SU PHE5020 Complete Course Latest 2021 July (Full)

PHE5020 Biostatistical Methods

Week 1 Discussion

Sample Size and Statistical Assumptions

Certain basic assumptions are necessary to allow for the statistical analysis of public health data. However, the validity of these assumptions can be affected by the sample size being analyzed. The purpose of this assignment is to refresh your knowledge of the basic assumptions underlying the biostatistical analysis and to consider how these assumptions are affected by the sample size being analyzed.

Using the South University Online Library, the Internet, and your text readings, research the following statistical topics:

Statistical power

Central limit theorem (CLT)

On the basis of your research and understanding, respond to the following:

Find and state the definition of statistical power that you identify with.

State the definition of statistical power in your own words.

Compare and contrast type I and type II errors.

Explain how power is affected by sample size.

Find and state the definition of CLT that you identify with.

State the definition of CLT in your own words.

Summarize the basic assumptions underlying hypothesis testing and confidence interval methods.

Explain how these assumptions are affected by sample size.

Explain the relation of a sample size to the basic assumptions underlying biostatistical analysis.

 

PHE5020 Biostatistical Methods

Week 2 Discussion

Parametric vs. Nonparametric Methods

The purpose of this assignment is to differentiate between parametric and nonparametric statistical methods. In addition, this assignment will help you understand and implement parametric or nonparametric statistical methods.

Using the South University Online Library, the Internet, and your text readings, research the following statistical topics:

Levels of measurement

Parametric and nonparametric methods

On the basis of your research and understanding, respond to the following:

Find and state the definition of levels of measurement that distinguishes the five types of data used in statistical analysis.

In your own words, compare the five types of data and explain how they differ.

Find and state a definition of parametric and nonparametric methods that distinguishes between the two.

In your own words, explain the difference between parametric and nonparametric methods.

Explain which types of data require parametric statistics to be used and which types of data require nonparametric statistics to be used and why.

Compare the advantages and disadvantages of using parametric and nonparametric statistics.

Describe how the level of measurement helps determine which of these methods to use on the data being analyzed.

 

PHE5020 Biostatistical Methods

Week 3 Discussion

Statistics for Contingency Tables

The purpose of this assignment is to learn about categorical data and the statistics used to analyze this type of data.

You can expect to research and provide your own definitions of these concepts. You will also discuss in what situations to use each statistic, how these statistics are used to test for significance of relations among the data, and how to interpret each statistic. The takeaways from this assignment are an understanding of contingency tables as a representation of categorical data, two statistics used to analyze this type of data, and an understanding of how to interpret these statistics in the context of a public health analysis.

Using the South University Online Library, the Internet, and your text readings, research the following statistical topics:

Contingency tables

The chi-square

Fisher’s exact test (FET)

On the basis of your research, respond to the following:

Find and state a definition of a contingency table that you feel is easy to understand.

In your own words, explain what contingency tables are and what they are used for.

Explain what type of data is displayed in contingency tables.

Explain how contingency tables and their related statistics are used to test for significance of relations among the data.

Two statistics that can be used in contingency tables are chi-square and FET. Distinguish between the two statistics.

Explain when you would use the chi-square and when you would use the FET.

Explain how you would interpret each statistic.

PHE5020 Biostatistical Methods

Week 4 Discussion

Coefficient of Determination

The purpose of this assignment is to learn about the coefficient of determination (R2) statistic as a measure of the fit of a regression line.

R2 is a statistical measure of how close the data are to a fitted regression line. In general, the higher the R2, the better the model fits your data. However, while R2 measures goodness of fit, it does not indicate whether a regression model is adequate. You can have a low R2 value for a good model or a high R2 value for a model that does not fit the data.

Using the South University Online Library, the Internet, and your text readings, research about R2.

On the basis of your research and your involvement in public health functions, respond to the following:

Find and state a definition of R2 that you feel is easy to understand.

In your own words, provide a substantive explanation of what R2 represents.

Explain what the statistic R2 is used for in regression analysis.

Explain how R2 is affected by sample size.

Describe whether a large R2 value means that a regression is significant. Provide reasons for your answer.

Describe how you would substantively interpret R2.

 

PHE5020 Biostatistical Methods

Week 5 Discussion

ORs and RRs

This assignment will help you analyze the relationship of risk (of an illness) to exposure in public health regression analyses. Both ORs and RRs can be used to demonstrate the relationship between exposure and risk. However, each has its own advantages and disadvantages. While ORs are often used in professional papers, they are also often mistaken for RRs. RRs would often be the better choice as they are less complex than ORs and the interpretation is straightforward.

Using the South University Online Library, the Internet, and your text readings, research the following:

ORs

RRs

On the basis of your research, respond to the following:

Identify and state the definition of an OR that you feel is easy to understand.

In your own words, explain what an OR is and for what it is used.

Identify and state the definition of an RR that you feel is easy to understand.

In your own words, explain what an RR is and for what it is used.

Compare and contrast ORs and RRs and how they are used for multisample inferences.

Explain the advantages and disadvantages of using each ratio.

 

PHE5020 Biostatistical Methods

Week 1 Project  

Hypothesis Testing and Inference

This assignment focuses on estimation and hypothesis testing with one-sample and two-sample inferences.

The essence of parametric testing is the use of standard normal distribution tables of probabilities. For each exercise, there will be a sample problem that shows how the calculations are done and at least one problem for you to work out.

For the first assignment, you will not need any statistical software. However, you will use a standardized normal distribution table (a z-score table) provided in the course textbook (Table 3—The normal distribution—in the Tables section in APPENDIX) to obtain your responses.

Click here to access the standardized normal distribution table from your course textbook.

Problem 1: Probability Using Standard Variable z and Normal Distribution Tables

Variables are the things we measure. A hypothesis is a prediction about the relationship between variables. Variables make up the words in a hypothesis.

In the attention-deficit/hyperactivity disorder’s (ADHD’s) hypothetical example provided in the tables below, the research question was: What is the most effective therapy for ADHD? One of the variables is type of therapy. Another variable is change in ADHD-related behavior, given exposure to therapy. You might measure change in the mean seconds of concentration time when children read. This experiment is designed to obtain children’s concentration times while they read a science textbook and to find out whether the therapy used worked on any of the children.

Use the stated µ and σ to calculate probabilities of the standard variable z to get the value of p (up to three decimal places). In addition, respond to the following questions for each pair of parameters:

Which child or children, if any, appeared to come from a significantly different population than the one used in the null hypothesis?

What happens to the “significance” of each child’s data as the data are progressively more dispersed?

In addition to the above, write a formal statement of conclusion for each child in APA style. A report template is provided for submission of your work.

Note: Tables 1 and 2 are practice tables with answers. Tables 3 and 4 are the assignment tables for you to work on.

Table 1 (µ = 100 seconds and σ = 10)

Table 1 (µ = 100 seconds and σ = 10)

Child	Mean seconds of concentration in an experiment of reading	z-score (z = [X – µ]/σ)	p-value
1	75	-2.50	0.0
2	81	-1.90	0.0
3	89	-1.10	0.1
4	99	-0.10	0.4
5	115	1.50	0.0
6	127	2.70	0.0
7	138	3.80	<0.0
8	139	3.90	<0.0
9	142	4.20	<0.0
10	148	4.80	<0.0

Table 2 (µ = 100 seconds and σ = 20)

Child	Mean seconds of concentration in an experiment of reading	z-score (z = [X – µ]/σ)	p-value
1	75	-1.25	0.1
2	81	-0.95	0.1
3	89	-0.55	0.2
4	99	-0.05	0.4
5	115	0.75	0.2
6	127	1.35	0.0
7	138	1.90	0.0
8	139	1.95	0.0
9	142	2.10	0.0
10	148	2.40	0.0

 

Table 3 (µ = 100 seconds and σ = 30)

Child	Mean seconds of concentration in an experiment of reading	z-score	p-value
1	75	-0.83
2	81	-0.63
3	89	-0.37
4	99	-0.03
5	115	0.50
6	127	0.09
7	138	1.27
8	139	1.30
9	142	1.40
10	148	1.60

 

Table 4 (µ = 100 seconds and σ = 40)

Child	Mean seconds of concentration in an experiment of reading	z-score	p-value
1	75	-0.63
2	81	-0.48
3	89	-0.28
4	99	-0.03
5	115	0.38
6	127	0.68
7	138	0.95
8	139	0.98
9	142	1.05
10	148	1.20

 

Click here for a template to provide your answers and submit the assignment.

Refer to the Assignment Resources on this page for Two Independent Samples of t-Test to view an example of probability using standard variable and normal distribution tables. The same resource is also available under lecture Estimation and Hypothesis Testing.

Problem 2: Two-Sample Inferences

A two-sample inference deals with dependent and independent inferences. In a two-sample hypothesis testing problem, underlying parameters of two different populations are compared. In a longitudinal (or follow-up) study, the same group of people is followed over time. Two samples are said to be paired when each data point in the first sample is matched and related to a unique data point in the second sample.

This problem demonstrates inference from two dependent (follow-up) samples using the data from the hypothetical study of new cases of tuberculosis (TB) before and after the vaccination was done in several geographical areas in a country in sub-Saharan Africa. Conclusion about the null hypothesis is to note the difference between samples.

The problem that demonstrates inference from two dependent samples uses hypothetical data from the TB vaccinations and the number of new cases before and after vaccination.

 

Table 5: Cases of TB in Different Geographical Regions

Geographical regions	Before vaccination	After vaccination
1	85	11
2	77	5
3	110	14
4	65	12
5	81	10
6	70	7
7	74	8
8	84	11
9	90	9
10	95	8

Using the Minitab statistical analysis program to enter the data and perform the analysis, complete the following:

Construct a one-sided 95% confidence interval for the true difference in population means.

Test the null hypothesis that the population means are identical at the 0.05 level of significance.

Click here to install Minitab Software.

In addition, in a Microsoft Word document, provide a written interpretation of your results in APA format.

Problem 3: Cross-Sectional Study

In a cross-sectional study, the participants are seen at only one point of time. Two samples are said to be independent when the data points in one sample are unrelated to the data points in the second sample.

The problem that demonstrates inference from two independent samples will use hypothetical data from the American Association of Poison Control Centers.

There are two groups of independent data collected in different regions, which also calls for a t-test. The numbers represent the number of recorded cases of poisoning with chemicals in the homes of 100,000 people in two regions.

Table 6: Cases of Poisoning With Chemicals

Year       Region 1               Region 2

1              150         11

2              160         10

3              132         14

4              110         12

5              85           10

6              45           11

7              123         9

8              180         11

9              143         10

10           150         14

Using the Minitab statistical analysis program to enter the data and perform the analysis, complete the following:

Formulate a null and an alternative hypothesis for a two-sided test.

Conduct the test at the 0.05 level of significance.

In addition, in a Microsoft Word document, provide a written interpretation of your results in APA format.

 

PHE5020 Biostatistical Methods

Week 2 Project  

Instructions

Week 2: Project Assignment

This assignment focuses on nonparametric methods. When a researcher is not in a situation to be able to assume parametric statistical methods requirements, known distribution, or dealing with small sample size, then nonparametric statistical methods need to be used, which make fewer assumptions about the distributional shape.

Click here to install Minitab Software.

Nonparametric Methods

In this assignment, we will use the following nonparametric methods:

The Wilcoxon signed-rank test: The Wilcoxon signed-rank test is the nonparametric test analog of the paired t-test.

The Wilcoxon rank-sum test or the Mann-Whitney U test: The Wilcoxon rank-sum test is an analog to the two-sample t-test for independent samples.

For each exercise, there will be a sample problem that shows how the calculations are done and the problems for you to work on.

Part 1: Wilcoxon Signed-Rank Test

Let’s take a hypothetical situation. The World Health Organization (WHO) wants to investigate whether building irrigation systems in an African region helped reduce the number of new cases of malaria and increased the public health level.

Data was collected for the following variables from ten different cities of Africa:

The number of new cases of malaria before the irrigation systems were built

The number of new cases of malaria after the irrigation systems were built

Table 1: Cases of Malaria

City	Before	After
1	110	55
2	240	75
3	68	15
4	100	10
5	120	21
6	110	11
7	141	41
8	113	5
9	112	13
10	110	8

Using the Minitab statistical analysis program to enter the data and perform the analysis, complete the following:

Run a sample Wilcoxon signed-rank test to show whether there is a statistically significant difference between the number of cases before and after the irrigation systems were built.

Obtain the rank-sum.

Determine the significance of the difference between the groups.

Determine whether building these systems helped reduce new cases of malaria.

In addition, in a Microsoft Word document, provide a written interpretation of your results in APA format. Refer to the Assignment Resources: Wilcoxon Signed-Rank Test Example to view an example of the Wilcoxon signed-rank test. The same resource is also available under lecture Nonparametric Methods.

Part 2: Wilcoxon Rank-Sum Test

Let us consider another hypothetical situation. The WHO wants to compare the mortality rates of children under the age of five years of underdeveloped and developed regions of the world. There were two independent samples of ten countries from each of the groups drawn at the same time, and the yearly mortality rates of children under the age of five years (per 100,000) inhabitants were reported (MRate1 and MRate2).

Table 2: Mortality Rates of Children

Country	MRate1	MRate2
1	120	11
2	110	9
3	105	13
4	61	11
5	45	14
6	114	11
7	118	10
8	138	8
9	85	6
10	70	6

 

Using the Minitab statistical analysis program to enter the data and perform the analysis, complete the following:

Run the Wilcoxon rank-sum test to show whether there is a statistically significant difference between the mortality rates of children under the age of five years of the regions. Results may be used in making decisions regarding which region needs to receive help to improve the public health issues of morality.

Obtain the difference in the mortality rates and whether there is a statistically significant difference.

In addition, in a Microsoft Word document, provide a written interpretation of your results in APA format.

 

PHE5020 Biostatistical Methods

Week 3 Project  

Week 3: Project Assignment

Statistics for Categorical Data: Odds Ratios and Chi-Square

This assignment focuses on categorical data. Two of the statistics most often used to test hypotheses about categorical data are odds ratios (ORs) and the chi-square. The disease-OR refers to the odds in favor of disease in the exposed group divided by the odds in favor of the unexposed group. Chi-square statistics measure the difference between the observed counts and the corresponding expected counts. The expected counts are hypothetical counts that would occur if the null hypothesis were true.

Part 1: ORs

A study conducted by López-Carnllo, Avila, and Dubrow (1994) investigated health hazards associated with the consumption of food local to a particular geographic area, in this case chili peppers particular to Mexico. It was a population-based case-control study in Mexico City on the relationship between chili pepper consumption and gastric cancer risk. Subjects for the study consisted of 213 incident cases and 697 controls randomly selected from the general population. Interviews produced the following information regarding chili consumption:

Table 1: Chili Pepper Consumption and Gastric Cancer Risk

Chili pepper consumption	Case of gastric cancer	Controls
Yes	A = 204	B = 552
No	C = 9	D = 145

 

Reference:

López-Carnllo, L., Avila, M. H., & Dubrow, R. (1994). Chili pepper consumption and gastric cancer in Mexico: A case-control study. American Journal of Epidemiology, 139(3), 263–271.

Note: You do not need to use the Minitab software to complete this assignment.

In a Microsoft Excel worksheet, calculate the odds of having gastric cancer.

In addition, provide a written interpretation of your results in APA format.

Refer to the Assignment Resources: Odds Ratio to view an example of odds ratio. The same resource is also available under lecture Testing Hypotheses.

Part 2: Chi-Square

Bain, Willett, Hennekens, Rosner, Belanger, and Speizer (1981) conducted a study of the association between current postmenopausal hormone use and risk of nonfatal myocardial infarction (MI), in which 88 women reporting a diagnosis of MI and 1,873 healthy control subjects were identified from a large population of married female registered nurses a