Sample Problem Statement:
- A research paper claims a meaningful contribution to the literature based on finding statistically significant relationships between predictor and response variables. In the footnotes, you see the following statement, “given this research was exploratory in nature, traditional levels of significance to reject the null hypotheses were relaxed to the .10 level.” Post your response to the scenario in which you critically evaluate this footnote. As a reader/reviewer, what response would you provide to the authors about this footnote?
Response to the Problem Statement:
The footnotes mentioned an important traditional levels of significance that were relaxed to 0.01 level. Therefore, we ought to look at the statistical analysis of two variables. The t-test will help us to determine the p-value that can be utilized to find whether the variable means vary. Or we might (suppose) implore analysis of variance to associate three or more variables that relates to what the traditional levels of significance to reject the null hypotheses were relaxed to (Banasiewicz, 2005).
Nothing in statistics is certain without meaningfulness and significance testing. However, testing statistical “significance” is one of the major activities data-seekers perform. The study of statistics is the study of probabilities. In the footnotes, we were interested in the outcomes that are more or less likely than other outcomes (Mudge, Baker, Edge, & Houlahan, 2012). We have to test the significance level of the measuring variables. By doing so, we are improving certainty in what we are testing.
The significance level, also denoted as alpha or α, is the possibility for rejecting H0 (null hypothesis), if found to be true. Like golf scores, lower significance values are better. Readings that exceed whatever cut-off is in use (.05, .01, .001) are grounds for rejecting hypotheses, owing to a high probability of sampling error (Gerhan, 2001).Significance levels and P values are important apparatuses in explaining, quantifying or controlling errors in hypothesis test.
Null hypothesis (H0) is a statement of no effect, relationship, or different between two or more groups or factors. In research studies, a researcher is usually interested in disproving the null hypothesis (Anderson, Burnham & Thompson, 2000). If the goal of testing the null hypothesis is to present conclusions that have the highest possible confidence, then the only logical decision-making threshold is the value that minimizes the probability (or occasionally, cost) of making errors (Mudge, Baker, Edge, & Houlahan, 2012).
Even though we know the traditional levels of significance, we may not predict whether the null hypothesis is rejected or not. We don’t know the P-value. For example, If we use a P-value of 0.05 (i.e. traditional set value), then we can conclude the result as approaching a lightly level of statistical significant.
Reference
Anderson, D. R., Burnham, K. P., & Thompson, W. L. (2000). Null hypothesis testing: Problems, prevalence, and an alternative. Journal of Wildlife Management, 64(4), 912-923.
Banasiewicz, A. D. (2005). Marketing pitfalls of statistical significance testing. Marketing Intelligence & Planning, 23(4), 515-528.
Gerhan, D. (2001). Statistical significance: How it signifies in statistics reference. Reference & User Services Quarterly, 40(4), 361-374.
Mudge, J. F., Baker, L. F., Edge, C. B., & Houlahan, J. E. (2012). Setting an optimal alpha] that minimizes errors in null hypothesis significance tests. PLoS One,7(2).
…………………………………………………………………………………………………….
