In this case, it was established that there was a conflicting conclusionarrived by two major polls. The major explanation can be on the wording used on questions to collect the relevant data. The AP-GfK poll provided respondents with three options support, oppose and neither support nor oppose. The other poll provided respondents with only two option, oppose and support. This usually gives different data hence findings. More importantly, the timing is another significant factor. Polls conducted before a law is debated and passed will be much different from poll results obtained after a law has been debated, passed by the congress and signed into law.(a) Correlation is always carried out to establish a number of factors. Ideally, helps researchers find out if there is a linear relationship between variables, the strength of the relationship and the direction of the association between the variables. Out of the tree scatter lot, I will be concerned with Correlation between taste and acetic. This is because the correlation coefficient is less than 0.7 hence a weak correlation which does not warrant further analysis.(b) When conducting regression analysis, it is always important to find out the strength or how best the equation to be developed from regression analysis best describes the relationship between the dependent and independent variables being considered. In order to do this, the adjusted R square is interpreted. From the summery output table, it is evident that the value of the adjusted R square was 0. This can be interpreted to mean that 61.16% of the variation in the dependent variable can be successfully explained by the linear model developed. Ideally, this means that there are other variables which contribute significantly to taste score, which are not included in the model. Having in mind that the R square adjusted is slightly over 60.0%, the equation is suitable to be used in predicting taste score using the existing independent variables.(c) In regression, some variables contribute significantly to changes in the dependent variable. From the coefficient table the standardized regression coefficient is helpful in helping scholars assess the relative importance of the predictors (Doane and Seward 233). Ideally, those variables or partial regression coefficient that differs significantly from zero are deemed to be significant contributors to changes in the dependent variable. In this case,
Doane, David and Seward, Lori. Applied Statistics in Business and Economics. New York: McGraw-Hill Publishing, 2013. Print.
Please type your essay title, choose your document type, enter your email and we send you essay samples