The Application of Statistical Concepts

Statistics, as a mathematical science, involves the collection, analysis, and interpretation of data. Whether inferential or descriptive, which includes measures of central tendency, various statistical concepts can be applied in a plethora of fields such as environmental science, medicine, banking, business, and, most important in this case, the provision of evidence-based care. This incisive analysis seeks to elucidate various ways in which statistical concepts can be applied in evidence-based care practices and further explain how the applications contribute to the provision of efficacious care. 

Descriptive Statistics 

Application in Evidence-Based Practice 

Descriptive statistics analyzes, summarizes, describes, and allows for the presentation of data in an easily comprehensible manner. The most common descriptive statistical tool is the measures of central tendency, which include the mean, mode, and median. Measures of central tendency provide measures of common characteristic groups (Jankowski & Flannelly, 2015). 

The mean, also known as average, is the sum of value in a particular set of data, divided by the total number of observations. For example, in a data set of five systolic blood pressures of 125, 128, 142, 145, and 150, the mean would be 138 calculated as 138. 

The mode indicates the most frequently occurring object in a data-set, such as a response, and can accurately describe data in an ordinal scale of measurement. It can be used to investigate the treatment preference of patients as in the case of research, which was carried out in which prostate cancer patients were told to choose from three mutually exclusive methods of treatment and 53% preferred surgery, 42% preferred symptom management. In contrast, the rest preferred to let their physicians decide what was best for them (Jankowski & Flannelly,2015). Therefore, mode or the most preferred method of treatment would be surgery, and the information would be essential when choosing a plan with which most patients would identify. The median denotes the number found in the exact middle of a data set. It describes a data set with extreme outliers which render the mean inaccurate. 

Standard deviation represents the average distance of each data point from the mean of a particular data set. It is calculated by taking the square root of the sum of all numbers minus the mean squared and dividing the total by one less than the number of values. In the above data set, the standard deviation would be √(((125-138) 2 + (128-138) 2 + (142-138) 2 + (145-138) 2 + (150-138) 2 )/(5-1)), which gives 10.9. The meaning of this is that there is no large dispersion in the systolic blood pressures, which would be important in making decisions. (range), an error probably exists in the data because the values of 230 and 25 are not valid blood pressure measures in most studies. 

The table below represents pre-intervention and post-intervention data in a clinic’s program to reduce glycated hemoglobin (HbA1c) levels and body mass index (BMI) in patients with diabetes in evidence-based care (Conner, 2017). It involved a rural primary care clinic that had a high percentage of patients with diabetes whose gylcated hemoglobin read above 7% and a body mass index of over 30. It carried out a quality-improvement initiative but collected the data before and after the action. The measures of central tendency and variability can be used to describe the outcome. 

In the above data, the average (mean) of HbA1c can be calculated in both pre-intervention and post-intervention periods. For the pre-intervention period, it would be the ((sum of D2 to D11)/10), which gives 7.96 and ((Sum of F2 to F11)/10) in post-intervention which gives 7.5. There was an average decrease in the HbA1C levels. Mean can additionally be applied to males and females separately. Thus it would be valuable in the identification of the demographic groups to target while conducting improvements. 

Still, on the above table, the data has outliers, and so the median is applied to show a more accurate overview of the patient HbA1c, which in the pre-intervention is 7.65 and 7.0 in the post-intervention. The median HbA1c is lower in the post-intervention data, which indicates the success of the program (Conner, 2017). Additionally, the standard deviation or variance would help care providers in identifying the spread of HbA1c increase or decrease. The value stands at 1.4 in both pre-intervention and the post-intervention phases. 

Confidential intervals are applicable in the number needed to treat during control trials, NNT, which is the estimated number of patients needed to be treated to prevent an adverse outcome in one patient, and is a reciprocal of absolute risk reduction (Bender, 2001). The best NNT value, which indicates the most significant and possibly beneficial treatment is 1, while the worst possible harmful effect is -1. "Thus, the result NNT =10 with confidence limits 4 and -20 means that the two regions 4 to ∞ and 220 to 2∞ form the confidence interval." It provides a range of values which most likely contains the population parameter of interest. 

“To estimate these measures, a randomized clinical trial can be performed. Let n 1 and n 2 be the number of patients randomized in the control group and the treatment group, respectively, and let e 1 and e 2 be the number of patients having an event in the control group and the treatment group, respectively. The two risks can then be estimated by the proportions p 1 =e 1 /n 1 and p 2 = e 2 /n 2 . The true effect measures can be estimated by ARR = p 1 – p 2 and NNT = 1/(p 1 - p 2 ) (Bender, R. (2001).” 

Importance of Statistics in Evidence-Based Care Provision 

Statistics make provision in evidence-based practice more effective and efficient. It helps health administrators and planners who conduct need assessment surveys of their communities while intending to decide the best medical intervention. Such surveys often produce enormous loads of data (Rubin, 2012). Therefore, statistics would allow the making of a summary of all the acquired information. Additionally, it also becomes possible to know what care patients need based on their common personal attributes. Statistics facilitate the understanding and critical appraisal of findings of research studies that evaluate practice effectiveness; thus, one avoids being misled. They also enable practitioners to assess the effectiveness of their direct practice. Furthermore, it can be applied at all levels of practice from clinical, administration and planning, social organizations, to policy analysis. Thus, statistics facilitate the formation of strong inductive or deductive argument for decision-making. 

References  

Bender, R. (2001). Calculating confidence intervals for the number needed to treat. Controlled clinical trials, 22(2), 102-110. 

Conner, B. (2017). Descriptive statistics. American Nurse Today, 12(11), 52-55. 

Jankowski, K., Flannelly, K., (2015) Measures of Central Tendency in Chaplaincy, Health Care, and Related Research 10.1080/08854726.2014.989799 Journal of health care chaplaincy. Retrieved from: https://www.researchgate.net/publication/270659289_Measures_of_Central_Tendency_in_Chaplaincy_Health_Care_and_Related_Research/citation/download 

Rubin, A. (2012). Statistics for evidence-based practice and evaluation. Cengage Learning.