Please Reply To The Following 2 Discussion Posts:

Please Reply to the following 2 Discussion posts:

 

Requirement

 

APA format with intext citation

Word count minimum of 150 words per post

References at least one high-level scholarly reference per post within the last 5 years in APA format.

Plagiarism free.

Turnitin receipt.

 

DISCUSSION POST # 1 Elaine

 

Research studies can be challenging and time-consuming, and one of the most complex elements in the process is determining how to analyze the data. Choosing the right statistical method is essential and the first step to data analysis. According to McKechnie & Fisher (2019) particular aspects of the research study including the research design, hypothesis, and data collected need to be considered when choosing a statistical method. The researcher needs to consider the data collected, the categories, scales, variables, and their relationships (McKechnie & Fisher, 2019).

There are many statistical tests used in nursing research including the Pearson’s Chi-squared test, Student’s t-test, Analysis of Variance (ANOVA), and Analysis of Covariance (ANCOVA) to name a few. One statistical analysis method commonly used in nursing research is the Pearson’s chi-squared test. The chi-squared test is utilized to test assumptions concerning proportional differences in categorical variables (Polit & Beck, 2018). These tests require nominal or dichotomous levels of measurement (McKechnie & Fisher, 2019). For example, let’s say we do a study to test whether a hypertensive medication helps patients with high blood pressure. In this study, we will have two groups, the patients who do not get the medication (control), and the patients who do get the medication (experimental). The data will be categorized into a crosstab and be generalized, positive effect (helps to lower BP) or null effect (no change in blood pressure). The data evaluation in this scenario will not look at specific blood pressure numbers or ranges but instead the overall positive or neutral effect of the medication. If the research study required further evaluation of the extent of positive or negative effects of the medication in numerical value, another statistical method would need to be used. Therefore, knowing what type of data you have and how you want to evaluate it is important when determining what statistical method to use.

 

DISCUSSION POST # 2 Gema

 

There are many statistical tests used in nursing, ranging from Pearson correlation, Chi-square, Paired T-test, ANOVA, Independent T-test, and the list goes on. When deciding on what statistical test to use in nursing research one must determine the research design is used, the distribution of data, and the type of variable in question. For example, Inferential statistics allows one to make predictions based on a sample and apply it to a population. In other words, you can make a population generalization based on data sample outcomes. “Inferential statistics can help researchers draw conclusions from a sample to a population” (Gueterman, 2019). Inferential statistics is a broad category of describing data. T-test and ANOVA, along with Analysis of variant, Correlation and Regression they fall under the broad category of Inferential statistics.

The type of statistical test that I would use, given the following research study:

The effectiveness of implementing the [Geriatric Depression Scale or standardized assessment instrument] for the treatment and management of [depression or disease] in primary care- would be a Correlation Statistical test to examine whether there is a relationship between two or more variables; the implementation of the GDS (Geriatric Depression Screening) scale, the elderly population and its correlation to treatment and management of the disease: depression. However, I can easily use the T-test as well to determine if the process of implementing GDS has an effect on the treatment and management of the geriatric population. Both options are suitable; nonetheless, analysis of these groups will result in an association or difference between variables.