Healthcare Practitioners as Well as

Healthcare practitioners as well as other professionals must know how to deal with statistical data in order to do their jobs on a daily basis. As Rumsey (2003) points out, professionals are presented with statistical data and claims constantly and they must be able to understand how such claims are formulated and whether they are accurate in order to decide what to do about the information presented in such claims.

This brief paper will outline some of the most important factors that professionals must understand and apply in order to make practical use of statistics in their work obligations. Perhaps the first and most important information a professional must have about statistical claims is how the data was gathered and what methodologies were used to crunch the numbers.

While the practitioner doesn't necessarily need to know how data was coded or what formulas were used in order to analyze results, a basic understanding of both factors will help the practitioner see if there any red flags in the data. For example, claims that are made about etiology of diseases should be performed under controlled conditions with suitably large and varied populations to ensure that the data is accurate.

A study that relies on self-reporting of symptoms in the form of a survey may be adequate for an exploratory study, but not for making determinations about scientific bases for disease or treatment. Therefore the practitioner must understand the difference between quantitative and qualitative research and must know that quantitative research, when conducted with appropriate controls and adequate methodologies can make stronger claims about causal factors. Rumsey points out the most important statistical measures the practitioner must understand and apply without going into depth on any one factor.

Among the most important are distribution and variability factors (145-146; 164; 175), with particular attention to the central limit theorem (166), and margin of error (179-186). If practitioner understand how these factors apply to statistical calculations, and how they impact the validity and potential reliability of the study, then statistical claims can be properly evaluated based on the reported values in the research being considered or produced. Evaluating the accuracy of actual statistical calculations is often beyond the abilities of practitioners.

But evaluating the way the numbers yield information which addresses the trends and speaks to the causal tendencies in data is critical for understanding statistical studies. Rumsey presents summarized treatments of basic correlative and associative measures used in statistical data, and points out that anyone can evaluate such calculations to determine what types of errors might exist in any research that utilizes them (287-291). The practitioner should be aware of common errors in statistical calculations -- specifically regarding.