results
1. From Homework No. 3: ( 5 points)
PROC CHART vbar
PROC UNIVARIATE histogram
PROC FREQ to create PROC CHART vbar
PROC TABULATE for two (2) Classification Variables (add row percent)
PROC BOXPLOT or PROC SGPLOT (either one)
PROC PLOT and PROC SGSCATTER (both)
Cut and Paste SAS Code and Results
1. From Homework no. 4: (5 points)
PROC FREQ and PROC CHI SQUARE
PROC GLM and PROC ANOVA (can include hypothesis test as one of the three (3) hypotheses in the Methods Section)
PROC T TEST and specify PAIRED T test (can include hypothesis test as one of the three (3) hypotheses)
PROC CORR SCATTER (may need to use Output Delivery System or ODS SAS Command to Save as PDF file See Slide no. 73 from Jan. 30, 2024 lecture no. 3 notes) (can include hypothesis test as one of the three (3) hypotheses
Cut and Paste SAS Code and Results
1. From Homework No. 5: (5 points) – NEW ANALYSIS
PROC REG with OUTTEST option – produce tables, fit plot and residual diagnostic plots;
NOTE: if OUTTEST does not work use ODS graphics on
PROC GLM ( use Output Delivery System or ODS SAS Command to Save as PDF file See Slide no. 73 from Feb. 6, 2024 lecture no. 4 notes)
1. Results (at least 2 pages) (Total: 10 points)
Describe findings from the statistics tests (or analyses from all five assignments).
1. What are the significant results?
2. What are NOT the significant results?
1. Discussion or Interpretation (Explanation of Results) (at least 2 pages)
(Total: 10 points)
1. Are the two variables related?
2. Why is the research question important?
3. How do these statistics methods answer your research question? How do these methods illustrate or explain the objective of your paper?
4. What are the limitations of the study? What other variables can be included?
5. What is the broader impact of the study? Who can benefit from this research?
6. What future studies can be generated from the results of your research?
1. References – Bibliography (two (2) references at least one from last five years)
(Total: 10 points)
1. Need two (2) references;
2. Use Citation format or no credit given. Please do not copy and paste the URL (i.e. the website for the citation). A citation in URL format will not be given credit.
3. Scholarly articles from reliable source on topic being studied.