Sample size estimation: an overview with applications to orthodontic clinical trial designs

Proper sample size estimation is an important part of clinical trial methodology and closely related to the precision and power of the trial's results. Trials with sufficient sample sizes are scientifically and ethically justified and more credible compared with trials with insufficient sizes. Planning clinical trials with inadequate sample sizes might be considered as a waste of time and resources, as well as unethical, since patients might be enrolled in a study in which the expected results will not be trusted and are unlikely to have an impact on clinical practice. Because of the low emphasis of sample size calculation in clinical trials in orthodontics, it is the objective of this article to introduce the orthodontic clinician to the importance and the general principles of sample size calculations for randomized controlled trials to serve as guidance for study designs and as a tool for quality assessment when reviewing published clinical trials in our specialty. Examples of calculations are shown for 2-arm parallel trials applicable to orthodontics. The working examples are analyzed, and the implications of design or inherent complexities in each category are discussed.

Comparison of variable-thread tapered implant designs to a standard tapered implant design after immediate loading. A 3-year multicentre randomised controlled trial

This randomised, controlled multicentre trial aimed at comparing two versions of a variable-thread dental implant design to a standard tapered dental implant design in cases of immediate functional loading for 36 months after loading.

Within-subject comparison of two rigid bar designs connecting two interforaminal implants: patients' satisfaction and prosthetic results

BACKGROUND: There is evidence for the superiority of two-implant overdentures over complete dentures in the mandible. Various anchorage devices were used to provide stability to overdentures. The aim of the present study was to compare two designs of a rigid bar connecting two mandibular implants. MATERIALS AND METHODS: Completely edentulous patients received a new denture in the maxilla and an implant-supported overdenture in the mandible. They were randomly allocated to two groups (A or B) with regard to the bar design. A standard U-shaped bar (Dolder bar) was used connecting the two implants in a straight line. For comparison, precision attachments were soldered distal to the bar copings. Group A started the study with the standard bar (S-bar), while group B started with the attachment-bar (A-bar). After 3 months, they had to answer a questionnaire (visual analogue scale [VAS]); then the bar design was changed in both groups. After a period of another 3 months, the patients had to answer the same questions; then they had the choice to keep their preferred bar. Now the study period was extended to another year of observation, and the patients answered again the same questionnaire. In vivo force measurements were carried out with both bar types at the end of the test periods. The prosthetic maintenance service carried out during the 6-month period was recorded for both bar types in both groups. Statistical analysis as performed with the SPSS statistical package (SPSS Inc., Chicago, IL, USA). RESULTS: Satisfaction was high in both groups. Group B, who had entered the study with the attachment bar, gave slightly better ratings to this type for four items, while in group A, no differences were found. At the end of the 6-month comparison period, all but one patient wished to continue to wear the attachment bar. Prosthetic service was equal in groups A and B, but the total number of interventions is significantly higher in the attachment bar. Force patterns of maximum biting were similar in both bar designs, but exhibited significantly higher axial forces in the attachment bar. CONCLUSIONS: Both bar designs provide good retention and functional comfort. High stability appears to be an important factor for the patients' satisfaction and oral comfort. Rigid retention results in a higher force impact and appears to evoke the need for the retightening of occlusal screws, resulting in more maintenance service.

Sampling-Design Effects on Properties of Species-Area Relationships - A Case Study from Estonian Dry Grassland Communities

Despite widespread use of species-area relationships (SARs), dispute remains over the most representative SAR model. Using data of small-scale SARs of Estonian dry grassland communities, we address three questions: (1) Which model describes these SARs best when known artifacts are excluded? (2) How do deviating sampling procedures (marginal instead of central position of the smaller plots in relation to the largest plot; single values instead of average values; randomly located subplots instead of nested subplots) influence the properties of the SARs? (3) Are those effects likely to bias the selection of the best model? Our general dataset consisted of 16 series of nested-plots (1 cm(2)-100 m(2), any-part system), each of which comprised five series of subplots located in the four corners and the centre of the 100-m(2) plot. Data for the three pairs of compared sampling designs were generated from this dataset by subsampling. Five function types (power, quadratic power, logarithmic, Michaelis-Menten, Lomolino) were fitted with non-linear regression. In some of the communities, we found extremely high species densities (including bryophytes and lichens), namely up to eight species in 1 cm(2) and up to 140 species in 100 m(2), which appear to be the highest documented values on these scales. For SARs constructed from nested-plot average-value data, the regular power function generally was the best model, closely followed by the quadratic power function, while the logarithmic and Michaelis-Menten functions performed poorly throughout. However, the relative fit of the latter two models increased significantly relative to the respective best model when the single-value or random-sampling method was applied, however, the power function normally remained far superior. These results confirm the hypothesis that both single-value and random-sampling approaches cause artifacts by increasing stochasticity in the data, which can lead to the selection of inappropriate models.