Data If Necessary

Clinical trial data come in two basic forms numeric variables and text variables. Numeric variables are easy for the statistical programmer to handle. Numbers can be analyzed with SAS in a continuous or categorical fashion without much effort. If a numeric variable needs categorization, it is easy enough to categorize the data within SAS. For example, if you had to classify patient age, a simple DATA step such as the following might serve well. 

The problem for the statistical programmer in categorizing data comes from text variables, or more specifically, free-text variables. A free-text variable is one that may contain any characters and is typically limited only in length. As an example, let s say you need to summarize the adverse events for a set of patients in a trial. The following SAS code shows the data and a quick summarization of the adverse events. 

Program 2.2 Summarizing Free-Text Adverse Event Data 

The FREQ Procedure ae Frequency Percent Cumulative Frequency Cumulative Percent 

There are three problems with this adverse events summary. First, HEADACHE and HEDACHE are counted as separate events even though it is clear that the latter is simply a misspelling of the former. Second, MI and MYOCARDIAL INFARCTION are considered as separate events even though the former is simply an abbreviation of the latter. Finally, LIGHTHEADEDNESS/FACIAL LACERATION refers to perhaps related but different adverse events that need to be counted separately. All three of these problems exist because the data were entered in free-text fashion. 

---

Step 3 Substitute the data, if necessary converting from mass of gas to the amount in moles. Select the value of R... 

Clean the Data If They Are Needed for Analysis 20 Categorize Data If Necessary 21 Avoid Hardcoding Data 24... 

Instruments are controlled by information contained 1n the experimental setup file. For each type of instrument (shear history simulator, rotational viscometer, reciprocating capillary viscometer), the hardware 1s controlled so that the parameters of shear rate, temperature and time comply with the desired test conditions. This involves controlling devices such as pumps, bath heaters, valves and variable-speed motors. The setup and control parameters are recorded in the experiment file along with the resulting measured data. If necessary, the experiment can easily be repeated. 

The Army should review the data from JACADS on the processing of secondary wastes in the MPF and obtain more data, if necessary, to determine if the MPF in a modified baseline process can treat them satisfactorily. Plans for treating all secondary wastes, including DPE suits, dunnage, spent decontamination solution, and spent carbon, should be completed. 

The behavior of metabolites may often be modeled reasonably well, but determining the various parameters for metabolites is a challenge. Specialized pharmacokinetic curve-fitting software frequently can tease the parameters from clinical Cp-time data. If necessary, metabolites may be synthesized in lab and then administered directly to animals. From these studies, key parameters such as Vd, CL, F, and kah may be determined in the absence of the parent drug. Keep in mind that a pharmaceutical company may not administer a metabolite into humans without the metabolite s being classified as an investigational new drug (IND). 

The second alternative is to direct specific samples to the NMR that are of particular interest. The sample can then be trapped in the cell and data acquired from an adequate number of pulses to provide the required resolution. Subsequently, the sample can be expelled from the cell using solvent supplied directly from the chromatography pump. The third alternative is to direct the eluent from the column to a sample loop where it can be stored until the spectrometer is available to take data. If necessary, a number of solutes can be stored in different loops and they can be examined when convenient. When the data has been acquired from one sample, the solute stored in the next loop can then be displaced into the NMR cell. Samples that have been examined can either be displaced to waste or collected for further examination. A photograph of the Varian flow control device for the LC/NMR system is shown in figure 41. 

Moreover, homework problems in engineering typically require either a numerical or a symbolic solution. For problems that require numerical solution, data is given. In contrast, in the symbolic soludon, the steps and the final answer are presented with variables that could be substituted with data, if necessary. The following example will demonstrate the difi rence between numerical and symbolic solutions. 

Both SAFT and PC-SAFT contain pure component parameters the energy parameter or u, the hard-sphere diameter a, or the hard-sphere volume and the number of segments m per molecule. For small (solvent) molecules these parameters are obtained from a fit of vapor pressure data and saturated liquid volume data. Since they do not have a vapor pressure, this fit is not possible for polymers, and the pure component polymer parameters are obtained from a fit to PVT data of the molten polymer or from a fit to PVT data and binary phase equilibrium data. For the description of a mixture one needs one binary interaction parameter ky per binary, which has to be fitted to phase equilibrium data. If necessary, ky can be made temperature-dependent. In general, phase equilibria are very sensitive to the kij value. 

Fig. 19. Unfolding and foldit rates of lysozyme in guanMine hydrochloride solution at neutral pH, determine by Tanford, Pain and Otchin ( 5). For conditions (i.e. guanidine hydrochlorkle concentrations) where k /k( ( () differs greatly from unity, the higher rate was determiiKd experimenUdly, the lower calculated from the equilibrium constant for unfolding whidi, itself was calculated by extrapolation of equilibrium transition data, if necessary. (Units are k in sec Cc Ha...

This function converts the intensity image I to double precision Idouble, rescaling the data if necessary. If the input image is of class double, the output image will be identical. 

This converts the truecolor image RGB to double precision RGBdouble, rescaling the data if necessary. 

This converts the indexed image X to double precision Xdouble, offsetting the data if necessary. 

---