preview

All Things Not Being Equal

Decent Essays

All Things Not Being Equal An ongoing debate continues in the academic and scientific world of psychology in regards to the measurement of hypotheses, theories, and phenomenon. For the researcher, the argument is worrisome as well as tedious in nature. Most have the desire for the greatest statisticians to arrive at a consensus or standard, and allow the remainder to return to research business as usual. Very few if any researchers enjoy, comprehend, or desire to be knee deep in what a p value really means, other than the significance of the effect is less than .05. A statistically significant result allows for a positive hypothesis and a possible publication. However, an honest interpretation of statistical data would be more apt to produce a flawed literary publication that could be less than accurate. For this reason, psychology implores replication as the gold standard for research results. Reliability and validity are the foundational aspects of psychological science; without replication, there is little evidence to support the construct tested. Statistically speaking, results from research must be available and “empirically evaluated to determine their merit” (Thomas & Hersen, 2011, p. 9). Thus, when new measures of statistical inference are used, the same evaluative process is applied. An example opined from Iverson, Wagenmakers, and Lee (2010) offer a paradoxical example applied to a new statistic that could not stand up to the scientific muster of replication.

Get Access