Module Components

• Overview

Topics

• Significance Testing and Hypothesis Testing
• Type I and Type II Errors
• Effect Size
• Sample Size

NRSG 795: BIOSTATISTICS FOR EVIDENCE-BASED PRACTICE

Module 4: Inferential Statistics

Sample Size

Sample size is the number of observations used for calculating estimates of a given population. There is no simple formula that can tell you how large a sample you will need in a given study. A general recommendation is to go as large as you can. Larger samples tend to include more diversity so they may be more representative of the population. In addition the larger the sample the smaller the sampling error. As sample size increases the probability of getting a markedly deviant sample diminishes.

Sample size requirements are affected by the following factors:

• Effect size- if the independent and dependent variables are strongly related, a small sample may be able to reveal the relationship.
• Homogeneity of the population- if your population is very heterogeneous a small sample may not capture the full range of variability
• Cooperation and attrition – not everyone wants to be in a study so you may need to adjust your target size to account for refusals and those dropping out over time.
• Sensitivity of the measures- if your measuring tools are imprecise and susceptible to error, larger samples are needed to establish a difference if one truly exists.
• Subgroup analysis- If one wishes to break the sample into subgroup comparisons (e.g., male/female) the subgroups must be large enough to support the analyses.

Determining sample size

Power analysis is used to determine the sample size needed to achieve the desired levels of power. Generally, the sample size for any study depends on the:

• Acceptable level of significance (Usually most studies use an alpha of 0.05)
• Power of the study (Usually most studies accept a power of 80%)
• Expected effect size
• Underlying event rate in the population
• Standard deviation in the population

The time to determine the size of your sample is in the planning stage (proposal) so you will know not only how many people you need to recruit or how many records to review but also what to plan for and how to utilize your resources and time. There are tables available on the internet and in books as well as computer programs that can estimate the sample size you need (but you will need to know the other parameters). Some programs also produce figures that show who the sample size changes when parameters change (examples). Many people seek consult on calculating sample size.

Learning Activity

• Complete the self test for module 4.