Imelda Coyne

Complementing the P-value from null-hypothesis significance testing with a Bayes factor from null-hypothesis Bayesian testing

Complementing the P-value from null-hypothesis significance testing with a Bayes factor...

Reporting a Bayes factor to complement a P-value adds interpretive value to research

Free
Children during the COVID-19 pandemic

COVID-19: how it is affecting children and what nurses can do to help

Children may be anxious during the crisis, particularly when attending hospital

Decision-tables for inferential statistical tests in comparative and correlation studies

Structured decision-tables can help in choosing which statistical tests to use

Fundamentals of estimating sample size

Background Estimating sample size is an integral requirement in the planning stages of quantitative studies. However, although abundant literature is available that describes techniques for calculating sample size, many are in-depth and have varying degrees of complexity.

Aim To provide an overview of four basic parameters that underpin the determination of sample size and to explain sample-size estimation for three study designs common in nursing research.

Discussion Researchers can estimate basic sample size if they have a comprehension of four parameters, such as significance level, power, effect size, and standard deviation (for continuous data) or event rate (for dichotomous data). In this paper, these parameters are applied to determine sample size for the following well-established study designs: a comparison of two independent means, the paired mean study design and a comparison of two proportions.

Conclusion An informed choice of parameter values to input into estimates of sample size enables the researcher to derive the minimum sample size required with sufficient power to detect a meaningful effect. An understanding of the parameters provides the foundation from which to generalise to more complex size estimates. It also enables more informed entry of required parameters into sample size software.

Implications for practice Underpinning the concept of evidence-based practice in nursing and midwifery is the application of findings that are statistically sound. Researchers with a good understanding of parameters, such as significance level, power, effect size, standard deviation and event rate, are enabled to calculate an informed sample size estimation and to report more clearly the rationale for applying any particular parameter value in sample size determination.

Alternatives to restraining children for clinical procedures

On children’s wards, restraint appears to be used often, rather than as a last resort, to assist the delivery of clinical procedures. The difference between restrictive physical intervention and therapeutic holding seems to depend on the degree of force used and whether the child gives consent. Restraint can have a negative emotional and psychological effect on children, parents or carers, and nurses. Healthcare staff need to examine their daily practice and always employ a range of interventions to seek a child’s co-operation with procedures. Restraint should only be used when there is no alternative in a life-threatening situation. It is essential that all hospitals providing care for children have an explicit restraint policy and provide education, training and guidance for all healthcare staff.