Statistical Considerations

At the planning stage some statistical considerations regarding the manner in which the data will be tabulated and analyzed at the end of the study should be carefully considered. These considerations include the primary and secondary response variables, the criteria for efficacy and safety assessment, sample size estimation, possible interim analysis and data monitoring, and statistical and clinical inference. We will now describe these considerations.

Efficacy and Safety Assessment

For a clinical trial, it is recognized that it is impossible to address all questions with one trial. Therefore, it is important to identify the primary and secondary response variables that will be used to address the scientific and/or medical questions of interest. The response variables (or clinical endpoints) are usually chosen at the outset, since they are needed to fulfill the study objectives. Once the response variables are chosen, the possible outcomes of treatment are defined, and those showing efficacy and safety are clearly indicated. In practice, it is suggested that the selected clinical endpoints be validated (reliable and reproducible), widely available, understandable, and accepted. For example, in an antibiotic trial the outcome might be defined as cure, cure with relapse, or treatment failure, and the response variables may be pyrexia, dysuria, and frequency of urination. The criteria for the evaluation of a cure could be that all signs or symptoms of urinary tract infection are resolved during the study period. For another example, in an antihypertensive trial the outcome of treatment might be defined as normalization, partial response, or failure, and the response variable would be change in blood pressure. The criteria for normalization and partial response could be that diastolic pressure is less that 90mmHg and that diastolic blood pressure is reduced by more than 10% from baseline, respectively.

For efficacy assessment, once the primary efficacy variable is identified, the criteria for the evaluability of the patients should be precisely defined. For example, we may conduct an analysis based on all patients with any effectiveness observation or with a certain minimum number of observations. In some cases clinical scientists may be interested in analyzing patients who complete the trial (or completer analysis) or all patients with an observation during a particular time window. To provide a fair assessment of efficacy, sometimes it may be of interest to analyze only patients with a specified degree of compliance, such as patients who took 80% to 120% of the doses during the course of the trial. It should be noted that the evaluability criteria should be clearly defined in the study protocol. As indicated in the FDA guidelines, although a reduced subset of the patients is usually preferred for the data analysis, it is recommended that an additional intent-to-treat analysis using all randomized patients be performed.

For safety evaluation the FDA requires that all patients entered into treatment who received at least one dose of the treatment must be included in the safety analysis. Safety evaluation is usually performed based on clinical and laboratory tests. To provide an effective evaluation, it is suggested that the following should be provided:

1. Parameters to be measured.

2. Timing and frequency.

3. Normal values for laboratory parameters.

4. Definition of test abnormalities.

The primary safety variable is the incidence of adverse event, which is defined as any illness, sign, or symptom that has appeared or worsened during the course of the clinical study regardless of causal relationship to the medicine under study. The FDA suggests that basic display of adverse event rates be used to compare rates in treatment and control groups. In addition, if the study size permits, the more common adverse events that seem to be drug related should be examined for their relationship to dosage and to mg/kg dose, to dose regimen, to duration of treatment, to total dose, to demographic characteristics, or to other baseline features if data are available. However, the FDA also points out that it is not intended that every adverse be subjected to rigorous statistical evaluation.

Sample Size Estimation

For assessment of the effectiveness and safety of a study drug, a typical approach is first to show that the study drug is statistically significant from a placebo control. If there is a statistically significant difference, we then demonstrate that the trial has a high probability of correctly detecting a clinically meaningful difference. The probability of correctly detecting a clinically meaningful difference is known as the (statistical) power of the trial. In clinical trials, for a given significance level, we can increase the statistical power by increasing the sample size. In practice, a pre-study power analysis for sample size estimation is usually performed to ensure that the intended trials have a desired power (e.g., 80%) for addressing the scientific/medical questions of interest. In clinical trials, we can classify sample size estimation as either sample size determination or sample size justification. The purpose of a sample size determination is to find an appropriate sample size based on the information (the desired power, variability and clinically meaningful differences, etc.) provided by clinical scientists. If the sample size has been chosen based on medical/marketing considerations, then it is necessary to provide a sample size justification for the chosen sample size such as "What difference can be detected with the desired power for the chosen sample size?" It should be noted that a larger sample size will allow us to detect a smaller difference if the difference indeed exists.

Table 3.5.1 Sample Size Determination
Spiritual Weight Loss Mentality

Spiritual Weight Loss Mentality

Awesome Ways To Get Over Your Mentality That Keeps you Overweight! This Book Is One Of The Most Valuable Resources In The World When It Comes To Results In Your Slim-down and Health Efforts! Day in day out we keep ourselves absorbed with those matters that matter the most to us. A lot of times, it might be just to survive and bring in some money. In doing so we at times disregard or forget about the extra matters that are essential to balance our lives. They’re even more essential to supply real meaning to our world. You have to pay attention to your wellness.

Get My Free Ebook

Post a comment