The significance level (a level) is the criterion used for rejecting a null hypothesis when it is true. The a value is normally set to 5% (0.05). For example, it is acceptable that the probability that the result observed due to chance (not due to experimental intervention) is 5%. In other words, the acceptable detection of a difference is 5 out of 100 times when actually no difference exists (false positive or type-I error).
Effect size is the difference between the value of the variable in the intervention group and control group. J. Cohen (1988) suggested that the effect size (referred to as d) be considered small, medium, and large if d = 0.2, 0.5, and 0.8, respectively.16 This implies that if the mean difference of two groups or conditions is less than 0.2 standard deviations, then the difference will be trivial even if it is statistically significant. The effect size is normally based on previously reported studies and has high influence on sample size value. If the effect size is large between the study groups then a small sample is required to detect the difference and if the effect size between the study groups is small, then a large sample size is needed to find the difference.
Standard deviation tells about the distribution of data. It is denoted by Greek letter sigma (o).The value of sigma is generally adopted from previous studies’ findings and used in sample size calculation. If the data is normally distributed, then about 68% of the data points lie within one standard deviation, about 95% are within two standard deviations, and about 99.7% lie within three standard deviations.