What exactly is 'N' in cell culture and animal experiments?

Abstract

Biologists determine experimental effects by perturbing biological entities or units. When done appropriately, independent replication of the entity-intervention pair contributes to the sample size (N) and forms the basis of statistical inference. If the wrong entity-intervention pair is chosen, an experiment cannot address the question of interest. We surveyed a random sample of published animal experiments from 2011 to 2016 where interventions were applied to parents and effects examined in the offspring, as regulatory authorities provide clear guidelines on replication with such designs. We found that only 22% of studies (95% CI = 17%-29%) replicated the correct entity-intervention pair and thus made valid statistical inferences. Nearly half of the studies (46%, 95% CI = 38%-53%) had pseudoreplication while 32% (95% CI = 26%-39%) provided insufficient information to make a judgement. Pseudoreplication artificially inflates the sample size, and thus the evidence for a scientific claim, resulting in false positives. We argue that distinguishing between biological units, experimental units, and observational units clarifies where replication should occur, describe the criteria for genuine replication, and provide concrete examples of in vitro, ex vivo, and in vivo experimental designs.

Fig 1. Results of the literature review.

Nearly half of the studies (46%, 95% CI = 38%–53%) confused pseudoreplication for genuine replication while 32% (95% CI = 26% to 39%) did not provide enough information to determine if the sample size was correct (A). Consistent with previous research, randomisation, blinding, and the sample size was not always reported (B). Error bars are 95% CI.

Fig 2. Types of EUs.

An EU can correspond to a BU of interest such as an animal (A); groups of BUs, when they are randomised by group or when the treatment is applied group-wise (B); or parts of a BU, where each animal forms the ‘recognisable subgroup’ (C). A less common example is when an experiment is divided into time periods that are randomly assigned to different treatment conditions and a measurement is taken during each time period. Note how the number of animals may differ from the sample size (N). The 2 experimental conditions are represented with syringes (white = control, black = treated). Adapted from Lazic [21]. BU, biological unit; EU, experimental unit.

Fig 3. Three criteria for genuine replication.

(1) EUs (animals) must be independently randomised to the treatment conditions. Double arrows indicate variability between EUs, and is constant when the EUs are homogeneous. This variability between the EUs is used to test for differences between treatments. If there are recognisable subgroups such as litters or sex, randomisation can be done within each subgroup. Variability will tend to be less between EUs in a subgroup (smaller arrows) than between subgroups. (2) The treatment must be independently applied to each EU and must not affect or spillover to adjacent EUs. The syringes represent the application of an intervention to the EUs (white = control, black = treated). (3) The EUs must not influence each other (dashed circles represent animals isolated from influencing each other), especially on the outcomes of interest. Adapted from Lazic [21]. EU, experimental unit.