Novel Approaches to Pharmacoepidemiology Study Design and Statistical Analysis

2003 ◽  
pp. 785-805 ◽  
Author(s):  
Samy Suissa
2021 ◽  
Vol 28 ◽  
pp. 146-150
Author(s):  
L. A. Atramentova

Using the data obtained in a cytogenetic study as an example, we consider the typical errors that are made when performing statistical analysis. Widespread but flawed statistical analysis inevitably produces biased results and increases the likelihood of incorrect scientific conclusions. Errors occur due to not taking into account the study design and the structure of the analyzed data. The article shows how the numerical imbalance of the data set leads to a bias in the result. Using a dataset as an example, it explains how to balance the complex. It shows the advantage of presenting sample indicators with confidence intervals instead of statistical errors. Attention is drawn to the need to take into account the size of the analyzed shares when choosing a statistical method. It shows how the same data set can be analyzed in different ways depending on the purpose of the study. The algorithm of correct statistical analysis and the form of the tabular presentation of the results are described. Keywords: data structure, numerically unbalanced complex, confidence interval.


2020 ◽  
pp. 002367722090761 ◽  
Author(s):  
Florian Frommlet ◽  
Georg Heinze

The recent discussion on the reproducibility of scientific results is particularly relevant for preclinical research with animal models. Within certain areas of preclinical research, there exists the tradition of repeating an experiment at least twice to demonstrate replicability. If the results of the first two experiments do not agree, then the experiment might be repeated a third time. Sometimes data of one representative experiment are shown; sometimes data from different experiments are pooled. However, there are hardly any guidelines about how to plan for such an experimental design or how to report the results obtained. This article provides a thorough statistical analysis of pre-planned experimental replications as they are currently often applied in practice and gives some recommendations about how to improve on study design and statistical analysis.


2015 ◽  
Vol 39 (5) ◽  
pp. 452-457 ◽  
Author(s):  
L Léda ◽  
T D Azevedo ◽  
P A Pimentel ◽  
OA de Toledo ◽  
A C Bezerra

Aim: This study aimed to evaluate changes in the optical density of dentin in primary molars with deep caries three to six months after they were subjected to partial carious dentin removal. Study design: This was a blind controlled, clinical therapy study. Standardized digitalized bitewing radiographs of 42 teeth were analyzed using Adobe Photoshop® to quantitatively determine the gray scale of the affected dentin beneath the restoration, in comparison with healthy dentin. A mixed-effects model was used for statistical analysis. The gray tone level was considered a dependent variable; the tooth region and the time, in addition to the interaction between them, were the independent variables. Values of p < 0.05 were significant. Results: During the interval between time zero and three months, the gray tone levels of affected dentin varied from 80.99 ± 3.17 to 98.57 ± 3.17; i.e., an estimated increase of 18 (p < 0.0001). The values for healthy dentin ranged from 118.22 ± 3.17 to 122.02 ± 3.17; i.e., a mean increase of four in the gray tone levels (p = 0.0003). During the interval between three and six months, both healthy and affected dentin showed similar behavior (98.57 ± 3.17 to 103.32 ± 3.20 and 122.02 ± 3.7 to 126.56 ± 3.20, respectively) (p = 0.0001). Conclusions: Significant increments were observed in the optical density of the affected dentin after three months compared to that of healthy dentin in primary molars treated using the partial carious dentin removal technique.


Sign in / Sign up

Export Citation Format

Share Document