CTC Statistics T Tests Discussion
- Assignment M7 as described in the lecture. NOTE: updated dataset so you will have to run descriptives and adjust all tables.
I will send the video lecture to see assignemnt details.
CORRELATION TESTS
1
Correlation Tests
Name XXX
Department of Nutrition and Family Sciences, University of Central Arkansas
FACS 6350: Statistical Methods
XXXX
March 03, 2022
Characteristic
APA Format
Formatting tables/ figures
Running Head/Cover page
Statistical notation in text
Introduction with literature review
Methodology and Description of
Variables
Points Available
1
1
1
4
2
Points Earned
0 must be in
APA and you
must have a
table for each
major analysis –
like the
correlation table
I provided as an
example
1
1
4
1.75
CORRELATION TESTS
Results (written for a results section
of a journal article)
Conclusion
SPSS Output Included
TOTAL
2
6
3
4
1
20
3
1
14.75
CORRELATION TESTS
3
Correlation Tests
This section should be about correlations and what they are.
Body Mass Index
Body mass index (BMI) is a calculation that requires the height and weight of a
specific person, the formula for BMI is weight divided by height, and usually the
measures of BMI are kg/m2 (Canada, 2022). This measure is widely used as an indicator
of whether a person is healthy in terms of his body weight and body height. The BMI can
help to categorize if a person is underweight, normal weight, overweight, or obese
depending on the age and gender (Ferrera, 2006). Would be more helpful to provide a
table here with the categories
Total Cholesterol
Cholesterol is a fat substance that can be found in all cells of the body. Total
cholesterol is a measure of the total amount of cholesterol in the blood of the body
(WebMD, 2020). There are 2 types of blood cholesterol, and the total blood cholesterol is
a measured of these 2 types, LDL cholesterol, and HDL cholesterol (WebMD, 2020).
LDL cholesterol is referred as bad cholesterol that can form fatty deposits on the arteries.
HDL cholesterol is referred as good cholesterol, it can help to remove the excess of
cholesterol in the body (WebMD, 2020).
Money Spent on Carryout
The money spent on carryout can be defined as the money a person spent in the
supermarket, fast food chain restaurants, and any type of food outside the house. The
CORRELATION TESTS
4
average American household spends about $3000 a year dining out according to the
Bureau of Labor Statistics (Statistics, 2017).
Systolic Blood Pressure
Blood pressure is the pressure of blood against the walls of the arteries. The blood
pressure reading is determined by 2 measures, systolic and diastolic blood pressures.
Systolic blood pressure measures the force the heart of a human exerts on the walls of the
arteries. Diastolic blood pressure, in the other hand, measures the strength the heart of a
human exerts on the walls of the arteries between the beats.
The normal systolic blood pressure for a health human is below 120 mm/Hg but
sometimes it can be higher than 140 mm Hg and we know this stage as hypertension.
Scientistic consider that adopting a healthy lifestyle can prevent a high blood pressure
and avoid health problems (Heart, 2003)
Methods
Research Questions
1.
1.
2. Is there a significant relationship between BMI0 and Money spent on
carryout? What timepoint? What strength? What direction?
2. Is there a relationship between BMI and minutes sedentary activity?
3. Is there a relationship between total cholesterol and systolic blood pressure?
Variables and Selection
CORRELATION TESTS
5
All subjects in the dataset with body mass index, money spent on carryout,
minutes sedentary activity, systolic blood pressure, and total cholesterol data were chosen
for analyses. All variables are continuous variables. Body mass index is measured in
kg/m2, systolic blood pressure is measured in mmHg, money spent on carryout/delivery
food is measured in dollars, minutes sedentary activity is measured in minutes, and total
cholesterol is measured in mg/dL.
Statistical Testing
There are 3 assumptions the data must meet before running the actual correlation,
those are normality distribution, linearity, and homogeneity of variance. A Shapiro Wilk
test was made to test if each variable is normally distributed, the p value of each ShapiroWilk was lower than alpha 0.05, so therefore the assumption of normality was not met for
any of the interest variables in the analysis. Also, histograms were created to get a visual
representation of each variable and the distributions of the variables. The histograms
suggest the distribution of each variable in the analysis is not normally distributed.
Scatterplots were created to check the linearity assumption. The relationship
between minutes sedentary and BMI is not linear, suggesting that the linearity
assumption for this relationship is not met.
Scatterplots between the dependent variable and the standardized residual of the
relationship for each test were created to check the homogeneity assumption. By looking
at the scatterplot for each relationship, the data are falling symmetrically above and
below the regression line, therefore the homogeneity assumption is met for each testing
relationship.
CORRELATION TESTS
6
Results
Descriptives
Descriptives were run in SPSS to determine the mean and standard deviation of
the 5 variables. The mean of body mass index at the beginning of the study was 34.82
kg/m2 with a standard deviation of 8.15 kg/m2. The mean of total cholesterol at the
beginning of the study is 175.78 mg/dL with a standard deviation of 43.87 mg/dL. The
mean total cholesterol after 1 year of the study is 179.71 mg/dL with a standard deviation
of 36.18 mg/dL. See table 1.
Table 1.
Participants Mean BMI and Cholesterol levels
Variable
mean
SD
BMI
34.82
8.15
Cholesterol 0
175.78
43.87
Systolic Blood Pressure
123.30
18.24
Minutes Sedentary
Activity
428.06
192.42
Money spent on
Carryout
53.53
105.09
n
319
319
319
319
318
There are 319 participants in total in the study, 107 (33.57%) are males and 212 (66.46%)
are female. All participants responded about their BMI, SBP, minutes sedentary activity
and cholesterol at the beginning of the study. There is only 1 missing value in the money
spent on carryout variable.
This is where you would put your assumptions testing results.
Correlations
There is a significant positive correlation identified between BMI and the
amount of money spent on carryout, r = .131, 95% BCa CI [.003, .259], p = .019.A
CORRELATION TESTS
7
Correlation Test was run to test if there is a relationship between money spent on
carryout and BMI at the beginning of the study. The test indicated that there is a
significant positive and weak relationship between money spent on carryout and BMI, r
(318) = 0.13, p < 0.05.
A Correlation Test was run to test if there is a relationship between minutes
sedentary activity and BMI at the beginning of the study. The test indicated that there is
no significant relationship between minutes sedentary activity and BMI, r (319) = 0.01, p
= 0.864.
A Correlation Test was run to test if there is a relationship between total
cholesterol and systolic blood pressure at the beginning of the study. The test indicated
that there is a significant positive and moderate relationship between total cholesterol and
systolic blood pressure, r (319) = 0.24, p < 0.05. There needs to be a better description of
your statistics and brief statements about what these stats mean. For example, what does a
“significant positive and weak relationship between money spent on carryout and BMI”
actually mean? You can then reiterate some points and expand on them in your
conclusion
Conclusions
Based on the results, there is a positive but weak relationship between money
spent on carryout and BMI, suggesting that as the money spent on carryout increases, the
BMI of the participant will increase as well. Also, the results suggest there is a positive
and moderate relationship between total cholesterol and systolic blood pressure, this
suggests that as the total cholesterol increases, systolic blood pressure increases too. A bit
CORRELATION TESTS
8
more detail on what you interpret these results to mean, in the bigger picture, would go
well here
One limitation of the study is about the sample, there is no information how the
data was collected, therefore, results might not be representative of the population. The
sample size was quite small compared to other studies. Some assumptions of correlation
tests were not met; therefore, the results might be not accurate and not representative of
the actual relationship between the variables. What are some future directions this kind of
research could take? what were some limitations to this analysis, and how can this
research be conducted differently in the future? Why does it matter if BMI decreases
when eating out decreases? Could you make an intervention about that? Who cares if TC
and BP decrease together?
CORRELATION TESTS
9
References
Canada, D. (2022, Feb 11). Body Mass Index Calculator. Retrieved from diabetes.ca:
https://www.diabetes.ca/managing-my-diabetes/tools---resources/body-massindex-(bmi)-calculator
Ferrera. (2006). Focus on Body Mass Index And Health Research. New York: Nova
Science.
Heart, L. N. (2003). National High Blood Pressure Education Program. The Seventh
Report of the Joint National Committee on Prevention, Detection, Evaluation, and
Treatment of High Blood Pressure .
Siegel. (1998). Nonparametric Statistics for the Behavioral Sciences. New York:
McGraw-Hill.
Statistics, U. B. (2017). Consumer Expenditures in 2015. Consumer Expenditures in
2015, 41.
WebMD. (2020, June). Understanding Cholesterol Numbers. Retrieved from
Webmd.com: https://www.webmd.com/cholesterolmanagement/guide/understanding-numbers
CORRELATION TESTS
10
Appendix A
CORRELATION TESTS
11
CORRELATION TESTS
12
CORRELATION TESTS
13
CORRELATION TESTS
14
CORRELATION TESTS
15
CORRELATION TESTS
16
CORRELATION TESTS
17
CORRELATION TESTS
18