MSC PUBLIC HEALTH – HEALTH PROMOTION QUANTITATIVE DATA ASSIGNMENT 2021/22
MSC PUBLIC HEALTH – HEALTH PROMOTION
QUANTITATIVE DATA ASSIGNMENT 2021/22
Table of Contents
Probability and statistical significance
Process of choosing statistical tests and theory about the tests
The assumption regarding parametric and non-parametric tests
Section
A
Descriptive
statistics
Figure 1: Descriptive statistics of
the demographic data
(Source:
SPSS)
Descriptive
statistics analysis of this indicates that the frequency of males is
comparatively lower than that of females. In the case of males, the
frequency percentage is 41.8 whereas, in the case of
females, the frequency percentage is 58.2. Under these statistics, the
minimum and the maximum value for the demographic data is highest in the case
of age
because this part consists of a comparatively high range of the
standard deviation. As this part consists of a high range of standard deviation
then the next two demographic data such as weight and height shows a range of
partial dominance in this scenario (Prentice et al. 2018). In the case of age, the maximum deviation is 65.00
whereas in the case of height maximum deviation is 198.00.
Descriptive statistics after 10 weeks indicate that the presence of the
highest number of values is in the case of after 10 weeks indicated by a mean
value of 87.15. A higher range of standard deviation is obtained in the
case of weight change with a deviation of 10.27.
T-test
Figure 2: Findings from the
statistical test regarding weight-loss group data
(Source:
SPSS)
The above
figure discusses a detailed overview of the t-test that has been confirmed by
IBM SPSS. Results of the t-test indicate that the mean value of weight loss is
maximum in the case of the male individual that has been indicated by 4.27,
whereas in the case of female individuals the weight loss is minimum that
indicated by 3.81. The lowest value of standard deviation is 3.1
which is represented the weight change of males and the standard deviation is
maximum in the case of the female individual that indicated by 3.72.
Standard error of mean regarding t-test is minimum in case of the female
individual that indicated by 0.54. Standard error of mean is
maximum in case of the male individual indicated by 0.55.
Descriptive
statistics of the whole
Figure 3: Descriptive statistics as
a whole
(Source:
SPSS)
This image
discusses a detailed overview of descriptive statistics of the whole data set.
In the case of diet 1.0, the highest level of waste change is indicated by 58
with a skewness value of -2.623. In the case of diet 2.0 highest value of
standard deviation is obtained by 10.80 after 10 weeks of diet. On the
contrary, in the case of diet 3.0, the highest value of standard
deviation is present in the case of weight before the diet indicated by 10.43.
The standard error of skewness and kurtosis value of these three diets is 0.481,
0.448 and 0.427. As the standard error is minimum in the case of diet 3
then it can be said that diet 3 has better ability in the loss of weight to an
ample extent (Bono et al. 2020). A
high range of skewness and kurtosis values also indicate that diet 1 and iron 2
is no longer valid for weight loss because there is a minimum deviation from
previous data and current data of weight change.
Inferential statistics with
paired-sample tests
Figure 4: Paired sample test
(Source:
SPSS)
Values of
the pair samples t-test indicate that the value is highest in the case of weight
before diet and lowest in the case of weight after diet that indicated
by 91.18
and 87.15. The pair sample test indicates the standard error of mean
indicated by 0.38787 with an upper value of 7.78.
Section
B
Probability
and statistical significance
Statistical
analysis with significance and probability is considered to be a determination
made by analysts by whom the result cannot be expandable with the chance
factor. Therefore it can be said that this stage provides determination from a p-value
that defines observing results assuming results align with the chance factor
alone. Statistical significance is the likelihood that indicates the difference
in conversion ratio between baseline and variation is not due to random chance.
It means there is a 5% chance that it could be wrong (Carrasco et al.
2020). A probable test can be done by proceeding with the chi square
test which indicates that there is the inclusion of a null hypothesis. The
presence of a null hypothesis indicates that variables nullify this concept.
0.05 is considered to be the baseline value of the probability factor. If a
statistical test is less than 0.05 then it can be said that the test hypothesis
is false and should be nullified. With higher than 0.05 indicates that there is
no effect observed in the statistical test.
Process
of choosing statistical tests and theory about the tests
In these
recent times, the statistical test provides a basis for differencing data in
the exposure of statistical theory. Some degree of descriptive statistics with
measurement of Central tendency is considered to be the main theme of
statistical analysis that is done by user-friendly software. SPSS is quality
statistical software by which data analysis is possible with minimum
complexity. Definition of variables and choosing quality variables are
considered to be the main theme of choosing the statistical test that can be summarized
by logistic regression (Sauerbrei et al. 2020).
A multivariate analysis program with binary dependent variables is needed for
constructing the statistical analysis. Moreover, data need to be divided into
numerical and categorical data sets. Division of these data sets can provide
sufficient learning regarding choosing statistical theory. Risk ratio odds
ratio with a rank of a correlation coefficient is also beneficial in this
scenario for conducting a statistical analysis.
The
assumption regarding parametric and non-parametric tests
Common
assumptions regarding non-parametric tests are considered to be randomness and
independence. The chi-square test is one of the statistical tests which is
considered to be nonparametric and consists of homogeneity, independence and
goodness of fit (Khomytska et al.
2020). Non-parametric parametric tests are not based on assumption;
it depends on data collection from a sample that has a minimum specific
distribution.
In order to
discuss a detailed overview of assumptions regarding the parametric test, it
can be observed that the taste which compares the mean values of data in the
case of each group shows a composition with Gaussian distribution (Pan
et al. 2020). The Gaussian
distribution indicates a normal distribution that exhibits similar degrees of
homoscedasticity. Homoscedasticity indicates homogeneity of variance that
consists of data of multiple groups with equal variances. Therefore, the main
assumptions of the parametric test indicate statistical distribution in the
data set whereas the nonparametric tests are devoid of any kind of
distribution.
Levels
for the measurement
There are
four levels of data set measurement that stand from lowest to highest such as
normal, ordinal, interval and ratio (Chou and Hung, 2021). This study regarding
wait analysis with three sequential diets charts indicates that there are two
statistical analyses performed throughout the study. These two types of
statistics act as measurement tools for descriptive and inferential statistics
with paired-sample tests. The analysis also indicates that data measurement
levels also depend on the standard deviation with skewness level to an ample
extent. Paired sample t-test of the inferential statistics relates with cumulative
frequencies of multifarious diets to an ample extent. Moreover, the
analysis also indicates that the data measurement level has worked
perfectly for the male individuals than that of the female individual.
Reference
lists
Bono, R., Arnau, J.,
Alarcón, R. and Blanca, M.J., 2020. Bias, precision, and accuracy of skewness
and kurtosis estimators for frequently used continuous distributions. Symmetry, 12(1),
p.19.
Carrasco, J.,
García, S., Rueda, M.M., Das, S. and Herrera, F., 2020. Recent trends in the
use of statistical tests for comparing swarm and evolutionary computing
algorithms: Practical guidelines and a critical review. Swarm and
Evolutionary Computation, 54, p.100665.
Chou, W.Y. and
Hung, S.H., 2021. Cumulative Frequency of Nature Dose: How Continuous and
Regular Forest Walking Improves Nature Relatedness, Restorativeness, and
Learning Engagement in College Students. Sustainability, 13(20),
p.11370.
Khomytska, I.,
Teslyuk, V., Kryvinska, N. and Bazylevych, I., 2020. Software-based approach
towards automated authorship acknowledgement—Chi-square test on one consonant
group. Electronics, 9(7), p.1138.
Pan, T., Zhao,
J., Wu, W. and Yang, J., 2020. Learning imbalanced datasets based on SMOTE and
Gaussian distribution. Information Sciences, 512,
pp.1214-1233.
Prentice, H.A.,
Lind, M., Mouton, C., Persson, A., Magnusson, H., Gabr, A., Seil, R.,
Engebretsen, L., Samuelsson, K., Karlsson, J. and Forssblad, M., 2018. Patient
demographic and surgical characteristics in anterior cruciate ligament
reconstruction: a description of registries from six countries. British
journal of sports medicine, 52(11), pp.716-722.
Sauerbrei, W.,
Perperoglou, A., Schmid, M., Abrahamowicz, M., Becher, H., Binder, H., Dunkler,
D., Harrell, F.E., Royston, P. and Heinze, G., 2020. State of the art in
selection of variables and functional forms in multivariable
analysis—outstanding issues. Diagnostic and prognostic research, 4(1),
pp.1-18.
Comments
Post a Comment