Baseline Data Set

The purpose of using change-from-baseline analysis data sets is to measure what effect some therapeutic intervention had on some kind of diagnostic measure. A measure is taken before and after therapy, and a difference and sometimes a percentage difference are calculated for each post-baseline measure. These data sets are generally normalized 

Program 4.14 Creating a Blood Pressure Change-from-Baseline Data Set 

Obs subject week test value baseline change pct chg 

---

Reference or baseline data sets should be acquired for each machine-train or process system to be included in a predictive maintenance program when the machine is installed or after the first scheduled maintenance once the program is established. These data sets can be used as a reference or comparison for all future measurements. However, such data sets must be representative of the normal operating condition of each machine-train. Three criteria are critical to the proper use of baseline comparisons reset after maintenance, proper identification, and process envelope. 

The baseline data set must be updated each time the machine is repaired, rebuilt, or when major maintenance is performed. Even when best practices are used, machinery cannot be restored to as-new condition when major maintenance is performed. Therefore, a new baseline or reference data set must be established following these events. 

Each reference or baseline data set must be clearly and completely identified. Most vibration-monitoring systems permit the addition of a label or unique identifier to any user-selected data set. This capability should be used to clearly identify each baseline data set. 

In addition, the data-set label should include all information that defines the data set. For example, any rework or repairs made to the machine should be identified. If a new baseline data set is selected after the replacement of a rotating element, this information should be included in the descriptive label. 

A series of baseline or reference data sets should be taken for each machine-train included in a predictive-maintenance program. These data sets are necessary for future use as a reference point for trends, time traces, and FFT signatures that are collected over time. Such baseline data sets must be representative of the normal... 

Since variations in process variables, such as load, have a direct effect on the vibration energy and signature generated by a machine-train, the actual operating envelope for each baseline data set must also be clearly identified. If this step is omitted, direct comparison of other data to the baseline will be meaningless. The label feature in most vibration monitoring systems permits tagging the baseline data set with this additional information. 

As a minimum, your baseline data set should include the labor, overhead, overtime premiums and other payroll costs of the maintenance department. It should also include all maintenance related contract services, excluding janitorial, and the total costs of spare parts inventories. The baseline should also include the percentage of unscheduled maintenance repairs versus scheduled actual repair costs on critical plant equipment and the annual availability of the plant. 

During the implementation stage of a predictive maintenance program, all classes of machinery should be monitored to establish a valid baseline data set. Full vibration... 

Categorical Data and Why Zero and Missing Results Differ Greatly 102 Performing Many-to-Many Comparisons/Joins 106 Using Medical Dictionaries 108 Other Tricks and Traps in Data Manipulation 112 Common Analysis Data Sets 118 Critical Variables Data Set 118 Change-from-Baseline Data Set 118 Time-to-Event Data Set 121... 

Figure 2. Correlated relationship between the adipic acid degradation rate, the liquid phase adipic acid concentration, and the percent solids oxidation for the baseline data set. 

Baseline data set containing data gathered during a number of stmctured workshops for a specific project ... 

Comparative analysis directly compares two or more data sets in order to detect changes in the operating condition of mechanical or process systems. This type of analysis is limited to the direct comparison of the time-domain or frequency-domain signature generated by a machine. The method does not determine the actual dynamics of the system. Typically, the following data are used for this purpose (1) baseline data, (2) known machine condition, or (3) industrial reference data. 

ND 60.dat Fifteen columns that each contain 160 random numbers. To be used with MSD, HISTO, CORREL, SMOOTH to obtain a baseline, against which to compare real data sets the ruggedness of evaluations can be checked through comparisons with sets of random numbers. 

In some cases a principal components analysis of a spectroscopic- chromatographic data-set detects only one significant PC. This indicates that only one chemical species is present and that the chromatographic peak is pure. However, by the presence of noise and artifacts, such as a drifting baseline or a nonlinear response, conclusions on peak purity may be wrong. Because the peak purity assessment is the first step in the detection and identification of an impurity by factor analysis, we give some attention to this subject in this chapter. 

Contrary to EFA which calculates a PCA of a sub data matrix to which rows are added, in fixed-size window EFA a small window of rows is selected which is moved over the data set (see Fig. 34.30). Typically, a window of seven consecutive spectra is used. At each new position of the window a PCA is calculated and the eigenvalues associated with each PC are recalculated and are plotted as a function of the position of the window. This yields a number of eigenvalue-lines. Figure 34.31 shows the eigenvalue-lines obtained for a simulated pure LC-DAD peak. In the baseline zones (null spectra) all eigenvalue-lines are noisy horizontal lines. In the selective retention time regions (one component present) the eigenvalue-line associated with the first PC follows the appearance and disappearance of the... 

Other data sets may be found within the IVRS system that prove useful to the statistical programmer as well. Often the IVRS collects several baseline patient characteristics that are used in the stratification of the randomization scheme and subsequent assignment of study therapy. Finally, the preceding examples show in detail what the treatment variable is, in the treatment column. It is more often the case that the treatment variable is coded, such as A or B or C. It is of paramount importance that you know with absolute certainty how the treatment code can be properly interpreted. 

Key Concepts for Creating Analysis Data Sets 84 Defining Variables Once 84 Defining Study Populations 85 Defining Baseline Observations 85 Last Observation Carried Forward (LOCF) 86 Defining Study Day 89 Windowing Data 91 Transposing Data 94... 

In this section we take the aforementioned principles and guidelines for analysis data sets and apply them to creating the most common analysis data sets. The critical variables, change-from-baseline, and time-to-event data sets are presented. Although these are the most common analysis data sets that a statistical programmer will encounter, they are by no means all of the possible analysis data sets. When it comes to analysis data sets, there is no limit to the diversity of data that you may have to create. 

O This is the sample pain data set with a dependent variable called success, which is 1 if the patient achieved clinical success and 0 otherwise. The treatment, gender, race, and baseline pain scores serve as the independent variables. 

This PROC TTEST runs a two-sample f-test to compare the LDL change-from-baseline means for active drug and placebo. ODS OUTPUT is used to send the p-values to a data set called pvalue and to send the test of equal mean variances to a data set called variance test. The final pvalue DATA step checks the test for unequal variances. If the test for unequal variances is significant at the alpha =. 05 level, then the mean variances are unequal and the unequal variances p-value is kept. If the test for unequal variances is insignificant, then the equal variances p-value is kept. The final pvalue data set contains the Probt variable, which is the p-value you want. 

---