WK 1 -8 NOTES

Topic 1 DQ 1 (Need 1 sentence and a reference)

Statistics can be a foreign topic to many people and/or cause anxiety. This checklist may help you succeed.

· Schedule 20-25 hours a week for studying and completing assignments

· Review the specific terms for each topic on the Statistics Visual Learner website

· Read the assigned chapters from the textbook and complete the Progress Checks as you are reading for practice

· Use the Electronic Resources for extra assistance (Khan videos, SPSS tutorials, SAGE resources, etc.)

· Complete the assignment(s) for each topic

Having reviewed this checklist, what challenges might you face? What steps can you take to succeed in the class? Review the levels of measurement terms in the Statistics Visual Learner media piece. Compare and contrast Stevens's four scales of measurement and explain when each type of scale should be used.

Measurement Levels

The nominal scale, ordinal scale, interval scale, and ratio scale are the four different levels of measurement. The article on the levels of measurement was published in 1946 by Stanley Stevens of Harvard University. Let's look at the four measurement levels that are listed below:

Nominal scale: A scale is referred to be a nominal scale if its name or label defines it. For instance, the individual's gender, ethnicity, political affiliation, etc.

Ordinal scale: This scale is referred to as an ordinal scale if it contains different orders or if each value on the scale corresponds to a quantity that is characterized by a rating. For instance, quality ratings like very good, good, fair, poor, extremely poor, etc.

Interval scale: For this type of scale, the measurement's precise quantity of the characteristic under consideration is represented by the scale. Consider temperature.

Ratio scale: We use the ratio scale of measurements to describe quantities in accurate form, such as exam marks, a person's age, etc.

Topic 1 DQ 2 (Need 1 sentence and a reference)

The professor teaching a large introductory class gives a final exam that has alternate forms, A, B, and C. A student taking the exam using Form B is upset because she claims that Form B is much harder than Forms A and C. Discuss how percentile point data might be useful to determine if the student is correct.

Based on the marks received out of a possible 100, the percentile is calculated. A student receives 25 out of 50 points. His percentile is then 50%.

In this instance, the scholar believes that question set B is more difficult than question sets A and B. If the teachers decide it is correct, they must determine how many marks meet the same criterion. For instance, all question sets have a maximum score of 90, but question set B has an equivalent well-known score of 70. If a student scores forty-five on test items from sets A and C, their percentile is 50%. If a student from question set B receives a score of 35, his percentile would also be 50%.

Topic 2 DQ 1 (Need 1 sentence and a reference)

The process of random sampling guarantees that the sample selected will be representative of the population. Why is this statement not true? What other factors and variables influence the outcomes of studies?

The claim that "the process of random sampling guarantees that the sample selected will be representative of the population" is not totally accurate. Although random sampling can raise the possibility of getting a representative sample, it cannot ensure it. The results of research can be influenced by a number of variables and conditions.

Explanation: including:

Sample size: A sample is more likely to be representative of the population if it is larger.

bias in sampling Even with random sampling, the results may still be biased if some demographic segments are over- or underrepresented in the sample.

Non-response bias: If a portion of the sample declines to participate or cannot be contacted, this may skew the findings.

Measurement bias: The manner in which data is gathered or assessed may have an impact on the outcomes. For instance, if a survey question is framed in a perplexing or deceptive manner, it could result in unreliable answers.

Confounding factors: The results of the study may be affected by other factors that are not being examined or taken into account. For instance, other factors like food or exercise may potentially be influencing the conclusion of a study that examines the impact of a medicine on a specific health outcome.

Topic 2 DQ 2 (Need 1 sentence and a reference)

Review the video on Normal Distribution in the Calculations section of the "Statistics Visual Learner" media piece. Bob compares his SAT Verbal score of 400 to Marge's ACT Verbal score of 20. "I beat you," he exclaims. "My score is 20 times your score!" Although his multiplication is good, his logic is faulty. Explain why.

This assertion is untrue. This assertion is false for a variety of reasons. which could include some of the following details:

The measurement standards differ. The SAT verbal score and the ACT verbal score are the two tests. Both have different scoring criteria.

Both exams have different measurement ranges.

Both the mean and standard deviation of the two populations are different, as are the results of the two tests.

The range of SAT scores is 200 to 800, with 800 being the highest. Bob achieved a score of 400. ACT scores range from 1 to 36, with 36 being the highest possible score. This suggests Marge did better than the norm.

Thus, Bob's reasoning is flawed.

Topic 3 DQ 1 (Need 1 sentence and a reference)

Review the video "Linear Correlation" in the Calculations section of the "Statistics Visual Learner" media piece. It is sometimes said that the higher the correlation between two variables, the more likely the relationship is causal. Do you think this is correct? Discuss.

Understanding the causal connection between the independent and dependent variables is referred to as correlation. High correlation does not always imply a causal connection between the two variables. Although a high correlation between two variables might suggest a causal connection, we cannot assume this. Other elements, such as environmental variables or other alterations, should be taken into account. Therefore, the aforementioned claim is untrue.

Topic 3 DQ 2 (Need 1 sentence and a reference)

Discuss the strengths and weaknesses of correlational and regression studies; discuss concepts such as positive and negative correlations, correlation coefficients, confounding variables, and causality.

Advantages and disadvantages of correlation studies:

Correlation strength:

Correlations are a quick and simple approach to determine whether two variables are related to one another.

A correlation coefficient is a straightforward and objective metric for expressing how strongly two variables are related.

Limitations of correlation:

Every correlation demonstrates a connection between two variables or the lack thereof.

If there is no correlation, there may still be a relationship; it could even be nonlinear.

Associations, both favorable and adverse:

There are both positive and negative correlations.

A relationship in which two variables' values rise or fall together is referred to as positive correlation.

When there is a negative correlation between two variables, it means that one of the variables is rising while the other is falling.

Correlation indices:

A correlation coefficient measures how strong a correlation is. The range of coefficients is from -1.0 to +1.0, where a coefficient less than 0 indicates a negative correlation and a coefficient greater than 0 indicates a positive correlation.

Topic 4 DQ 1 (Need 1 sentence and a reference)

Explain Type I error and give an example. Explain Type II error and give an example. What is the best way to reduce both kinds of error? Find a current scenario that has a Type I error and a Type II error. Is this scenario an example of an inverse relationship? Why or Why not?

A type I error occurs when a null hypothesis that is actually true is mistakenly rejected during statistical hypothesis testing. The level of significance is the likelihood that a type I error will occur.

Based on a few mild symptoms, we decided to get tested for dengue.

The Type I mistake then claims that we have dengue, but we don't.

A type II error occurs when a null hypothesis that is genuinely true is not rejected during statistical hypothesis testing (type I error). The beta represents the likelihood of making a type II error.

As in the case of the referenced above. The test results indicate that we do not have dengue, yet we do.

Methods for lowering type I and type II errors include:

By selecting a lower threshold of significance before to conducting a test (requiring a lower p-value for rejecting), the likelihood of a type 1 mistake (rejecting a valid null hypothesis) can be reduced.

Once the level of significance has been determined, it is possible to reduce the likelihood of a type 2 error (failing to reject a false null hypothesis) by either selecting a larger sample size or by selecting an alternative "threshold" value for the relevant parameter that is farther away from the null value. When calculating the probability of a type 2 error, you assume this threshold alternative value for the parameter.

Topic 4 DQ 2 (Need 1 sentence and a reference)

Review the term Significance Test in the "Statistics Visual Learner" media piece. When a newspaper or magazine article reports the results of a study and draws a conclusion without also reporting whether the results are statistically significant, what are the possible reasons for doing so? How seriously should you take the conclusion offered in such a study? Discuss.

A statistical test called a significance test is used to examine if a study's findings are more likely to be the result of chance or to actually reflect a difference or relationship. The term "significant" in statistics denotes that the outcomes are not likely to have occurred by chance.

There are a number of reasons why a newspaper or magazine article can disclose study results without mentioning whether they are statistically significant:

Lack of knowledge: The author might not be aware of the significance of reporting statistical significance or the notion behind it.

Due to space restrictions, the author might have to exclude some information, such as statistical significance, in order to adequately report the results.

Bias: The author could have a bias and only present findings that concur with their viewpoint, regardless of whether or not those findings are statistically significant.

When analyzing the findings of a study that does not state statistical significance, it is crucial to use caution. The stated conclusion might not be supported by the evidence and might even be false. It is usually preferable to look for studies that have undergone peer review and that present statistically significant findings in order to make educated decisions.

Topic 5 DQ 1 (Need 1 sentence and a reference)

What are the strengths and weaknesses of using a  t-test? Give a real-world example to support your answer.

A T-Test is a tool for hypothesis testing that is used to examine a population's supposition. It is a type of inferential insight used to determine the significant contrast between two groups' approaches with similar highlights.

The instances are examined based on their methodologies and are quite straightforward illustrations of free gatherings.

Pros

1. Fundamental for speculating: The results of the t-test are useful for determining whether, in the event that they are accurate, they may be applied to the entire population.

2. really easy to understand: The yield of free examples is really easy to understand. The yield shows you how significantly different one example's mean is from another group's mean. Additionally, it shows each group's mean as well as the typical gap between groups. A higher t-score indicates that the groups are exceptional, whereas a lower t-score indicates that the groups are comparable.

3. Strength: It anticipates that the free examples of two populations would often be communicated and will have a comparable difference. Since there are two examples from a population that have inconsistent differences, the t-test is actually favorable to the violation of the primary assumption.

4. Easy to get data: only a few people are needed for autonomous t-test experiments. There is only one needed value from each subject;

It needs participants from the two example bunches to perform better on a quantitative variable.

5. Determine the information's source: Using the T-test, we may examine the typical results of two informative index tests and determine whether the example individuals are representative of the general population.

6. Plain language

The t-test equation for unrestricted cases is simple. Because of this, understanding what is happening doesn't require a lot of factual planning.

7. Efficient: Information can be easily deduced from two examples using a PC's guidance. Calculating t-test results can be done using common programming tools like Microsoft Excel, which aid in measurable capabilities.

8. Saves time: Since only a small sample size is needed for computation, it saves both money and the time required to acquire and analyze a large amount of data.

9. Individual contrast control: T-test repeated measure design has little impact because the amount of error from tests is negligible. Additionally, it encourages excellent control of individual contrasts. There is only one group available for testing, which may result in less information commotion.

10. Provide crucial information: The test provides all the information you need to consider the population.

Cons

1. Difficult to get subjects: Finding the subjects for the example data is expensive and difficult in the examination cycle.

2. Persist impacts: When using matched example t-tests, problems with rehashed gauges rather than contrasts between bunch plans lead to persist impacts.

3. Limited amount of clamor: Although you probably won't worry about specific differences between the informational indexes of the gatherings, there is still a distinct difference between the gatherings and only one out of every odd example will respond in a similar manner, leading to a limited amount of clamor.

4. Natural effect: Independent t-test can help you distinguish between test groups, but it can't help you manage the effects of the weather. The output of a t-test may be affected by climate changes.

5. Different correlations: Because the T-test results in type I errors, it cannot be used for many tests. It will be challenging to rule out the flawed idea while doing a matched t-test among a collection of tests.

6. A decrease in opportunity levels: As the df of a group test decreases, you need a larger t-esteem to calculate the t-test importance, which creates a more pronounced trade-off between the more significant influence and reduced opportunity levels.

7. Consistent quality of information: The yield becomes temperamental if the information acquired violates the t-test's premise.

For instance

Let's say you try a naturopathic remedy for a cold. Virus two to three days. The next time you have a cold, you buy an over-the-counter medication, and the virus lasts for seven days. When you observe your friends, they all tell you that their colds had a shorter duration (typically 3 days) when they took the homeopathic remedy. Is there a chance that similar results will occur again? By comparing the two groups' techniques, a t test can help you make decisions by estimating the possibility that certain outcomes will occur by accident.

Knowing more about the general populace will be useful for conducting this in the best possible method. The interpretation makes perfect sense. For example, if the t-score is smaller, the groups will be similar, and if it is larger, the groups will be distinct. This is demonstrated by the example provided in relation to homeopathic treatment and over-the-counter medications. Additionally, a small percentage of people need to be informed about this medication's efficacy, so doing this takes less time.

However, there will be differences between people in the two groups, making it difficult to determine whether a medicine is effective since it will vary from person to person. There will be environmental variations as well as the effectiveness. Problems may arise when the samples come from various environments.

Topic 5 DQ 2 (125 words and 1 reference)

Discuss how the  t-test for correlated groups and the  t-test for single samples are alike and different. Give a current example to support your answer.

Topic 6 DQ 1 (Need 1 sentence and a reference)

Review the four "ANOVA" videos in the Calculations section of the "Statistics Visual Learner" media piece.

Explain why factorial designs with two or more independent variables (or factors) can induce errors when interpreting data. Give an example.

When an experiment has three or more conditions, the ANOVA hypothesis test is applied. It is preferable to employing multiple t tests since the likelihood of a type I error increases with the number of tests run. If there is a significant difference, ANOVA can identify it, but it cannot pinpoint the location of the difference (GCU, 2016). When there is only one factor of interest, the one-way ANOVA is used to compare three or more populations. An one-way ANOVA must meet five criteria: the populations must have distributions that are roughly normal, share the same variance, be composed of random samples of quantitative data, be independent of one another, and come from populations that can be classified in only one way.

When two independent factors interact to affect the values of the dependent variable, it is known as a two-way ANOVA. Six conditions must be met for a two-way ANOVA: The sample values for each cell are drawn from populations with normal distributions, populations with similar variances, simple random samples, independent samples, samples categorized in two ways, and cells with an equal number of sample values (Statistics Visual Learner, n.d.).

It might be challenging to evaluate the interactions between the independent variables in factorial designs with two or more independent variables because they are complex. Additionally, as I mentioned previously in my piece, ANOVA can identify differences but not their locations. This becomes more difficult to comprehend as there are more independent components.

GCU, (n.d.).Statistical Visual Learner.GCU. Retrieved from http://lc.gcumedia.com/hlt362v/the-visual-learner/assets/anova.pdf

Grand Canyon University.(2016). Lecture 6 [PDF document]. Retrieved from https://lc-grad3.gcu.edu/learningPlatform/content/content.html?operation=viewContent&contentId=8955fe9d-

Topic 6 DQ 2 (Need 1 sentence and a reference)

Explain how the ANOVA impacts a Type I error. How might a Type I error change when comparing groups two at a time using the  t-test for independent groups?

A Type I error is a false positive, therefore keep in mind that the likelihood of making one is equal to our significance level,. This is accurate if we are only performing a single analysis on a single dataset (such as a t-test with just two groups). The likelihood that we are taking advantage of random chance and rejecting a null hypothesis when we shouldn't rises as we begin performing several analyses on the same dataset. This problem is avoided and our error rate is maintained at the level we selected thanks to ANOVA, which compares all groups simultaneously with a single analysis.

There is a probability that you will create a Type I error with every t-test you run. Typically, this inaccuracy is 5%. Your likelihood of "making a mistake" will have climbed to 10% if you conduct two t-tests on the same data. It takes more than multiplying 5% by the number of tests to calculate the new error rate for multiple t-tests. However, the outcomes are remarkably comparable if you merely perform a few multiple comparisons. This means that three t-tests would result in 15% (in actuality, 14.3%), and so on. These mistakes must be corrected. To ensure that the Type I error stays at 5% and that any statistically significant results you get are not the consequence of simply conducting several tests, an ANOVA accounts for these errors.

Topic 7 DQ 1 (Make sure there are references)

Review the three "Non Parametric" test videos in the Calculations section of the "Statistics Visual Learner" media piece.

How would you create a statistical analysis based on the scenario below? Explain. What level of significance would you test at and why?

A researcher is examining preferences among four new flavors of ice cream. A sample of  n = 80 people is obtained. Each person tastes all four flavors and then picks a favorite. The distribution of preferences is as follows. Do these data indicate any significance preferences among the four flavors using the chi-square test?

Ice Cream Flavor
A	B	C	D
12	18	28	22

Topic 7 DQ 2 (make sure there are references)

Describe the differences between parametric and nonparametric tests. Which are more powerful and why? Give an example of a situation where you would select a parametric and a nonparametric test.

Topic 8 DQ 1 (Need 1 sentence and a reference)

To determine whether a new sleeping pill has an affect that varies with dosage, a researcher randomly assigns adult insomniacs, in equal numbers, to receive either 4 or 8 grams of the sleeping pill. The amount of sleeping time is measured for each subject during an 8-hour period after the administration of the dosage. What type of design is this, and what type of statistic is needed to analyze the data (consider ABAB studies)?

01 :

Each group, in my opinion, exists independently. I think we may compare population means between the two groups by using a 2-way ANOVA since they are both receiving the same medication (but at different dosages). The f-test of the ANOVA can be used to examine the data gathered. Perhaps we could compare the means of the two groups using a t-statistic in order to "simply" (I use this word lightly) find variations in the medication's effects.

02 :

In this case, the independent variable is either a fresh sleeping tablet weighing 4 grams (treatment 1) or 8 grams (treatment 2) (nominal data; both sleeping pills). The samples include adult patients with insomnia who were given equal quantities, however we are unsure of the exact amount. The amount of sleep (nominal data; sleep and do not sleep) that must be measured by researchers after the sample groups took this medication for 8 hours is the dependent variable. Therefore, I believe I will choose to employ the two-variable (X2) test.

The hypothesis that holds true is H0: There is no connection between taking new medication at bedtime and sleeping.

H0 is false, hence H1 is the alternative.

8 hours after taking the medication, go to bed.fresh sleeping pills 4 g. (n1) New sedatives (n2)sleepABnot sleepCD. 8 g

Response 3: The two distinct dosages that are being provided are the two independent variables in this study. A two-way ANOVA test is required because there are two different independent variables in this situation. To examine the statistical significance of the test results, you would need to utilize an f-statistic. The means of the test results must be compared in order to evaluate whether there is a significant difference between taking a smaller dose and a greater dose. To do this, use a two-way ANOVA test.

Topic 8 DQ 2 (make sure there are references)

Dr. Bill Board designs a 2 X 2 between-subjects factorial design, where Factor A is word frequency (low or high) and Factor B is category cues (no cues or cues). Assume that the data are interval. What type of statistic is needed to analyze the data?