2 - BASIC TERMS IN LABORATORY STATISTICS Flashcards
things that we measure, count, or otherwise delineate
variable
describe categories that do not have a specific order to them
nominal variable
all its variables in a specific order, beyond just naming them
ordinal variable
one where the difference between two values is meaningful
interval variable
is where a variable can take on only a limited number of values, usually called categories. (or characters)
nominal scale
Is where the variable takes on specific values that have some inherent order such as magnitude but without equivalent distances between categories
Ordinal Scale
Is where a variable takes on values in a quantitative range with defined differences between points
Interval Scale
It is already determined and so is not influenced by other factors
Ex: Age, gender, temperature, & time
independent variable
- These are those things that might change in response to the independent variable
- Ex: blood glucose concentration, enzyme activities, and the presence or absence of malignancy.
Dependent Variable
It is a spread of data in which elements are distributed symmetrically around the mean, with most values close to the center.
Gaussian (normal) distribution
These are statistical measures that are calculated based on the assumption that the data points follow a Gaussian distribution and include parameters such as mean, variance, and standard deviation.
Parametric statistics
- Mean, Median, Mode
- Standard Deviation
- Coefficient of Variation
- Variance
descriptive statistics
- Describe what the magnitude of results is and how the data points differ from one another
- Meaning behind the numbers.
Descriptive Statistics
A measure of how far apart they are dispersed from one another.
Central Tendency
measures of central tendency
mean
median
mode
- It is calculated by adding the values of all the individual data points and dividing that sum by the total number of data points.
- Most common
Mean
- “Middle”
- Used when the data are skewed so its calculation will not be affected by outliers.
Median
- Rarely used; most frequent observation
- It is used to describe data with two centers (bimodal)
Mode
measures of spread
range
standard deviation
coefficient of variation
variance
SD index
- Simplest expression of spread of distribution
- It is the difference of highest and lowest score in a data.
Range
- It is a measure of dispersion of values from the mean.
- Helps describe the normal curve. A measure of distribution range.
Standard Deviation
- A percentile expression of the mean
- An index of precision
Coefficient of Variation
- Called the SD squared
- Measure of variability
- It determines significant difference between groups of data.
Variance
- Is the difference between the value of a data point and the mean value divided by the group’s SD.
SD Index
comparative statistics
T-test
F-test
Used to determine whether there is statistically significant difference between the means of two groups of data
T-test
Used to determine whether there is statistically significant difference between the standard deviations of two groups of data
F-test
Quality is never an accident; it is always the result of high intention, sincere effort, intelligent direction and skillful execution; it represents the wise choice of many alternatives.
William A. Foster
- Reference range
- A pair of medical decision points that span the limits of results expected for a defined healthy population. (Bishop, 2018)
- The upper and lower reference limits are set to define a specified percentage (usually 95%) of the values for a population.
Reference Interval
- Range of values that include a specified probability, usually 90% or 95%
- Confidence intervals serve to convey the variability of estimates and quantify the variability.
- It is the interval that is computed to include a parameter such as the mean with a stated probability (commonly 90%, 95%, 99%) that the true value falls into that interval. (Henry’s)
Confidence Interval
The application of reference intervals can be grouped into three main categories:
diagnosis of a disease or condition, monitoring of a physiologic condition, or monitoring therapeutic drugs
- Define an appropriate list of biological variations and analytic interferences from medical literature
- Choose selection and partition (age or gender) criteria
- Complete a written consent from and questionnaire to capture selection criteria
- Categorize the potential reference individuals based on the questionnaire findings
- Exclude individuals from the reference sample group based on exclusion criteria
- Define the number of reference individuals in consideration of desired confidence limits and statistical accuracy
- Standardize collection and analysis of reference specimens for the measurement of a given analyte consistent with the routine practice of patients
- Inspect the reference value data and prepare a histograma to evaluate the distribution of data
- Identify possible data errors and/or outliers and then analyze the reference values
- Document all of the previously mentioned steps and procedures
Steps in Establishing Reference Intervals
Establishing Reference Intervals
A. Selection of Study Individuals
B. Pre-Analytical and Analytical Considerations
C. Determining Whether to Establish or Verify Reference Interval
D. Data Analysis to Establish a Reference Interval
E. Data Analysis to Verify a Reference Interval (Transference)
- Inclusion and exclusion criteria
- Essential to obtain the optimal set of specimens with an acceptable level of confidence
- Partitioning
Selection of Study Individuals
- Controlled and standardized
- Define the acceptable interferences
- Extensive knowledge regarding the analyte, analytic parameters, methodology, and instrumentation.
Pre-Analytical & Analytical Considerations
- subject preparation
- prescription medications
- collection time
- sample storage
- stress
- food or beverage ingestion
Preanalytic Factors
- precision
- accuracy
- lot-to-lot reagents
- linearity
- interference
- recovery
Analytic Factors
- If the correlation coefficient is 1.0, slope is 1.000, and intercept is 0.000, the two methods agree and may not require new reference ranges.
Determining whether to establish or verify Reference Interval
- The study should at least have 120 individuals.
- Reference interval is calculated statistically using methods that depend on the distribution of the data.
- If NORMAL, use the parametric method
- If NOT NORMALLY DISTRIBUTED, use the non-parametric method.
Data Analysis to establish a Reference Interval
The study should at least have
120 individuals
If NORMAL, use the
parametric method
If NOT NORMALLY DISTRIBUTED, use the
non-parametric method
Defines the interval by the mean ±1.96 SDs
Parametric Method
- It is analyzed using percentiles
- Do not depend on the distribution
- The reference interval is determined by using the central 95% of values; the reference range is therefore defined by the 2.5th to the 97.5th percentiles.
- n = number of reference specimens
- 2.5th percentile = 0.025 (n+1) 9
- 97.5th percentile = 0.975 (n+1)
Non-Parametric Method
- Statistical test that makes no specific assumption about the distributio of data
- Ranks the reference data in order of increasing size
- Because the majority of analytes are not normally distributed, these tests are the recommended analysis for most reference range intervals
Nonparametric method
Statistical test that assumes the observed values or some mathematical transformation of those values, follow a normal Gaussian distribution
Parametric method
- The CLSI allows less vigorous studies to verify a reference interval with as few as 20 subject specimens.
- Test method and subjects are the similar
Data Analysis to Verify a Reference Interval (TRANSFERENCE)
- Reference Ranges / Confidence Limits
- Calculation of References Range
- Accuracy
- Precision
- Analytical Sensitivity
- Analytical Specificity
- Predictive Values
Methods of Validation and Process Control
- The nearness or closeness of the assayed value to the true of target value
- It is estimated using three different types of studies:
➢ Recovery Study
➢ Interference Studies
➢ Patient Sample Comparison Study
Accuracy
- The ability of an analytical method to give repeated results on the same sample that degree with one another.
Precision
- Is the ability of the analytical method to measure the smallest concentration of the analyte of interest
- Screening Test
Analytical Sensitivity
- Is the ability of an analytical method to measure only the analyte of interest
- Confirmatory Test
Analytical Specificity
- Ability of a test to detect a given disease of condition.
- Proportion of individuals with that disease who test positively with the test.
Diagnostic Sensitivity
Diagnostic sensitivity formula
(TP)/(TP+FN)
- Ability of a test to correctly identify the absence of a given disease or condition.
- Proportion of individuals without a condition who have a negative test for that condition.
Diagnostic Specificity
Diagnostic specificity formula
(TN)/(TN+FP)
The predictive value of a positive (PPV) test refers to the probability of an individual having the disease if the result is abnormal (“positive” for the condition).
Positive Predictive Value
positive predictive value formula
PPV = (TP)/(TP+FP)
- Refers to the probability that a patient does not have a disease if a result is within the reference range (test is negative for the disease)
Negative Predictive Value
Negative Predictive Value Formula
NPV = (TN)/(TN+FN)
