Responses need
bredaw
MAT540Week4Discussion12ResponsesNeededStatisticalTesting.docx|
Discussion 1 Statistical Testing [WLOs: 1, 2] [CLOs: 2, 4, 5] |
There are strengths and weaknesses associated with statistical testing. For this discussion, begin by reviewing the various methods of statistical testing presented in your textbook (i.e., t-tests, ANOVA, chi-square, and f-tests).
Guided Response: Review the posts from your classmates, and respond to at least two, comparing reviews of statistical testing.
Respond to Crystal Carter post
The sensical thing about testing is giving the data validity. I believe this to be the importance of statistical testing, hypothetical testing, and other research testing. Being able to test the probability of different variations, using the F test and/or ANOVA test, is important to research because it ultimately helps to get to a finding or result. Completing one test gives you the results of that specific test, using those specific variables. I believe that being able to conduct probability tests can broaden the finding when it comes to research purposes. With ANOVA testing allowing the ability to test the equality of several different means, my thought would be that researchers can accelerate their findings and be more efficient in getting results.
The quote that most resonated with me this week was “Trying to analyze a situation without enough data was like looking at a photograph of a ball in flight and trying to gauge its direction. Is it going up, down, sideways? Is it about to collide with a baseball bat? Is it moving at all, or is something on the blind side holding it in place? A single frame didn’t mean a thing. Patterns were based on data. With enough datapoints, you could predict just about anything.” (Sakey, 2013). This made the most sense to me because there are often times, I’m looking at numbers/data and wondering where this or that came from. Too little data can leave gaps, leaving the reader to make their own assumptions and fill it in. Appropriate statistical testing should produce enough data to make the study understandable.
Respond to Nicole Smith post
T-tests are used to see if there is a difference between the mean of two groups but require the data set from each group, the standard deviation and the number of values. ANOVA is generally used when you need to test 3 or more population means are equal. Chi-squared looks at the differences between the expected and the observed variables. The quote that was listed by Akutra-Ramses Atenosis Cea stood out the most to me. If you do look ahead there is a higher percentage that you will be able to gain rather then loose that market ground. Testing is very important in research. For example, starting up a business requires a lot of testing and analysis especially when it comes to finding the proper location. To far away from your target market, they would not come, to close, it may drive other potential markets away depending on the demographics of such area where you have set up shop. Areas in town may have a stigma attached to them. It could potentially deter newer customers away from other markets.
Lind, D. A. (2019). Statistical Techniques in Business and Economics (17th Edition). Retrieved from Connect MH Education: http://connect.mheducation.com/class/
Respond to Roland Manayon post
Statistical Testing
As Jennifer K. McArthur (1993) puts it, “No data are excluded on subjective or arbitrary grounds. No one piece of data is more highly valued than another. The consequences of this policy have to be accepted, even if they prove awkward”. This quote highlights the importance of every piece of data in statistics. Biases against or for anything should have no room to keep the integrity of data and the outcome of the research. A researcher must be objective and not selective or subjective of data to be analyzed.
Statistcial testing is important in research because in statistics there is no 100% accuracy of results, that is why data sets need to be tested methodically. That is why standard deviation is such an important measurement in statistics. Lind, Marchal, and Wathen (2017) discussed some of the most commonly used testing methods such as T-Test, ANOVA, Chi-Square, and F-Test, among others. Every testing method is used for different purposes and on different data sets, for instance, T-Test is used for means testing – to determine the difference between the means using one independent variable and another dependent variable. ANOVA or Analysis of Variance technique, is used when there are three or more population means to be tested. Using ANOVA, these three assumptions must be true regarding the population: 1) follow normal distribution, 2) have equal standard deviation, and 3) are independent (Lind, Marhcal, & Wathen, 2017, Ch. 12, Pg. 392).
References
Lind, D. A., Marchal, W. G., & Wathen, S. A. (2017). Statistical techniques in business and economics. (17th ed.). Retrieved from http://connect.mheducation.com/class/
|
Discussion 2 Examples of Standardized Tests in Research [WLOs: 1, 2] [CLOs: 2, 4, 5] |
Locate an example of a research study that uses statistical tests. List the statistical tests that are used, and explain what each one allows the researchers to accomplish and/or conclude in the study.
Guided Response: Review the posts from your classmates, and respond to at least two. In each response, compare how statistical tests were used in the research studies you and your classmate provided, noting the strengths and weaknesses of each example.
Respond to Yasmin El Sherif post
Worldwide, there are about one million suicides annually. In the United States (USA) approximately 750,000 people died by suicide over the last 25 years. Suicides outnumber homicides by at least a 3:2 ratio in the USA. Deaths from suicide exceeded deaths from AIDS by 200000 in the past 20 years. Four times as many Americans died by suicide during the Vietnam War than from wartime fatalities. (Links to an external site.)Links to an external site.
From a statistical perspective, the analysis of suicide and related events are among the most challenging and interesting drug safety problems. There is no other area where the indication for treatment is so strongly confounded with the adverse event of interest. Even in well-controlled observational studies, selection effects can lead to severely biased results. Since suicide events are rare, RCTs in and of themselves generally have sample sizes that are too small to draw valid inferences. Furthermore, patients enrolled in RCTs may have little resemblance to those patients who are the ultimate consumers of the medications of interest. In the following, I provide a brief overview of several areas of promising statistical research.
While meta-analysis combines effect sizes such as standardized mean differences or odds ratios, ‘research synthesis’ provides a re-analysis of the complete set of person-level longitudinal data from each study.
Wang, W. (2016). Statistical methods for drug safety , by Robert D. Gibbons and Anup K. Amatya. Journal of Biopharmaceutical Statistics, 26(5), 1003–1004. https://doi-org.proxy-library.ashford.edu/10.1080/10543406.2016.1208521
Respond to Marilyn Owens-Keyes post
Example of Standardized Test in Research
The study I chose to discuss is on long-term weight-loss and maintenance. The study was performed to examine the long-term weight-loss of individuals who are completing a structured weight-loss program over a 5-year span. The statistical test used in this study was the analysis of variance (ANOVA), a research tool used to test the difference between group means after any other variance in the outcome variable is accounted for.
The research design required studies to be performed in the United States, participants must be in a structured weight-loss program and provided follow-up data with variance estimates for two years or more. The analysis included the use of the fixed effects model assumptions of estimated of diet, sex, and follow-up at each year; evaluation of homogeneity across studies; and 95% CIs calculated.
The study confirmed that exercise is an important key in weight-loss maintenance. Predictors for long-term weight-loss maintenance was not identified because of insufficiency of long-term data. Data was provided from observations for the need to develop more hypothesis. Observations showed no significant difference in maintenance or reduction between men and women and the power of the analysis was not enough to detect differences between groups.
Respond to Reginald Whimbush post
The research study was conducted by Makabe and his team (2014) to try find out the impact of work-life balance on well-being and job satisfaction among nurses in Japan. A cross-sectional survey was done on 1,202 nurses from three Japanese hospitals. The participants were divided into four groups based on their actual WLB proportion and desired WLB; Group A (50/50), Group B (60/40), Group C (70/30) and Group D (80/20) (Makabe et al, 2015). Questionnaires were distributed to collect demographic data as well as data on the nurses’ balance between private life and actual proportion of work.
An Analysis of Variance (ANOVA) was used on testing data regarding age, hours of work, nursing experience and annual leave acquisition rate (Makabe et al, 2015). The analysis of covariance (ANCOVA) was also used to test for all satisfactions, stress-coping ability and Quality of Life among the four groups. Covariates selected for the ANCOVA were hours of work, job title, childcare role and unit type. The research findings from the ANCOVA indicate nurses in Groups C and D were unsatisfied with the quality of life and job satisfaction. Poor quality of life and lower job satisfaction could result to resignation (Makabe et al, 2015).
References
Makabe, S., Takagai, J., Asanuma, Y., Ohtuma, K., & Kimura, Y. (2015). Impact of work-life imbalance on job satisfaction and quality of life among hospital nurses in Japan. Industrial Health, 53(2): 152–159.
