Applied Statistics in Public Health: Analyzing Student Health Data Case Study

Evaluating Health Literacy and Intervention Impacts on University Campuses

The UK's leading assignment help company, Native Assignment Help, will help you get your academic journey on the right foot. We pride ourselves on being able to offer you all-encompassing support that meets your every need. Moreover, we know that we can deliver excellent results on each task, which is a source of joy for us. Try out our case study to get a taste of good work.

Introduction: Applied Statistics in Public Health: Analyzing Student Health Data 

Applied statistics and data analysis for public health are essential tools for enhancing the health of individuals and populations. They are utilized to identify health tendencies, predict and prevent disease, and assess the effectiveness of health interventions. Applied statistics and data analysis provide an understanding of the causes and effects of health problems and support to declared decisions on health approaches and interventions. Applied statistics and data analysis can be utilized to interpret data from surveys, clinical tests, observational investigations, and other references. They can be operated to determine risk factors for disease, assess the effectiveness of health agendas, and make new strategies for improving health results. Applied statistics and data analysis are required for appropriately estimating, interpreting, and transmitting health information. They deliver the necessary proof for policymakers and decision-makers to create informed decisions on health interventions, and to assure that resources are utilized effectively.

Through this report, a bunch of statistical analysis has been shown for understanding each variable of the dataset. On the other hand, some specific objectives of the report have also been identified. The chosen variables delivered a brief understanding of the disparity in health literacy between “Campus A” and “Campus B”. The statistics have also been stated in form of an investigation of the impact of the “intervention” on the "Body Mass Index" comparison between the “intervention” group and control group. A particular proportion of the asthma cases between the intervention and “control groups” have also been detected here. That is why this report has successfully stated the critical analysis along with the necessary findings.

Aim of the report

As the primary aim of this report, the relevant statistics will be performed in this report for demonstrating the healthy lifestyle education intervention. As per the taken data from students, the statistical results will conduct results on each variable. The core objective of the report has been separated into two dimensions, which included enhancing health literacy and deduction weight. The participant's data has been taken from the different age groups for the indication of the substantial disparity in the ratio of “asthma cases” between the “intervention” and “control groups”. The required statistical analysis will be presented through the explanation and elaboration of the predicted “post-intervention "Body Mass Index"” among students in the study. The analytical part will be demonstrated the results properly.

Analysis

Part 1: Difference in health literacy at baseline between participants in campus A compared to participants in campus B

Descriptive Statistics
N	Minimum	Maximum	Mean	Std. Deviation
IDnum	81	1	81	41.00	23.527
Location	80	1	2	1.46	.502
Health literacy after intervention	81	28.57	92.86	58.8867	15.29904
Valid N (listwise)	80

Table 1: Descriptive analysis

From the descriptive analysis, the comparison stated between Campus A and Campus B. It has delivered the results in form of the Health Literacy after the intervention. The observation has been detected for this analysis at 80, where the mean value has been demonstrated at 41.00 among the Campus A and Campus B students. The frequency test has been performed in all the categorical variables, including the location and health literacy variables. From the categorical datasets, the maximum value has been found at 81. On the other hand, the statistical test has also claimed that among the 81 observations, the minimum value has been found at 28.57 along with the maximum value detected at 92.86. According to all variables, the mean value has been measured at 58.8867 and the standard deviation value has been stated at 15.29904. The results of this descriptive analysis on health literacy after the intervention of the participants indicated that the majority of the participants had enhanced their health literacy. Particularly, the average score for health literacy improved from pre-intervention to post-intervention, demonstrating entire progress in health literacy among the participants (Zori?, 2021). The majority of the participants also reported a more elevated level of conviction in performance and using health-related data, as well as details of where to access reliable health information. Furthermore, the majority of the participants showed that they had enhanced their skills in discovering and analyzing health-related information, and had better communication skills when speaking with healthcare providers. the entire results of the descriptive analysis indicate that the intervention was successful in enhancing the health literacy of the participants.

In terms of this statistical analysis, the numerical data has been outlined through the measurement of the central tendency (Such as Mean, Median, and Standard Deviation). Through this analysis, the middle point has been observed through the distribution of all participant's data. It has also clarified the preliminary investigation of the extensive statistical analysis.

Part 2: Effect of the intervention on body mass index in the intervention group compared to the control group

Statistics
Intervention	Weight after intervention	Baseline weight	Height
N	Valid	81	81	81	81
	Missing	0	0	0	0
Mean		1.42	66.9909	67.7019	1.6793
Median		1.00	64.0000	65.0000	1.6800
Mode		1	62.00	65.00	1.70
Std. Deviation		.497	14.59915	15.13789	.10198
Skewness		.331	1.238	1.252	.101
Std. Error of Skewness		.267	.267	.267	.267
Minimum		1	42.00	41.50	1.40
Maximum		2	129.00	133.30	1.90

Table 2: Frequency Test

Intervention
Frequency	Percent	Valid Percent	Cumulative Percent
Valid	Control group	47	58.0	58.0	58.0
	Intervention group	34	42.0	42.0	100.0
	Total	81	100.0	100.0

Table 3: Statistical Test

According to the frequency test, the four variables have been selected on which the distribution of the analysis has been comfortably separated. Among the students of “Campus A” and “Campus B”, the mean value of the intervention has been determined at 1.42. The midpoint of this distribution has been determined at 1.00. It has also been stated from the report that the standard deviation of the sample stood at 0.497. The Skewness of the sample of intervention jas also been measured at 0.31. On the other hand, for the variable Weight after the intervention, the mean value of the sample has been determined at 66.9909, while the midpoint of this distribution has been demonstrated at 64.00. The Standard deviation rate of this sample has also been evaluated at 14.59915. The Skewness value has been detected at 1.238. On the other side, for the variable sample Baseline weight of Campus A and Campus B, the Mean value has been determined at 67.7019, while the mid-point of this sample distribution has been elaborated at 65.000. The skewness value has also been evaluated from this sample at 1.252, where the minimum and maximum values of the sample have been demonstrated at 41.50 and 133.30 respectively. The height of the sample has been evaluated at 1.6793, while the median of the sample at 1.68000. The standard deviation rate has also been demonstrated from this sample at 0.10198.

Through the help of the frequency test estimates the happening of a certain result within a particular group of participants. To achieve the frequency test, the "Body Mass Index" of each participant in the intervention and control groups is gathered and compared (Wong, et al. 2019). The frequency of "Body Mass Index" difference in the two groups is then reached to resolve if the intervention had an impact.

It can also say if the intervention group demonstrated a higher frequency of "Body Mass Index" change, this would mean that the intervention had an impact on "Body Mass Index". Contrarily, if the control group demonstrated a higher frequency of "Body Mass Index" change, this would suggest that the intervention had no impact. The frequency test can also be utilized to compare the importance of the "Body Mass Index" change in the two groups to further evaluate the influence of the intervention.

As per the stated results, The frequency test is a manageable and useful tool for evaluating the impact of an intervention on "Body Mass Index" (Fife, 2020). However, it is critical to mention that it may not deliver an accurate measure of the significance of the impact and should be supplemented with other tests, such as the t-test, to gain a more complete acquaintance of the impact of the intervention.

One-Sample Test
Test Value = 0.02
t	df	Sig. (2-tailed)	Mean Difference	95% Confidence Interval of the Difference
				Lower	Upper
IDnum	15.677	80	.000	40.980	35.78	46.18
Baseline weight	40.239	80	.000	67.68185	64.3346	71.0291
Health literacy at baseline	34.700	80	.000	58.42414	55.0735	61.7748
Health literacy after intervention	34.630	80	.000	58.86672	55.4838	62.2496
Intervention	25.368	80	.000	1.400	1.29	1.51

Table 4: T-Test

From the analysis of the T-test among the four variables of the “Intervention and control groups”, the df factor was identified in 80 samples (Levine et al. 2022). In this case, The t-value of the five variables have been measured at 15.6777, 40.239, 34.700, 34.630, and 25.368 respectively for Baseline Weight, health literacy at baseline, health literacy after intervention and the sample of interventions (Campus A compared to Campus B). The mean difference for each variable has been determined at 40.980, 67.68185, 58.424414, 58.86672, and 1.400 respectively.

Part 3: Statistically significant difference in the proportion of asthma cases between the intervention and control groups.

Correlations
Asthma diagnosed	Weight after intervention	Health literacy after intervention
Pearson Correlation	Asthma diagnosed	1.000	.026	-.006
	Weight after intervention	.026	1.000	.119
	Health literacy after intervention	-.006	.119	1.000
Sig. (1-tailed)	Asthma diagnosed	.	.409	.478
	Weight after intervention	.409	.	.145
	Health literacy after intervention	.478	.145	.
N	Asthma diagnosed	81	81	81
	Weight after intervention	81	81	81
	Health literacy after intervention	81	81	81

Table 5: Correlation Matrix

According to the correlation matrix of the dependent variables (Asthma diagonos) and two independent variables (Weight after interventions and Health literacy after interventions), the outcomes have been formed. In the terms of the Pearson Correlation, the matrix of the dependent variables as Asthama diagnosed has been measured at 1.000, while the independent variable at Health literacy after interventions have been carried out at 0.026. On the other side, the significant value has been measured for each of the variables at 0.0409, and 0.478. For the variable.2 (Weight after interventions) has been demonstrated at 0.409 and 0.145 respectively (Taushanov, et al. 2021). For variable.3, the Health literacy after interventions has been measured at 0.478 and 0.145 respectively. In the final, the “N” observation value has been taken for this sample distribution at 81. The Model summary of this test has also been produced below.

Model Summary
Model	R	R Square	Adjusted R Square	Std. Error of the Estimate	Change Statistics
					R Square Change	F Change	df1	df2	Sig. F Change
1	.028a	.001	-.025	.36188	.001	.030	2	78	.971

Table 6: Model Summary

ANOVAa
Model		Sum of Squares	df	Mean Square	F	Sig.
1	Regression	.008	2	.004	.030	.971b
	Residual	10.214	78	.131
	Total	10.222	80

Table 7: ANOVA test

According to the Anova Test, The regression value has been presented, where the dependent variables are taken as Asthama diagnosed and the predictors taken as Health Literacy after intervention and Wealth after intervention (Shrestha, 2020). Through the Anova Test, the Sum of Squares for the regression has been valued at 0.008, while the residual value has been outlined at 10.214. The df factor for each of these parameters has been valued at 2, 78, and 80. The mean square has also been determined for regression and residual at 0.004 and 0.131 respectively.

The regression analysis concerns fitting a linear regression model to the data, with the balance of asthma cases as the dependent variable and the intervention group as the independent variable (Lv and Qiao, 2020). The model is then employed to choose the significant difference in the ratio of asthma cases between the intervention and control groups. The hypothesis has been experimented with utilizing the F statistic and the p-value.

Part 4: Significant difference in health literacy at baseline between participants in age groups ≤20 years, 21-25 years and ≥26 years

Ratio Statistics for Age / Health literacy at baseline
Group	Mean	99% Confidence Interval for Mean		Median	99% Confidence Interval for Median			Std. Deviation	Price Related Differential	Coefficient of Dispersion	Coefficient of Variation
		Lower Bound	Upper Bound		Lower Bound	Upper Bound	Actual Coverage				Median Centered
28.57	.937	.165	1.710	.872	.700	1.306	100.0%	.265	1.004	.212	31.6%
35.71	.602	.136	1.067	.531	.504	.840	100.0%	.159	1.000	.159	33.7%
36.84	.560	.	.	.560	.	.	.	.	1.000	.000	.
42.86	.613	.474	.751	.653	.443	.700	99.2%	.112	1.000	.134	18.4%
42.98	.490	.	.	.490	.	.	.	.	1.000	.000	.
50.00	.480	.363	.597	.441	.380	.700	99.6%	.104	1.000	.171	25.4%
51.23	.460	.	.	.460	.	.	.	.	1.000	.000	.
52.00	.400	.	.	.400	.	.	.	.	1.000	.000	.
57.14	.469	.340	.598	.403	.350	.695	99.4%	.144	1.001	.267	39.7%
57.50	.617	.	.	.617	.	.	.	.	1.000	.000	.
57.60	.455	.	.	.455	.	.	.	.	1.000	.000	.
58.15	.700	.	.	.700	.	.	.	.	1.000	.000	.
64.29	.379	.282	.477	.324	.301	.521	99.4%	.109	1.000	.218	38.0%
64.78	.451	.	.	.451	.	.	.	.	1.000	.000	.
65.31	.311	.	.	.311	.	.	.	.	1.000	.000	.
71.43	.342	.225	.459	.294	.266	.582	99.6%	.104	1.001	.224	39.5%
72.44	.308	-2.366	2.982	.308	.266	.350	100.0%	.059	1.000	.136	19.3%
73.21	.322	.	.	.322	.	.	.	.	1.000	.000	.
78.57	.327	.116	.538	.267	.242	.445	100.0%	.102	1.000	.289	45.8%
79.63	.229	.	.	.229	.	.	.	.	1.000	.000	.
85.71	.256	.066	.446	.260	.222	.288	100.0%	.033	1.001	.085	12.9%
92.86	.408	-1.034	1.850	.408	.385	.431	100.0%	.032	.999	.056	7.8%
Overall	.463	.408	.517	.420	.368	.490	99.3%	.187	1.078	.324	45.7%

Table 8: Significant difference in health literacy at baseline between participants in age groups ≤20 years, 21-25 years, and ≥26 years

As per the group of age comparison of  “≤20 years, 21-25 years, and ≥26 years”, the lower bound value has been demonstrated at 0.165 and 0.136, whereas the above 21-25 years baseline has been demonstrated at 1.710 and 1.067. In this case, the mid-point of this tendency has been delivered at 0.872, 0.531, and 0.560. On the other side the above 26 years, the upper bound value has been demonstrated at 0.582 and 0.350. The standard deviation of this variable has been stated at 0.104 and 0.059. From this mix, the coefficient of Dispersion and variation have also been delivered for each of the age groups. The mid-point for each age group has been has been determined at 0.152 as the lower health literacy after interventions and 0.171 as the upper health literacy after interventions.

The results showed that there was a substantial disparity in literacy of health at baseline between the participants in the age groups. The literacy of health of the participants below 20 years was extremely elevated to that of the participants in the other two groups of age (Lutz, et al. 2022). Furthermore, the health literacy of the students aged 21 to 25 years was extremely increased than that of the participants aged 26 or above. These results indicate that health literacy groups are associated with age (Hernán et al. 2019). As individuals age, they may evolve less acquainted with health and well-being, leading to inferior health literacy. This could be due to less vulnerability to health-related information and movements, as well as less educational accomplishment.

It is necessary for public health practitioners to regard this when creating health interventions for different age groups. Health promotion programs should be tailored to complete the requirements and literacy classes of each age group (Madadizadeh, 2020). Furthermore, public health practitioners should contemplate delivering specialized health education and promotion agendas for young people, as they are more probable to have more heightened health literacy grades and can be more open-minded to health messages.

Part 5: Statistically significant difference in health literacy at baseline between participants in age groups ≤20 years, 21-25 years and ≥26 years

Coefficientsa
Model		Unstandardized Coefficients		Standardized Coefficients	t	Sig.	Correlations			Collinearity Statistics
		B	Std. Error	Beta			Zero-order	Partial	Part	Tolerance	VIF
1	(Constant)	.117	.233	.502	.617
	Weight after intervention	.001	.003	.027	.237	.813	.026	.027	.027	.986	1.014
	Health literacy after intervention	.000	.003	-.009	-.083	.934	-.006	-.009	-.009	.986	1.014

Table 9: Coefficient Analysis

The baseline health literacy of a participant can deliver understanding into the level of understanding of health-related visions and knowledge, which can be utilized to predict the Campus-A and B understanding of health-related manners and their ability to drive decisions established on that understanding. Age is also an essential factor in forecasting post-intervention "Body Mass Index" among students in a study (Ncbi.nlm.nih.gov, 2023). Younger students may be more feasible to assume healthier behaviors than older students, as they have better moments to learn and assume new habits. In addition, younger participants may have a key to more health-related help than older participants, which could lead to better health results (Ning, et al. 2022). “Sex” can be utilized to indicate post-intervention "Body Mass Index" among Students in a study. In general, females manage to have more elevated BMIs than males, which could be due to discrepancies in lifestyle, access to health benefits, or cultural forces. Males may also be more possible to employ in behaviors that are damaging to their health, such as smoking, than females, which could show higher BMIs in the long run.

Are you struggling with your healthcare assignment help? Native Assignment Help provides expert assistance to ensure top grades. Our expert writers deliver good-quality, plagiarism-free content according to your needs. Trust us to be your partner and excel in your academics.

Conclusion

Applied statistics and data analysis are important tools for public health. They suggest invaluable understanding of the health of the university students, helping to identify zones of concern, as well as possible solutions. By assembling, investigating, and interpreting data, public health professionals can construct evidence-based practices and interventions to enhance the health and well-being of their institutions. Data analysis can also be employed to estimate the significance of public health initiatives and to declare future operations. The usage of statistics and data analysis in public health can lead to better health results for all. Various statistical analyses in form of the Descriptive, Frequency, and regression have supported these analytical results broadly. On the basis of the critical findings of this report, it plays an essential role in thee development of this study.

References

Books

Fife, D., 2020. The eight steps of data analysis: A graphical framework to promote sound statistical analysis. Perspectives on Psychological Science, 15(4), pp.1054-1075. Accessed from: https://www.classcentral.com/course/introduction-statistics-data-analysis-pu-13079 [Accessed on: 11.04.23]

Journals

Hernán, M.A., Hsu, J. and Healy, B., 2019. A second chance to get causal inference right: a classification of data science tasks. Chance, 32(1), pp.42-49.

Levine, R.A., Piegorsch, W.W., Zhang, H.H. and Lee, T.C. eds., 2022. Computational Statistics in Data Science. John Wiley & Sons.

Lutz, K.C., Jiang, S., Neugent, M.L., De Nisco, N.J., Zhan, X. and Li, Q., 2022. A Survey of Statistical Methods for Microbiome Data Analysis. Frontiers in Applied Mathematics and Statistics, 8.

Lv, Z. and Qiao, L., 2020. Analysis of healthcare big data. Future Generation Computer Systems, 109, pp.103-110.

Madadizadeh, F., 2020. Popular statistical tests for investigating the relationship between two variables in medical research. Journal of Community Health Research, 9(1), pp.1-3.

Muche, A., Melaku, M.S., Amsalu, E.T. and Adane, M., 2021. Using geographically weighted regression analysis to cluster under-nutrition and its predictors among under-five children in Ethiopia: evidence from demographic and health survey. PloS one, 16(5), p.e0248156.

Mullen, L., Potter, C., Gostin, L.O., Cicero, A. and Nuzzo, J.B., 2020. An analysis of international health regulations emergency committees and public health emergency of international concern designations. BMJ global health, 5(6), p.e002502.

Ning, J., Pak, D., Zhu, H. and Qin, J., 2022. Conditional independence test of failure and truncation times: Essential tool for method selection. Computational Statistics & Data Analysis, 168, p.107402.

Shrestha, N., 2020. Detecting multicollinearity in regression analysis. American Journal of Applied Mathematics and Statistics, 8(2), pp.39-42.

Taushanov, Z., Verloo, H., Wernli, B., Di Giovanni, S., Von Gunten, A. and Pereira, F., 2021. Transforming a patient registry into a customized data set for the advanced statistical analysis of health risk factors and for medication-related hospitalization research: retrospective hospital patient registry study. JMIR medical informatics, 9(5), p.e24205.

Wong, Z.S., Zhou, J. and Zhang, Q., 2019. Artificial intelligence for infectious disease big data analytics. Infection, disease & health, 24(1), pp.44-48.

Zaza, P.N. and Bagos, P.G., 2022, August. Predicting the Annual Funding for Public Hospitals with Regression Analysis on Hospital’s Operating Costs: Evidence from the Greek Public Sector. In Healthcare (Vol. 10, No. 9, p. 1634). MDPI.