Posted: September 7th, 2022

Teaching English Through Poetry

Name:
Institution:
Course:
Date:
Teaching English Through Poetry
Regression analysis is a statistical technique that tries to model and explore the correlation between many variables. It is a set of statistical procedures for assessing the interrelation between outcome variables (dependent variables) and one or more predictors (covariates or independent variables) (Zhao & Liu, 295). Regression analysis is usually employed for two distinct theoretical reasons. First, the technique is broadly used for forecasting and predicting, in which its use has a considerable connection with artificial intelligence tools such as machine learning. Second, the technique is used to understand casual interrelations between the dependent and independent variables. Considerably, regression analysis by itself discloses the correlation between an outcome variable and a set of predictors in a fixed set of data. To use regression analysis to infer casual relationships or to predict outcomes, respectively, an investigator should justify why a correlation between two variables has an informal interpretation or why the available interrelation has high predictive power for a new situation.
The earliest regression forms were published by Legendre and Gauss in the years 1805 and 1809, respectively. The earliest regression form was considered as the method of least squares. Both Gauss and Legendre applied the regression technique to the problem of verifying, from observation of astronomies, the orbits of bodies around the sun. In the 19th century, the term regression was devised by Francis Galton to explain a biological occurrence (Gunst & Mason, 50). The occurrence was referred to as the regression towards the mean, and it stated that the heights of all the offspring of a tall ancestor will always regress towards a typical average.
As discussed, regression analysis is an inference test exploring the correlation between outcome and predictor variables. The method was chosen for this study because there are several variables to be tested. The independent variable is the age of students, resources used, and the teaching technique used, whereas the dependent variable affects students’ learning.
On the other hand, hypothesis testing is a statistical technique where the researcher examines the assumptions regarding a population parameter. The methods used by the researcher are highly dependent on the reason for the analysis and the nature of the data used (Tartakovsky et al., 80). The hypothesis testing technique is always used to examine the credibility of a hypothesis using sample data. Data used to test hypotheses always come from a data generation process or a larger population. The technique involves either rejection or acceptance of a null hypothesis.
John Arbuthnot first used the hypothesis testing technique in 1710 in examining the human sex ratio at birth. Pierre Simon Laplace was the second researcher to employ the hypothesis testing technique in 1770. Even though the early forms of hypothesis testing were used in 1700, it was highly popularized in the beginning and mid-20th century (Tartakovsky et al., 86). The modern hypothesis testing is primarily the work of three individuals Karl Pearson, William Sealy Gosset, and Ronald Fisher. Karl Pearson coined Pearson’s chi-squared test and p-value. William coined Student’s t-distribution, and Fisher invented analysis of variance, null hypothesis, and significance test.
The hypothesis testing technique was employed in this study because there were several hypotheses derived from the topic. Therefore, the technique was essential in rejecting or accepting the derived hypotheses. The technique will involve rejection or acceptance of the null or alternative hypothesis and vice versa at a selected statistical significance level. For example, the null (H0) hypothesis considered in this study, Teaching the English language through poetry does not significantly influence the English proficiency of students (p>0.05). Whereas the alternative hypothesis (H1) was that Teaching the English language through poetry significantly influences the English proficiency of students (p<0.05).
Participants
Sample size dramatically affects the outcome of the research. A smaller sample size (98 respondents) was chosen to reduce time wastage during the analysis process. The smaller number of samples was efficient because it minimized time wastage in data analysis (Fugard & Potts, 670). Also, data generated in smaller sample sizes are always reliable and efficient for the analysis. The sample size for the study was efficient and reliable. It was not too small or too big. Sample sizes for researches should neither be too small or too big because they both have disadvantages for the study and compromise the results and conclusions for the study (Faber & Fonseca, 207). Too large samples can intensify the detection difference, stressing differences that are not statistically relevant for the study. Similarly, too small samples may avert the findings from being inferred. Therefore, a medium sample size was chosen for this study to enhance the relevance and reliability of the findings. Also, the sample size helped in minimizing time wastage during the study.
A significant number of participants were from the age bracket of 26 and 28. These are adults who understand their rights and what is good for them. Therefore, they will read the consent personally choose to be part of the study (Pandis et al., 8). Similarly, the study targeted this age because they understand poetry and have experience in education and arts. Therefore, they will be better positioned to understand how the use of poetry affects the understanding of individuals. Thus, the age bracket was selected mainly due to their experience, thus providing relevant data for the study. Finally, the age bracket was also a perfect way of strategically recruiting participants for the study.

Works cited
Faber, Jorge, and Lilian Martins Fonseca. “How sample size influences research outcomes.” Dental press journal of orthodontics 19.4 (2014): 27-29.
Fugard, Andrew JB, and Henry WW Potts. “Supporting thinking on sample sizes for thematic analyses: a quantitative tool.” International Journal of Social Research Methodology 18.6 (2015): 669-684.
Gunst, Richard F., and Robert L. Mason. Regression analysis and its application: a data-oriented approach. CRC Press, 2018.
Pandis, Nikolaos, Argy Polychronopoulou, and Theodore Eliades. “Sample size estimation: an overview with applications to orthodontic clinical trial designs.” American journal of orthodontics and dentofacial orthopedics 140.4 (2011): e141-e146.
Tartakovsky, Alexander, Igor Nikiforov, and Michele Basseville. Sequential analysis: Hypothesis testing and changepoint detection. CRC Press, 2014.
Zhao, Jing, and Xiaojuan Liu. “A hybrid method of dynamic cooling and heating load forecasting for office buildings based on artificial intelligence and regression analysis.” Energy and Buildings 174 (2018): 293-308.

Check Price Discount

Study Notes & Homework Samples: Next Post »Social Work and Policy