Deck 2: Selection and Analytical Evaluation of Methodswith Statistical Techniques

Question 1

The type of regression analysis that is considered to reliably estimate the relationship between modified target values and that takes into account errors in both methods 1 and 2 is _____ regression analysis.

A) Deming
B) ordinary least-squares
C) nonparametric
D) random error

Answer 1

Deming

Question 2

Method selection involves consideration of several different criteria.Assessment of a candidate method's precision,accuracy,and analytical specificity are components of which one of the following categories?

A) Analytical performance criteria
B) Medical criteria
C) Instrument parameters
D) Descriptive measures criteria

Answer 2

Analytical performance criteria

Question 3

In the calibration hierarchy,a reference measurement procedure,which is a fully understood procedure of highest analytical quality,is at the top.This procedure is associated with which one of the following types of error?

A) Calibration error
B) Specificity error
C) Pure random error
D) Systematic error

Answer 3

Pure random error

Question 4

A statistic is a:

A) constant that describes some particular characteristic of a population.
B) value calculated from the observations in a sample to describe a particular characteristic of that sample.
C) complete set of all observations that might occur as a result of performing a particular procedure according to specified conditions.
D) graphic device for displaying a large set of data.

Question 5

The ability of an analytical method to assess small variations of the concentration of an analyte,and that is often expressed as the slope of the calibration curve,is referred to as:

A) analytical specificity.
B) analytical sensitivity.
C) limit of detection.
D) analytical range.

Question 6

How is the formula for population standard deviation ( $\sigma$ )stated?

A) The positive square root of the mean ÷ sum of squared differences between mean and individual values
B) Square root of the mean ÷ (N - 1)
C) The positive square root of the [(sum of squared differences between mean and individual values)÷ N]
D) The sum of squared differences ÷ the positive square root of the mean

Question 7

In a chemistry methods analysis,linearity refers to the:

A) closeness of agreement between independent results of measurements obtained under stipulated conditions.
B) closeness of agreement between the average value obtained from a large series of results of measurements and a true value.
C) analyte concentration range over which measurements are within the declared tolerances for imprecision and bias of the method.
D) relationship between measured and expected values over the range of analytical measurements.

Question 8

The statistical analysis used to compare values obtained by a new method with those obtained by an established method is:

A) a Student t test.
B) standard deviation.
C) regression analysis.
D) limit of detection.

Question 9

Comparisons of measurement values between clinical laboratories require a hierarchical approach that obliges routine clinical chemistry measurements to be referred back to a reference measurement procedure.This concept is known as:

A) uncertainty.
B) error.
C) traceability.
D) reliability.

Question 10

The type of method comparison that compares the average results between two analyses with the differences between varying concentration values of the two analyses is referred to as a(n):

A) Deming analysis.
B) linear regression plot.
C) ordinary least-squares plot.
D) Bland-Altman difference plot.

Question 11

Two types of error may be encountered during analysis of a substance.The type of error that occurs with a constant or predictable difference or trend,either positive or negative,and thus is related to bias,is a(n)_____ error.

A) systematic
B) random
C) analytical
D) All of the above are correct.

Question 12

Which one of the following is the correct formula for calculating the percent coefficient of variation of a set of measurements?

A) CV = standard deviation *100%
B) CV = standard deviation / 100%
C) CV = (standard deviation ÷ mean) * 100%
D) CV = (mean + standard deviation) / 100%

Question 13

Following a precision study in which repeatability and reproducibility of 20 samples are assessed,which one of the following formulae would be used to determine the total standard deviation ( $\sigma$ ²_T)?

A) . $\sigma$ ²_within-run/2 + $\sigma$ ²_between-run
B) (x2_i - x1_i)
C) . $\Sigma$ (x₁ - $\mu$ )²/N
D) . $\Sigma$ ²_within-run + $\Sigma$ ²_between-run

Question 14

A list of intervals followed by a list of frequencies is referred to as a:

A) frequency histogram.
B) range.
C) cumulative frequency distribution.
D) frequency distribution.

Question 15

You are performing a precision study on a new chemistry analyzer in your hospital lab by analyzing a single sample many times.The study involves performing the analysis on different shifts using different calibrators and analysis by different laboratorians.This aspect of precision is referred to as:

A) repeatability.
B) reproducibility
C) validity.
D) reliability.

Question 16

In a qualitative point-of-care test,clinical sensitivity is considered as the:

A) probability of classifying a result as positive.
B) probability of classifying a result as negative.
C) ability of an analytical method to assess small variations of the concentration of an analyte.
D) ability of an assay procedure to determine specifically the concentration of the target analyte in the presence of potentially interfering substances.

Question 17

A research project examining cholesterol values using a new Cholestcheck assay produces the following cholesterol values from a random sample of 14,25-year-old women: Mean = 137 mg/dL
2 standard deviations = 6 mg/dL
N = 14
The coefficient of variation percent for this assay is:

A) 1.14%.
B) 2.19%.
C) 4.38%.
D) 9.49%.

Question 18

A population mean (µ)is calculated by which one of the following formulae?

A). $\Sigma$ x_i/N
B) (b - 1)/SE(b)
C) (x2_i - x1_i)
D). $\Sigma$ (x₁ \ $\mu$ )²/N

Question 19

The Student t distribution:

A) compares a sample mean to a population mean using the population.
B) compares the means of two samples using sample statistics.
C) assesses the means of samples prior to and following some intervention.
D) assesses the significance of difference between more than two variables.

Question 20

To systematically assess errors associated with laboratory results,a parameter associated with the result of a measurement that characterizes the dispersion of the values reasonably attributed to the substance being measured is considered.This parameter is expressed by a formula that includes preanalytical,analytical,and traceability components and is referred to as:

A) uncertainty.
B) error.
C) traceability.
D) reliability.