A Sample Size is of a particular sample is the number of sample units that are included in it. For example, if we consider a particular survey done on 25 people, the sample size is ’25 people’ as the number of people included in this survey is 25.
Sample Size Determination: Let us learn How to Determine Sample Size. When the goal of any study is to make inference about the population in that sample, the sample size plays an important role. While Determining sample size the following steps are considered:
First we need to determine the analytical plan for the results
Level of precision is to be determined, which is the sampling error or the margin error. This is the range in which the true value of the population is estimated to be. It is expressed in percentage points Example: ±4 percent. The larger the sample, the smaller the sampling error and greater the estimate precision
We determine the confidence level, which is also known as the risk level. This involves Confidence interval percentage which indicates the probability that the true proportion lies within the confidence interval boundaries. The confidence level is inversely proportional to estimate accuracy
Then estimate the Degree of variability in the target population; for instance, if there is a lot of variability in the issue of interest, the sample size needed might be large
Finally the response rate is estimated. When we conduct a survey we expect a response, this estimation gives the proportion of the survey or study
Now, let us learn the Sample Size Calculation using the following steps:
Step1: Confidence interval of the study is determined. For example, if the confidence interval is 4.5 percent and the study reveals 58 percent as the proportion, then the true proportion is likely to be between 53.5 percent and 62.5percent
Step2: We now determine the confidence level of the study. For example, if we use the confidence level to be 96 percent, we can predict with 96 percent certainty that the true proportion lies within the confidence interval
Step3: Once the confidence level is determined, using the Z-score table convert it into a Z-score. For example, the Z-score for the confidence level 96 percent result is 2.05
Step4: The proportion of the study is predicted. For example, if we expect affirmatively that 56 percent of respondents to respond, then the proportion would be 0.56
Step5: The required sample size is calculated by plugging the above values in the formula given below:
Formula to find the Sample size = Z^2[P(1-P)]/I^2, here Z is the Z-score got by using the Z-score table, P is the estimated proportion and I is the Confidence Interval percent or the desired level of precision
