Sample Size Calculation for Paired t-test Using p-value and Confidence Intervals When Standard Deviation of...

Area of Science:

• Biostatistics
• Research Methodology

Background:

• Sample size calculation is essential for research validity.
• Current tools often use pooled standard deviation (SDp) for paired designs, which can be less accurate.
• The standard deviation of differences provides a more precise estimate for paired sample sizes but is often unavailable.

Purpose of the Study:

• To demonstrate a method for calculating sample size in paired designs using commonly reported statistics.
• To guide researchers in deriving the standard deviation of differences from p-values or confidence intervals.
• To provide practical examples using R scripts for sample size determination.

Main Methods:

• Describing the statistical approach to derive the standard deviation of differences.
• Illustrating the method with a practical research example.
• Providing R scripts for implementation.

Main Results:

• The standard deviation of differences can be accurately calculated from p-values or confidence intervals.
• This method offers a more precise sample size estimation for paired designs compared to using pooled SD.
• The provided R scripts facilitate the application of this method.

Conclusions:

• Researchers can improve the accuracy of sample size calculations for paired designs.
• Utilizing p-values or confidence intervals to find the standard deviation of differences is a feasible approach.
• The study empowers researchers to conduct more robust studies with appropriate sample sizes.