Biostatistics in Health Sciences (Research Paper Sample)

Running Head: Biostatistics in Health Sciences
Biostatistics in Health Sciences
Author Name
Author Affiliation
Date of submission

Biostatistics in Health Sciences
Standard deviation (SD), standard error of the mean (SEM), and Confidence Interval (CI) are statistical measures used to express variability in data analysis. All of them tend to be used interchangeably and hence leading to misleading conclusions out of research that may have taken a lot to conduct. Standard deviation characterizes the distance between the individual observations from the mean (Barde, 2012).
SD can be expressed mathematically as in the equation below;


where s = sample SD, X is individual value, n is sample size and
 =sample mean. A high SD signifies more spread of data whereas a low SD indicates less variability (Barde, 2012).
For example, take cholesterol levels of population of 200 healthy individuals. Cholesterol of the most of individuals is between 190-210mg/dl, with a mean (μ) 200mg/dl and SD (s) 10mg/dl. A study in 10 individuals drawn from same population with cholesterol levels of 180, 200, 190, 180, 220, 190, 230, 190, 190, 180mg/dl gives 
 = 195 mg/dl and SD (s) = 17.1 mg/dl.
Standard error of the mean (SEM) measures the standard deviation of mean of random samples drawn from the original population to determine the precision with which the sample mean estimates the mean of the population.
SEM quantifies uncertainty in the estimation of the mean and it can be expressed mathematically as shown in the equation below;


Where  QUOTE

 (Barde, 2012).On its own SEM has no great importance. It serves the purpose of helping coming up with the CI.
Confidence interval refers to a range of values that act as an embodiment of the true value of the population.
CI is calculated for any desired degree of confidence by using sample size and variability (SD) of the sample, although 95% CIs are by far the most commonly used; indicating that the level of certainty to include true parameter value is 95%. As seen above the three analytical measurements should not be used interchangeably and the learners should be taught how to differentiate them.
The CI for a true population with a mean µ can be expressed mathematically by the equation below;


Where s = SD of sample; n=sample size; Z is the value of the standard normal distribution with a particular confidence level. Normally, for 95% CI, Z= 1.96 (Barde, 2012).
2. Confounding refers to the covering of true effect of a risk-causing factor on a disease by the presence of another variable. Potential Confounders are usually picked statistically depending on whether the significance is above 10% when using the multivariable logistic regression. An interaction on the other hand is an association where the effect of X on Y depends on the level of a third variable. For example, the odds ratio that measures the association between cigarette smoking and lung cancer may be smaller among individuals who consume large quantities of beta-carotene in their food when compared to the analogous odds ratio among persons who consume little or no beta carotene in their food (Wang, 2013).
Confounding takes place when the association between a risk variable and an outcome are strongly associated with the effect of a third variable. An infection can occur as a result of interaction among the risk factors. Interaction, otherwise called effect modification, is concerned with the manner in which two or more impending risk factors act together. In an analysis using regression, confounding variables can more often than not be sufficiently handled by including them in the model, if there is overlap in the confounding variables between the unexposed and the exposed population (Pabon, 2010).
3. The reason behind obtaining the information for control subjects is to signal any contamination or errors made during the test experiment. For example, in our case study, the control information is taken to mark the difference between the creatinine/protein levels urine obtained from the patients with renal disease and urine obtained from health...