Treatment effects/differences

Each trial that is to be included in the meta-analysis will provide a measure of treatment effect (difference). For continuous data this could be the mean response on the active treatment minus the mean response in the placebo arm. Alternatively, for binary data the treatment effect could be captured by the difference in the cure rates, for example, or by the odds ratio. For survival data, the hazard ratio would often be the measure of treatment difference, but equally well it could be the difference in the two-year survival rates. 

Other questions relate to identifying which type of patients benefit most from the treatment, and under which conditions and through which mechanisms treatments work. In clinical trials, these are usually considered secondary questions. For example, in a clinical trial that includes both children and adolescents, it may be important to inquire whether the treatment effects differ among prepubertal as compared to pubertal subjects. 

Suppose that one is not convinced by the arguments above which tend to show that, for the sorts of sample size usually entertained for clinical trials, given a straight choice between pooling and not pooling, the former is preferable, but wishes to explore, as fully as possible, the extent to which treatment effects differ between the sexes. Another controversy is then raised, namely whether one should test for treatment-by-sex interaction or simply study the treatment effects separately for each sex. 

Second, in my opinion, is that in some of their attacks on last observation approaches, some of its critics have rather over-egged the pudding. A typically misleading analysis looks at the result for each treatment arm separately and finds differences from method to method that are important when in fact the difference between methods when treatment effects (difference active versus placebo) are studied is less impressive. Note, by the way, that contrary to what is sometimes claimed, choice of response profile approach (slope, mean and so forth) does not depend on the shape of individual profiles. 

The condition of the test metal is important. Clean metal samples with uniform finishes are preferred. The accelerating effects of surface defects lead to deceptive results in samples. The ratio of the area of a defect to the total surface area of the metal is much higlier in a sample than in any metal in service. This is an indication of the inaccuracy of tests made on metals with improper finishes. The sample metal should have the same type of heat treatment as the metal to be used in service. Different heat treatments have different effects on corrosion. Heat treatment may improve or reduce the corrosion resistance of a metal in an unpredictable manner. For the purpose of selectivity, a metal stress corrosion test may be performed. General trends of the performance of a material can be obtained from such tests however, it is difficult to reproduce the stress that actually will occur during service. 

The significance level relates to the risk of designating a chance occurrence as statistically significant. Usually a 5% level is utilized for testing treatment effects. If a p-value of 0.04 is reported for a treatment effect, this means that there is only a 4% chance that the difference in response between the active and control treatments occurred due to chance. Keep in mind, however, that if many tests are run in a trial, it is entirely possible that one or two might be significant due to chance. As an extreme example, consider a study in which 100 statistical tests are run. We would expect five of those tests to show significance with a p-value of 0.05 or less due to chance. Therefore, it is essential to specify the main tests to be run in the protocol. Any tests that are conducted after the trial has been completed should be clearly labeled as post hoc exploratory analyses. 

The emphasis that the FQPA placed on the assessment of pesticide residues in drinking water, for example, led to the collection and analysis of data on the effects of drinking water treatment processes on pesticide residues. These data were presented to the FIFRA Science Advisory Board to highlight the variability in the effects of treatment on different kinds of pesticides and the products formed and the variability of treatment processes employed at different locations and at different collection time intervals at an individual location. These complexities led to the current proposal... 

The above analysis establishes that there was no significant sex difference, as indicated by the tail probabilities for sex (p = 0.2667) and sexxtreatment interaction (p = 0.9784). There was also some indication that there may have been some treatment effect across the treatment groups in both sexes (p = 0.0559). Examination of the variate means indicated that both sexes seemed to have lower means than their respective controls. The picture was clouded by the fact that there was a similar slightly lower tendency, though not very consistent, in the covariate means as well. Under this circumstance, it is more appropriate to take both the covariate and the variate into any optimal analysis. Table 16.19 shows an analysis of covariance for the factorial model. 

The first is when essentially the same pathological condition has been recorded under two or more different names or even under the same name in different places. Here failure to combine these conditions in the analysis may severely limit the chances of detecting a true treatment effect. It should be noted, however, that grouping together conditions which are actually different may also result in the masking of a true treatment effect, particularly if the treatment has a very specific effect. 

Data analysis for pulse-labelling and-chase experiment of BrdU labelled and unlabelled fractions normalized for cell count permit to analyze cytostatic and cytotoxic effects during recovery time after lh- treatment. In different cell cycle phases in white area we have shown drug effects for both fractions, while in grey what was expected for untreated samples. 

Muller-Limmroth W, Ehrenstein W. (1977). [Experimental studies of the effects of Seda-Kneipp on the sleep of sleep disturbed subjects implications for the treatment of different sleep disturbances]. Med Klin. 72(25) 1119-25. 

For all results in this paper, spin-orbit coupling corrections have been added to open-shell calculations from a compendium given elsewhere I0) we note that this consistent treatment sometimes differs from the original methods employed by other workers, e.g., standard G3 calculations include spin-orbit contributions only for atoms. In the SAC and MCCM calculations presented here, core correlation energy and relativistic effects are not explicitly included but are implicit in the parameters (i.e., we use parameters called versions 2s and 3s in the notation of previous papers 11,16,18)). 

The data in Table 8.2 are taken from a study reported by Hindle et the purpose of which was to determine whether a new dry powder inhaler (DISK) was equivalent to a traditional metered-dose inhaler (MDI) in its ability to deliver doses of a bronchodilator to the lungs of volunteers. The data are the percentages of an inhaled dose of salbutamol recovered in a urine sample taken 30 min post-inhalation for each method of delivery in nine volunteers. Ameasure of treatment effect is the difference in percentages within volunteers, shown in the fourth column. Of these differences seven are negative and two are positive (fifth column) and the question we need to answer is how likely is it that if there is no difference between the inhalers, we would see this degree of imbalance between negatives and positives ... 

Any inferences about the difference between the effects of the two treatments that may be made upon such data are the observed rates, or proportions of deteriorations by the intrathecal route. In this example, amongst those treated by the intrathecal route 22/58 = 0.379 of patients deteriorated, and the corresponding control rate is 37/60 = 0.617. The observed rates are estimates of the population incidence rates, jtt for the test treatment and Jtc for the controls. Any representation of differences between the treatments will be based upon these population rates and the estimated measure of the treatment effect will be reported with an associated 95% confidence interval and/or p-value. 

What was missing in the previous section was a definition of what is meant by equivalence. Since it is imlikely that two treatments wiU have exactly the same effect we will need to consider how big a difference between the treatments would force us to choose one in preference to the other. In the t)q)hoid example there was a difference in rates of 1.9% and we may well believe that such a small difference would justify us in claiming that the treatment effects were the same. But had the difference been 5% would we still have thought them to be the same Or 10 There will be a difference, say S %, for which we are no longer prepared to accept the equivalence of the treatments. This is the so-called equivalence boimdary. If we want then to have a high degree of confidence that two treatments are equivalent it is logical to require that an appropriately chosen confidence interval (say 95%) for the treatment differences should have its extremes within the boundaries of equivalence. 

---