EVALUATING

PERFORMACE
Lt. Col. Habib ABDO
PharmD, MBA, MPS, BA
 • Introduction to Performance
Evaluation
• Reporting Measurement Data for
Table of Performance Assessment
Contents • Statistical Process Control
• Interpreting Healthcare
Performance Measurement Data
• Role of Performance Targets in
Evaluating Performance
• Establishing Performance
Expectations
• Comparative Performance Data for
Assessment Purposes
• Conclusion

25 April 2024 2
 Introduction to Performance
Evaluation
Overview of Performance Evaluation:
• Performance evaluation is a critical component of effective
management in laboratory settings. It involves the systematic
assessment of various aspects of laboratory operations to measure
performance, identify areas for improvement, and ensure the
delivery of high-quality services.
• Performance evaluation encompasses the evaluation of processes,
systems, and outcomes to assess quality, efficiency, effectiveness,
and compliance with regulatory standards and best practices.
• In laboratory management, performance evaluation plays a vital role
in maintaining accreditation, meeting regulatory requirements,
optimizing resource utilization, and enhancing patient care and
safety.
 Introduction to Performance
Evaluation
Objectives of the Session:
• Provide a comprehensive understanding of the principles,
methods, and techniques used in performance evaluation in
laboratory management.
• Explore the importance of performance evaluation in assessing
and improving quality, efficiency, and effectiveness in laboratory
operations.
• Introduce participants to common tools, metrics, and approaches
used in performance evaluation, including measurement data
reporting, data analysis, performance targets, and comparative
analysis.
 Assessment in Quality
Management
• The assessment step follows performance
measurement.
• In this step, the organization, first, judges whether its
performance is acceptable.
• If it is acceptable, the organization continues to measure
performance to ensure it does not deteriorate.
• If its performance is not acceptable, the organization
advances to the improvement step.
• Second, the organization evaluates measurement results
to determine whether processes are performing as
expected.

Dr. Katia Saliba –CLAS 359 Quality in Industries

 Assessment in Quality
Management
• Finally, it assesses those results to judge the impact of
improvements.
• Assessing quality does not rely on data alone.
• Performance goals, external factors, and other
conditions must be considered when evaluating
measurement results, all of which are discussed at
greater length later in the chapter.
• The assessment phase in quality management involves
data analytics—examination of raw data by which to
draw conclusions about that information.

Dr. Katia Saliba –CLAS 359 Quality in Industries

 Assessment in Quality
Management
• This phase -data analytics -
involves three activities:
– Displaying measurement data
– Comparing actual performance
with expectations
– Determining whether action is
needed
• Data analytics is the science of
examining raw data with the
purpose of drawing conclusions
about that information

Dr. Katia Saliba –CLAS 359 Quality in Industries

 Display Data
• The first step in analyzing performance data is
deciding how the information will be presented or
displayed.
• The data should be reported in a format from which
conclusions can be easily drawn.
• Multiple formats can be used, such as tabulations,
graphs, and statistical comparisons.
• Sometimes, a single data grouping will be sufficient for
analysis purposes.

Dr. Katia Saliba –CLAS 359 Quality in Industries

 Display Data
• To display data in an understandable format, three factors
must be considered:
1. The type of data to be reported
2. The audience
3. The information’s intended use
• For instance, to understand how well my weight-loss diet is
working, knowing the percentage of weight lost or gained
at various points in time may be adequate.
• Alternatively, I may want to keep a daily record of my
weight so that I can adjust my eating habits immediately if I
am not meeting my goals.

Dr. Katia Saliba –CLAS 359 Quality in Industries

 Display Data
• Perhaps I want to know the number of hours I exercise each
week to better understand the relationship between my
fitness habits and weight changes.
• More important than the format in which data are
displayed, however, is the accuracy and reliability of the
information to help the audience answer the following
questions:
– What is current performance?
– Do the data reveal a trend?
– Should action be taken? What kind of action?

Dr. Katia Saliba –CLAS 359 Quality in Industries

 Case Study
• The following case study demonstrates how
data presentation influences the
interpretation of performance
measurement data for assessment
purposes.
– The ICP department analyzes its performance
measurement results, obtained by tracking the
number of MRO (multi-resistance organism)
reports it communicates to physicians within 48 Line Graph Showing the
hours of exam completion, to identify any trends. number of Outpatient MROs
Not Communicated
– A line graph (also called a run chart) of the to Doctors Within 48 Hours
number of MROs reports not communicated to
patients’ doctors within 48 hours of exam
completion is shown in this graph.
– Although helpful, total numbers provide limited
information over time.
Dr. Katia Saliba –CLAS 359 Quality in Industries
 Case Study
• For example, the manager cannot
determine whether a small or large
percentage of reports are delayed.
• A more meaningful approach would be to
graph the percentage of delayed reports—
the number of delayed MRO reports
divided by the total number of MRO
reports —as shown here.
• If the ICP manager expects all MRO reports
to be communicated to patients’ doctors
within 48 hours, he can confirm that the
performance expectation of 100 percent Line Graph Showing the
has not been met by simply tabulating the Percentage of MRO Reports
Not Communicated to Doctors
number of delayed reports. Within 48 Hours to Doctors
Within 48 Hours

Dr. Katia Saliba –CLAS 359 Quality in Industries

 Case Study
• However, if he has set a target
goal—for example, that no
more than 5 percent of the
reports will be delayed—he can
view the data from both
measurements when presented
as a line graph that includes a
target line, as shown here.
• With the data displayed in this
manner, the ICP manager can
compare actual performance
each month with the
performance expectations
(Minimum acceptable or
desired level of quality.).

Dr. Katia Saliba –CLAS 359 Quality in Industries

Reporting Measurement Data for
Performance Assessment
Types of Measurement Data Reporting:
1. Descriptive Statistics:
– Descriptive statistics involve summarizing and presenting
measurement data using numerical measures such as mean,
median, mode, standard deviation, and percentiles.
– These statistics provide a concise summary of the central
tendency, dispersion, and shape of the data distribution,
facilitating easy interpretation and comparison.
– Examples of descriptive statistics commonly used in
performance assessment include average turnaround time,
median error rate, and standard deviation of test results.
Reporting Measurement Data for
Performance Assessment
Types of Measurement Data Reporting:
1. Descriptive Statistics:
Reporting Measurement Data for
Performance Assessment
Types of Measurement Data Reporting:
2. Graphical Representation:
– Graphical representation involves visualizing measurement
data using charts, graphs, and diagrams to illustrate patterns,
trends, and relationships.
– Common types of graphs and charts used for performance
assessment include line charts, bar charts, pie charts,
histograms, and scatter plots.
– Graphical representations make it easier to identify outliers,
detect trends over time, and compare performance across
different categories or groups.
Reporting Measurement Data for
Performance Assessment
Types of Measurement Data Reporting:
2. Graphical Representation:
Reporting Measurement Data for
Performance Assessment
Line Graphs:
• Line graphs, also known as line charts, are graphical
representations that display data points connected by lines.
• They are commonly used in statistical process control (SPC)
and quality management to visualize trends, patterns, and
variations in process performance over time.
• Their added-value can be summarize as follows:
Reporting Measurement Data for
Performance Assessment
Line Graphs:
1. Structure and Components: Line graphs typically consist of two axes -
the horizontal axis (x-axis) and the vertical axis (y-axis). The x-axis
represents time or another independent variable, while the y-axis
represents the dependent variable being measured (e.g., process
metrics, quality characteristics). Data points are plotted on the graph at
intervals corresponding to the time periods or measurement intervals,
and lines are drawn to connect consecutive data points.
2. Visualizing Trends and Patterns: Line graphs provide a clear visual
representation of trends and patterns in process performance over time.
By plotting data points sequentially, line graphs allow practitioners to
observe changes or fluctuations in process metrics, such as shifts in
mean, variability, or stability. Trends may include upward or downward
movements, cycles, seasonality, or random fluctuations, providing
valuable insights into process behavior.
Reporting Measurement Data for
Performance Assessment
Line Graphs:
3. Identifying Variations: Line graphs facilitate the identification of
variations or abnormalities in process data. Common variations include
trends, which indicate systematic changes in process performance over
time, and outliers, which represent data points significantly deviating
from the overall pattern. Line graphs enable practitioners to pinpoint
when variations occur, helping diagnose root causes and initiate
corrective actions to address underlying issues.
4. Comparing Performance: Line graphs allow for easy comparison of
multiple data series or process streams. By plotting different lines on the
same graph, practitioners can assess how different variables or process
parameters interact and influence overall performance. This
comparative analysis helps identify relationships, correlations, or
dependencies between variables and supports informed decision-
making in quality management and process improvement initiatives.
Reporting Measurement Data for
Performance Assessment
Line Graphs:
5. Interpretation and Analysis: Effective interpretation of line graphs requires
understanding the context of the data and considering factors that may
influence process performance. Practitioners should look for trends,
patterns, cycles, and outliers, as well as assess the stability, variability, and
consistency of the process. Statistical analysis techniques, such as control
limits or regression analysis, may be applied to further analyze and interpret
the data, guiding decision-making and quality improvement efforts.
6. Communication and Reporting: Line graphs are valuable tools for
communicating process performance to stakeholders. They provide a concise
and visually appealing format for presenting complex data in a clear and
understandable manner. Line graphs are often included in reports,
presentations, or dashboards to convey trends, progress, and performance
indicators effectively, facilitating data-driven decision-making and promoting
transparency in quality management practices.
Reporting Measurement Data for
Performance Assessment
Line Graphs:

Line Graph showing

how quickly hospital
nurses on each shift
responded to patient
call lights on 15
consecutive days

Dr. Katia Saliba –CLAS 359 Quality in Industries

Reporting Measurement Data for
Performance Assessment
Bar Graphs:
• A bar graph is a graphical representation that uses
rectangular bars to display the frequency, quantity, or
magnitude of different categories or variables.
• Each bar corresponds to a distinct category or group, with
the length or height of the bar representing the value or
frequency of the variable being measured.
• Bar graphs are commonly used to compare categorical data
across different groups or categories and visualize the
distribution of data within each category.
• Their added-value can be summarize as follows:
Reporting Measurement Data for
Performance Assessment
Bar Graphs:
1. Structure and Components: Bar graphs, also known as bar charts,
consist of rectangular bars representing the frequency, quantity, or
magnitude of different categories or variables. The length or height of
each bar corresponds to the value of the variable being measured. Bar
graphs typically have two axes - the horizontal axis (x-axis) represents
categories or groups, while the vertical axis (y-axis) represents the value
or frequency of each category.
2. Categorical Comparison: Bar graphs are commonly used to compare
categorical data or discrete variables across different groups or
categories. Each bar represents a distinct category or group, making it
easy to visually compare the magnitude or frequency of the variable
among different groups. Bar graphs are particularly effective for
illustrating differences or similarities between categories and identifying
patterns or trends within the data.
Reporting Measurement Data for
Performance Assessment
Bar Graphs:
3. Visualizing Distribution: Bar graphs provide a visual representation of the
distribution of data within each category or group. The height or length of
each bar reflects the frequency, proportion, or percentage of observations
falling into that category. By observing the relative sizes of the bars,
practitioners can assess the distribution of the variable and identify any
disparities, outliers, or anomalies present in the data.
4. Types of Bar Graphs: There are several types of bar graphs used in quality
management and data analysis, including:
– Clustered Bar Graphs: Display multiple bars for each category side by side,
allowing for direct comparison between groups.
– Stacked Bar Graphs: Represent different subcategories within each group by
stacking bars on top of each other, showing both the total and the
breakdown of each group's composition.
– Grouped Bar Graphs: Combine clustered and stacked bar graph formats to
compare multiple variables across different categories simultaneously.
Reporting Measurement Data for
Performance Assessment
Bar Graphs:
5. Interpretation and Analysis: Effective interpretation of bar graphs involves
analyzing the relative heights or lengths of the bars to identify patterns,
trends, or relationships within the data. Practitioners should pay attention to
differences in bar heights, examine the distribution of values across
categories, and consider factors influencing the observed patterns. Statistical
analysis techniques, such as calculating proportions, percentages, or
averages, may be applied to further analyze and interpret the data.
6. Communication and Reporting: Bar graphs are widely used for presenting
categorical data in reports, presentations, or visualizations. They offer a clear
and intuitive way to communicate complex information to stakeholders,
making it easier to understand and interpret key insights. Bar graphs are
often accompanied by descriptive labels, titles, and legends to provide
context and facilitate interpretation, ensuring that the intended message is
effectively conveyed to the audience.
Reporting Measurement Data for
Performance Assessment
Bar Graphs:

Vertical Bar Graph

comparing computer
response times at
four hospitals during
one period

Dr. Katia Saliba –CLAS 359 Quality in Industries

Reporting Measurement Data for
Performance Assessment
Bar Graphs:

Horizontal Bar Graph

showing number of
patient falls in each
hospital unit,
January–March

Dr. Katia Saliba –CLAS 359 Quality in Industries

Reporting Measurement Data for
Performance Assessment
Bar Graphs:

Horizontal Clustered
Bar Graph showing
home health agency
performance
measures

Dr. Katia Saliba –CLAS 359 Quality in Industries

Reporting Measurement Data for
Performance Assessment
Bar Graphs:

Vertical Bar Graph

showing timeliness of
home health service
delivery by day of the
week

Dr. Katia Saliba –CLAS 359 Quality in Industries

Reporting Measurement Data for
Performance Assessment
Histograms:
• A histogram is a graphical representation of the frequency
distribution of continuous data.
• It consists of a series of contiguous rectangles (bars) where the
width of each bar represents the interval or range of values, and
the height represents the frequency or count of data points
falling within that interval.
• Histograms are commonly used in statistical analysis to visualize
the distribution of data and identify patterns, trends, or outliers.
• They provide insights into the shape, central tendency, and
variability of the data, making them valuable tools for exploratory
data analysis and decision-making.
• Their added-value can be summarize as follows:
Reporting Measurement Data for
Performance Assessment
Histograms:
1. Frequency Distribution: Histograms display the frequency
distribution of data, showing how values are distributed across
different intervals or bins. The horizontal axis (x-axis) represents
the range of values, divided into intervals or bins, while the
vertical axis (y-axis) represents the frequency or count of data
points falling within each interval.
2. Rectangular Bars: Each interval or bin in a histogram is
represented by a rectangular bar. The width of the bar
corresponds to the width of the interval, while the height
represents the frequency of data points within that interval. The
area of each bar is proportional to the frequency, providing a
visual indication of the relative occurrence of different values.
Reporting Measurement Data for
Performance Assessment
Histograms:
3. Shape of Distribution: The shape of a histogram provides
insights into the underlying distribution of the data. Common
shapes include:
– Symmetrical (Normal) Distribution: In a normal distribution, data
points are symmetrically distributed around the mean, resulting in a
bell-shaped curve.
– Skewed Distribution: Skewed distributions have asymmetric shapes,
with data points clustered more towards one end of the range than
the other. Positive skewness indicates a tail towards higher values,
while negative skewness indicates a tail towards lower values.
– Bimodal or Multimodal Distribution: Bimodal or multimodal
distributions have multiple peaks or modes, indicating distinct
subgroups or patterns within the data.
Reporting Measurement Data for
Performance Assessment
Histograms:
4. Central Tendency and Dispersion: Histograms provide insights into
the central tendency and dispersion of the data. The central
tendency is indicated by the peak or highest point of the histogram,
which corresponds to the mode or most frequently occurring value.
The spread or dispersion of the data is reflected in the width and
shape of the distribution, with wider distributions indicating greater
variability.
5. Identifying Patterns and Outliers: Histograms help identify
patterns, trends, and outliers within the data. Outliers, or data
points that significantly deviate from the rest of the distribution,
may appear as isolated bars or spikes in the histogram, warranting
further investigation to determine their cause and significance.
Reporting Measurement Data for
Performance Assessment
Histograms:
6. Interpretation and Analysis: Effective interpretation of
histograms involves analyzing the shape, central tendency, and
dispersion of the distribution, as well as identifying any notable
patterns or outliers. Histograms are often accompanied by
descriptive statistics, such as measures of central tendency
(mean, median, mode) and measures of dispersion (range,
standard deviation), to provide additional context and insights
into the data.
Reporting Measurement Data for
Performance Assessment
Histograms:

Histogram
of clinic
wait times

Dr. Katia Saliba –CLAS 359 Quality in Industries

Reporting Measurement Data for
Performance Assessment
Histograms:
Reporting Measurement Data for
Performance Assessment
Pie Charts:
• Pie charts are circular graphical representations commonly
used to illustrate the proportional distribution of
categorical data.
• Their added-value can be summarized as follows:
Reporting Measurement Data for
Performance Assessment
Pie Charts:
1. Proportional Representation: Pie charts divide a circle into
sectors, with each sector representing a category or group of
data. The size of each sector is proportional to the relative
frequency, proportion, or percentage of data points belonging to
that category. The entire circle represents the total dataset, and
each sector's size corresponds to its share of the whole.
2. Categorical Data Visualization: Pie charts are ideal for
visualizing categorical data, where each category is distinct and
non-overlapping. Common uses of pie charts include displaying
market share, budget allocations, demographic distributions,
and survey responses categorized into mutually exclusive
groups.
Reporting Measurement Data for
Performance Assessment
Pie Charts:
3. Comparison of Proportions: Pie charts facilitate comparison
between different categories or groups based on their relative sizes.
Practitioners can easily identify which categories dominate or
contribute the most to the total, as well as discern smaller or less
significant categories. This visual comparison helps highlight trends,
patterns, or disparities within the dataset.
4. Single Dataset Representation: Pie charts are most effective when
representing a single dataset with a limited number of categories.
They provide a clear and intuitive overview of the distribution of
data, making it easy for viewers to grasp the relative proportions of
different categories at a glance. However, pie charts may become
cluttered and difficult to interpret when representing multiple
datasets or too many categories.
Reporting Measurement Data for
Performance Assessment
Pie Charts:
5. Limitations and Considerations: While pie charts are useful for
visualizing proportions, they have some limitations. For instance,
accurately comparing sector sizes becomes challenging when
dealing with small differences in proportions or when there are too
many categories. Additionally, pie charts do not effectively convey
changes over time or relationships between variables, making them
less suitable for certain types of data analysis.
6. Labeling and Annotation: Effective use of labels and annotations is
essential for interpreting pie charts accurately. Each sector should
be labeled with the corresponding category name and percentage
or proportion to provide context and aid interpretation. Additional
annotations, such as legends or data labels, may be included to
clarify the meaning of the chart and highlight key insights.
Reporting Measurement Data for
Performance Assessment
Pie Charts:

Pie Chart showing top

five patient
complaints and
percentage of
patients citing each as
their top complaint

Dr. Katia Saliba –CLAS 359 Quality in Industries

Reporting Measurement Data for
Performance Assessment
Scatter Diagrams:
• Scatter diagrams, also known as scatter plots, are graphical
representations used to display the relationship between
two continuous variables.
• Their added-value can be summarized as follows:
Reporting Measurement Data for
Performance Assessment
Scatter Diagrams:
1. Visualizing Relationships: Scatter diagrams plot individual data
points on a two-dimensional graph, with one variable represented
on the horizontal axis (x-axis) and the other variable on the vertical
axis (y-axis). Each data point represents the value of both variables,
allowing practitioners to visualize the relationship between them.
2. Identifying Patterns and Trends: Scatter diagrams help identify
patterns, trends, or relationships between variables. Depending on
the pattern observed, scatter diagrams can reveal positive
relationships (as one variable increases, the other variable also
increases), negative relationships (as one variable increases, the
other variable decreases), or no apparent relationship (random
distribution of data points).
Reporting Measurement Data for
Performance Assessment
Scatter Diagrams:
3. Correlation Analysis: Scatter diagrams are commonly used to assess the
strength and direction of correlation between two variables. Correlation
coefficients, such as Pearson's correlation coefficient or Spearman's rank
correlation coefficient, quantify the degree of linear relationship
between variables. A correlation coefficient close to +1 indicates a
strong positive correlation, a coefficient close to -1 indicates a strong
negative correlation, and a coefficient close to 0 indicates no linear
correlation.
4. Outlier Detection: Scatter diagrams help identify outliers or anomalous
data points that deviate significantly from the overall pattern. Outliers
may indicate errors in data collection, measurement variability, or the
presence of unusual phenomena. Detecting outliers is important for
assessing the validity and reliability of the data and may prompt further
investigation or data validation.
Reporting Measurement Data for
Performance Assessment
Scatter Diagrams:
5. Visualization of Clusters: In addition to identifying relationships
between variables, scatter diagrams can reveal clusters or groupings of
data points. Clustering may indicate subgroups or patterns within the
data that merit further exploration. Techniques such as clustering
algorithms or density-based analysis can be applied to identify and
characterize clusters more systematically.
6. Prediction and Forecasting: Scatter diagrams can be used in predictive
modeling and forecasting to visualize relationships between predictor
variables and outcomes. By examining the scatter plot, practitioners can
assess the strength and direction of the relationship and determine
whether a predictive model is appropriate for the data. Regression
analysis and other statistical techniques may be employed to develop
predictive models based on the observed relationship.
Reporting Measurement Data for
Performance Assessment
Scatter Diagrams:

Scatter Diagram
Relationship
Patterns

Dr. Katia Saliba –CLAS 359 Quality in Industries

Reporting Measurement Data for
Performance Assessment
Scatter Diagrams:

Scatter Diagram
showing relationship
between two
variables: Computer
response time and
number of users
connected

Dr. Katia Saliba –CLAS 359 Quality in Industries

Reporting Measurement Data for
Performance Assessment
Pareto Charts:
• Pareto charts are similar to bar graphs, except that they sort
performance data in order of decreasing frequency and include notation
of other factors to highlight the Pareto Principle.
• The Pareto Principle, named after the nineteenth-century Italian
economist Vilfredo Pareto, states that for many events, 80 percent of the
results come from 20 percent of the inputs.
• Joseph Juran, an originator of the science of quality, applied the Pareto
Principle to quality management.
• Juran advised management to concentrate improvement efforts on the
“vital few” sources of problems and not be distracted by those of lesser
importance.
• Pareto charts, then, are used to identify the 20 percent—the vital few—
of the problems affecting 80 percent of performance.

Dr. Katia Saliba –CLAS 359 Quality in Industries

Reporting Measurement Data for
Performance Assessment
Pareto Charts:
• Special types of bar graphs that display the most frequent
problem as the first bar, the next most frequent as the next
bar, and so on; also called Pareto diagrams.
• Pareto Principle
• Originally, the Pareto Principle referred to the observation
that 80 percent of Italy’s wealth belonged to only 20
percent of the population. The principle conveys the notion
that the majority of results come from a minority of inputs
(an 80/20 rule of thumb).

Dr. Katia Saliba –CLAS 359 Quality in Industries

Reporting Measurement Data for
Performance Assessment
Pareto Charts:
• To illustrate how a Pareto chart is used for quality
assessment purposes, consider the following situation:
– Community Hospital starts a new practice intended to reduce
problems related to patient misidentification.
– At the time of registration, patients scheduled for outpatient
diagnostic tests now are given an identification (ID) wristband on
which their name, birth date, and record number are printed.
– Technicians in outpatient testing areas use the ID band information
to positively identify patients before performing a test.
– Formerly, only patients admitted to the hospital received an ID
band.

Dr. Katia Saliba –CLAS 359 Quality in Industries

Reporting Measurement Data for
Performance Assessment
Pareto Charts:
– Shortly after the new process is implemented, staff members in the
outpatient registration area begin to complain about it.
– Some employees say the ink on the bands smears easily.
– Others say the bands are not well made and do not always fasten
securely around the patient’s wrist.
– Rather than react to random complaints, the manager of outpatient
registration gathers additional information to thoroughly evaluate
the situation.
– The manager asks employees to report ID band problems each time
one occurs.
– At the end of 30 days, the manager records the data and creates a
Pareto chart.

Dr. Katia Saliba –CLAS 359 Quality in Industries

Reporting Measurement Data for
Performance Assessment
Pareto Charts:

Dr. Katia Saliba –CLAS 359 Quality in Industries

Reporting Measurement Data for
Performance Assessment
Pareto Charts:
• The manager concludes from these data that three main problems are
triggering the complaints:
– the fasteners do not hold,
– the space provided for patient’s identifying information is too small, and
– the unit has too few large-sized bands on hand.
• A different brand of wristband—one that fastens better and has more
space for the patient’s identifying information—solves two of the
problems.
• The third problem—insufficient inventory of large bands—would be
solved by keeping more large bands in stock to accommodate larger
patients.
• If these problems (20 percent of total problems, or the “vital few”) are
resolved, complaints about ID bands should decrease by more than 80
percent.
Dr. Katia Saliba –CLAS 359 Quality in Industries
Reporting Measurement Data for
Performance Assessment
Pareto Charts:
• When considering the use of Pareto charts, keep the following in
mind:
– Use Pareto charts to separate the few major problems (the vital few)
from the many possible problems (the trivial many). Pareto charts
encourage use of data, not perception, to determine which
problems are most important.
– Arrange performance categories or problems according to their
frequency (how many), not their classification (what kind). The
order should descend from left to right.
– The right vertical axis can be used to measure the percentage of
total occurrences in each category, but in some situations, the main
problems may be apparent without adding a cumulative percentage
trend line.

Dr. Katia Saliba –CLAS 359 Quality in Industries

Reporting Measurement Data for
Performance Assessment
Radar Charts:
• Radar charts are used to plot five to ten performance measures
for an interval of time, along with performance expectations.
• Radar charts are Graphs used to display the differences between
actual and expected performance for several measures; also
called spider charts or spider diagrams because of their shape.
• Printing these lines in different colors helps the audience discern
actual versus expected performance.

Dr. Katia Saliba –CLAS 359 Quality in Industries

Reporting Measurement Data for
Performance Assessment
Radar Charts:
• When considering the use of radar charts, keep the following in
mind:
1. Radar charts show areas of relative strength and weakness and
depict overall performance.
2. In a radar chart, a point close to the center on any axis indicates a
low value. A point near the edge is a high value.
3. When interpreting a radar chart, check each axis as well as the
overall shape to determine
• The following exhibit is a radar chart showing patient satisfaction survey
results for a healthcare system.
• The heavy solid line represents the actual results, and the dotted line
represents the expected performance or target rates.

Dr. Katia Saliba –CLAS 359 Quality in Industries

Reporting Measurement Data for
Performance Assessment
Radar Charts:

Radar Chart
showing patient
satisfaction
survey results

Dr. Katia Saliba –CLAS 359 Quality in Industries

Reporting Measurement Data for
Performance Assessment
Types of Measurement Data Reporting:
3. Tabular Presentation:
– Tabular presentation involves organizing measurement data
in tables or matrices to facilitate comparison, analysis, and
interpretation.
– Tables can display raw data, summary statistics, or
aggregated results, providing a detailed breakdown of
performance indicators by category, time period, or other
relevant factors.
– Tabular presentation allows for efficient data retrieval,
manipulation, and visualization, supporting in-depth analysis
and decision-making.
Reporting Measurement Data for
Performance Assessment
Types of Measurement Data Reporting:
3. Tabular Presentation:
Reporting Measurement Data for
Performance Assessment
Types of Measurement Data Reporting:
3. Tabular Presentation:

Tabular Report of
Onetime Patient
Satisfaction
Survey Results

Dr. Katia Saliba –CLAS 359 Quality in Industries

Reporting Measurement Data for
Performance Assessment
Types of Measurement Data Reporting:
3. Tabular Presentation:

Tabular Report of
Home Health Agency
Performance Results
for Four Quarters

Dr. Katia Saliba –CLAS 359 Quality in Industries

Reporting Measurement Data for
Performance Assessment
Benefits of Effective Data Reporting:
• Enhanced Understanding: Clear and concise reporting of
measurement data improves stakeholders' understanding of
performance indicators and trends.
• Informed Decision-Making: Accessible and well-presented data
reports support informed decision-making and performance
improvement efforts.
• Communication and Transparency: Transparent and comprehensive
data reporting promotes communication and accountability among
stakeholders, fostering trust and collaboration.
• Continuous Improvement: Regular monitoring and reporting of
measurement data enable ongoing performance evaluation and
continuous improvement in laboratory operations.
 Statistical Process Control
• Statistical Process Control (SPC) is a key methodology
in quality management that utilizes statistical
techniques to monitor and control processes to ensure
they operate efficiently and produce products or
services that meet quality standards consistently.
• Here's an elaboration on SPC in quality management:
 Statistical Process Control
1. Monitoring Variation: SPC focuses on understanding and managing
variation within processes. It recognizes that all processes exhibit some
level of natural variation, but excessive variation can lead to defects or
inconsistencies in output. By monitoring variation over time, SPC helps
distinguish between common cause variation (inherent to the process)
and special cause variation (due to external factors or anomalies).
2. Control Charts: One of the primary tools used in SPC is the control
chart. Control charts graphically display process data over time and
include upper and lower control limits based on statistical analysis.
Data points falling within these control limits represent common cause
variation, while points beyond the limits indicate special cause
variation. Control charts enable practitioners to identify trends, shifts,
or abnormalities in the process, allowing for timely intervention and
corrective action.
 Statistical Process Control
3. Key Metrics: SPC typically focuses on key quality characteristics or
metrics relevant to the process being monitored. These metrics could
include dimensions of a manufactured part, chemical concentrations in a
production process, or wait times in a service delivery process. By
measuring and analyzing these metrics using statistical techniques, SPC
helps ensure that processes remain within specified tolerances and
produce outputs that meet customer requirements.
4. Process Improvement: SPC is not just about monitoring and maintaining
control; it also serves as a foundation for process improvement. By
identifying patterns or trends in process data, SPC can highlight areas for
optimization or enhancement. For example, if a control chart indicates a
consistent upward trend in defect rates, it may signal the need for
process redesign, equipment maintenance, or additional training for
personnel to address underlying issues.
 Statistical Process Control
5. Continuous Monitoring: SPC emphasizes the importance of continuous
monitoring and adjustment of processes to maintain control and
improve quality. Rather than relying solely on periodic inspections or
audits, SPC advocates for real-time data collection and analysis to detect
deviations from the norm promptly. This proactive approach helps
prevent defects or quality failures before they occur, leading to higher
levels of customer satisfaction and operational efficiency.
6. Cross-Functional Collaboration: Successful implementation of SPC often
requires collaboration across different functions within an organization.
Quality professionals, engineers, operators, and other stakeholders work
together to collect, analyze, and interpret process data effectively. This
interdisciplinary approach ensures that SPC efforts are aligned with
broader organizational goals and objectives, fostering a culture of
continuous improvement and quality excellence.
 Statistical Process Control
SPC tools:
1. Control Charts: Control charts are graphical
representations of process data over time. They typically
include a centerline representing the process mean and
upper and lower control limits based on statistical
analysis. Common types of control charts include:
– X-Bar and R Charts: Used for monitoring the central tendency
(mean) and dispersion (range) of process variables.
– Individual and Moving Range (I-MR) Charts: Suitable for monitoring
processes with small sample sizes or individual data points.
 Statistical Process Control
SPC tools:
2. Histograms: Histograms display the frequency distribution of
process data, providing insights into the spread and shape of
data distributions. They help identify patterns, trends, and
outliers in process performance.
3. Pareto Charts: Pareto charts prioritize problems or causes based
on their frequency or impact. They help focus improvement
efforts on the most significant issues by identifying the "vital
few" from the "trivial many.“
4. Scatter Diagrams: Scatter diagrams visualize the relationship
between two variables, such as input and output parameters.
They help identify correlations, patterns, or trends in process
data and assess the strength and direction of relationships.
 Statistical Process Control
SPC tools:
5. Cause-and-Effect Diagrams (Fishbone Diagrams): Cause-and-
effect diagrams identify potential causes or factors contributing
to process variations or defects. They organize causes into
categories (e.g., people, process, equipment, materials) to
facilitate problem-solving and root cause analysis.
6. Run Charts: Run charts display process data over time without
statistical control limits. They help visualize trends, shifts, or
patterns in process performance and serve as a precursor to
control chart analysis.
 Statistical Process Control
SPC tools:
7. Scatter Plots: Scatter plots are graphical representations of
paired data points, typically used to assess the relationship
between two variables. They help identify correlations, outliers,
or clusters in process data and guide decision-making.
8. Box-and-Whisker Plots: Box-and-whisker plots summarize the
distribution of process data, including measures of central
tendency and dispersion (e.g., median, quartiles, range). They
provide a visual representation of variability and help compare
data sets or groups.
 Statistical Process Control
• SPC techniques can be applied to data displayed in a line graph
without calculating upper and lower limits of the normal range.
• Only the average, or mean ɥ, of the data is calculated, and it is
displayed as a Center Line CL on the graph.
• Ideally, the Line Graph has a minimum of 15 data points; some
statisticians suggest a minimum of 20 data points.
• Suppose that every day you plot on a Line Graph the number of
minutes you take to run five Km.
• After a 30-day period, your daily run times vary but likely remain
in a predictable range (some variation is expected in any
process).

Dr. Katia Saliba –CLAS 359 Quality in Industries

 Statistical Process Control
• When you plot the current day’s time on the graph, you can see
whether the time lies in the normal range.
• The upper (UCL) and lower limits (LCL) of your run time norm are
derived from the statistical theory of normal distribution
(discussed later).
• As soon as the UCL and LCL are determined, the Line Graph
becomes Control Chart.
• But how to determine the UCL and LCL, if CL is the mean ɥ or
average?

Dr. Katia Saliba –CLAS 359 Quality in Industries

 Statistical Process Control
• Suppose that every day you plot on a line graph the number of
minutes you take to run five Km.
• After a 30-day period, your daily run times vary but likely remain
in a predictable range (some variation is expected in any
process).
• At what point is your run time significantly different from the
norm?
• To answer this question, you use data from the past 30 days to
calculate the upper and lower limits of your run time norm.
• When you plot the current day’s time on the graph, you can see
whether the time lies in the normal range.
• The upper and lower limits of your run time norm are derived
from the statistical theory of normal distribution.
Dr. Katia Saliba –CLAS 359 Quality in Industries
 Statistical Process Control
• The following is a control chart showing your hypothetical three-mile
run times for a 30-day period.
• The run times for each day are different, but these differences are
normal process variation (common cause variation) because the
times are within the statistically calculated upper and lower control
limits.
• Thus, according to the data shown below, your performance is in a
state of statistical control, meaning your performance is stable and
will likely remain within the control limits unless some aspect of the
running process changes.
• When performance data are displayed on a control chart with
statistically calculated upper and lower control limits, the type of
variation (common cause or special cause) prompting the changes in
performance is easy to determine.

Dr. Katia Saliba –CLAS 359 Quality in Industries

Statistical Process Control

Dr. Katia Saliba –CLAS 359 Quality in Industries

 Statistical Process Control
Normal Distribution statistical theory
• About 68 percent of values drawn from a normal distribution are
within one standard deviation 1SD of the mean ɥ(average),
• about 95 percent of the values are within two standard
deviations (2SD),
• and about 99 percent lie within three standard deviations (3SD).
• If the upper and lower limits (UCL & LCL) of your normal run
time are set at three standard deviations (3SD) from the mean
(ɥ), you have little chance of registering a run time outside of
these parameters.

Dr. Katia Saliba –CLAS 359 Quality in Industries

 Statistical Process Control
Upper Control Limit: The upper
boundary below which data plotted
on a control chart can vary without
the need for change or correction.

Lower control limit: The lower

boundary above which data plotted
on a control chart can vary without
the need for change or correction.

Dr. Katia Saliba –CLAS 359 Quality in Industries

 Statistical Process Control
At what point is your run time significantly different from the norm?
• To answer this question, you use data from the past 30 days to
calculate the upper and lower limits of your run time norm.
• If your times remain stable (always lie in the normal range), your
running performance is in a state of statistical control.
• The only way you can achieve better run times is to change a
fundamental step in the process (e.g., run a different route, wear
new shoes for your run).
• Suppose one day your run time is outside the limits of your norm.
• Because these limits have been statistically calculated on the basis of
your past performance, you know that something unusual occurred.
• You will want to identify and correct the cause of the longer time.

Dr. Katia Saliba –CLAS 359 Quality in Industries

 Statistical Process Control
Shifts, Trends and Rules Reading in a Line Graph or Control
Charts
• Ideally, the line graph has a minimum of 15 data points; some
statisticians suggest a minimum of 20 data points.
• Performance results plotted on the graph are compared with the
Center Line to locate significant performance shifts or trends.
• A shift or trend represents potentially unstable performance that
needs to be investigated.

Dr. Katia Saliba –CLAS 359 Quality in Industries

 Statistical Process Control
Trend
• A significant performance trend is evident when one of the
following situations occurs:
– Eight consecutive data points move steadily upward or
downward on a line graph that shows 20 or more data points
(points may fall on or cross the center line).
Shift
• A significant shift in performance is evident when the
following situations occurs:
– Eight consecutive data points appear above or below the
Center Line on a line graph that shows 20 or more data
points (ignore data points that fall on the center line).

Dr. Katia Saliba –CLAS 359 Quality in Industries

Statistical Process Control

Dr. Katia Saliba –CLAS 359 Quality in Industries

 Interpreting Healthcare
Performance Measurement Data
Data Analysis Techniques:
1. Trend Analysis:
– Trend analysis involves analyzing performance data over time
to identify patterns, changes, and trends.
– By examining data trends, healthcare organizations can
assess whether performance is improving, deteriorating, or
remaining stable over time.
– Trend analysis helps identify areas for further investigation or
intervention and supports evidence-based decision-making.
 Interpreting Healthcare
Performance Measurement Data
Data Analysis Techniques:
1. Trend Analysis:
 Interpreting Healthcare
Performance Measurement Data
Data Analysis Techniques:
2. Variance Analysis:
– Variance analysis compares actual performance against
expected or target performance to identify deviations or
variances.
– Positive variances indicate that actual performance exceeds
expectations, while negative variances indicate
underperformance.
– Variance analysis helps identify root causes of performance
discrepancies and informs corrective actions to address
performance gaps.
 Interpreting Healthcare
Performance Measurement Data
Data Analysis Techniques:
3. Root Cause Analysis:
– Root cause analysis (RCA) is a systematic process for
identifying underlying causes of performance issues or
failures.
– RCA involves identifying contributing factors, analyzing their
interactions, and determining the primary causes of
performance problems.
– By addressing root causes, healthcare organizations can
implement targeted interventions to prevent recurrence and
improve performance.
 Interpreting Healthcare
Performance Measurement Data
Data Analysis Techniques:
3. Root Cause Analysis:
 Interpreting Healthcare
Performance Measurement Data
Benefits of Effective Data Interpretation:
• Informed Decision-Making: Effective interpretation of
performance data provides insights for informed decision-
making and strategic planning.
• Performance Improvement: Identifying performance
trends, variances, and root causes enables targeted
interventions to improve performance outcomes.
• Continuous Learning: Data interpretation fosters a culture
of continuous learning and improvement within healthcare
organizations, driving quality enhancement and patient
safety initiatives.
 Role of Performance Targets in
Evaluating Performance
Definition and Purpose of Performance Targets:
• Performance targets are specific, measurable objectives set
by organizations to guide and assess performance
improvement efforts.
• The purpose of performance targets is to provide clear
benchmarks or goals for performance outcomes, against
which actual performance can be compared and evaluated.
• Performance targets help organizations align their efforts
with strategic objectives, prioritize activities, and monitor
progress towards desired outcomes.
 Role of Performance Targets in
Evaluating Performance
Setting and Monitoring Performance Targets:
• Techniques for establishing realistic and achievable
performance targets involve:
– Baseline Assessment: Conducting a thorough assessment of
current performance levels to establish a starting point for
improvement efforts.
– Benchmarking: Comparing performance against industry
standards, best practices, or peer organizations to set
aspirational targets.
– Stakeholder Consultation: Engaging stakeholders, including
employees, management, and external partners, to ensure
alignment of targets with organizational goals and
expectations.
 Role of Performance Targets in
Evaluating Performance
Setting and Monitoring Performance Targets:
• Once performance targets are set, organizations must
establish mechanisms for monitoring progress towards
these targets:
– Performance Tracking: Implementing systems and processes
to track and monitor performance indicators regularly.
– Performance Reviews: Conducting periodic reviews to assess
progress towards targets, identify barriers or challenges, and
make necessary adjustments to strategies and action plans.
– Performance Reporting: Communicating performance results
transparently to stakeholders, including leadership, staff, and
external stakeholders, to promote accountability and drive
continuous improvement.
 Role of Performance Targets in
Evaluating Performance
Importance of Performance Targets in Evaluating
Performance:
• Clear Direction: Performance targets provide clear direction and
focus for performance improvement efforts, guiding organizations
towards desired outcomes.
• Accountability: Setting specific performance targets holds individuals
and teams accountable for achieving results and meeting
organizational expectations.
• Measurement: Performance targets serve as measurable
benchmarks for assessing performance, enabling organizations to
track progress and evaluate success.
• Motivation and Engagement: Clear and achievable performance
targets motivate employees, enhance engagement, and foster a
culture of accountability and continuous improvement.
 Establishing Performance
Expectations
Common Techniques for Establishing Performance
Expectations:
1. Benchmarking:
– Benchmarking involves comparing performance metrics and
practices against industry standards, best practices, or peer
organizations.
– By benchmarking performance against external benchmarks,
organizations can identify areas of strength and opportunities
for improvement.
– Benchmarking helps set realistic and aspirational
performance expectations based on the achievements of top-
performing organizations.
 Establishing Performance
Expectations
Common Techniques for Establishing Performance
Expectations:
2. Expert Judgment:
– Expert judgment involves seeking input from subject matter
experts, such as experienced professionals, leaders, or
consultants, to establish performance expectations.
– Experts provide insights, recommendations, and perspectives
based on their knowledge, experience, and expertise in the
field.
– Expert judgment ensures that performance expectations are
informed by industry expertise and aligned with
organizational goals and priorities.
 Establishing Performance
Expectations
Common Techniques for Establishing Performance
Expectations:
3. Stakeholder Input:
– Stakeholder input involves soliciting feedback and
perspectives from stakeholders, including employees,
customers, patients, and community members.
– By involving stakeholders in the performance expectation-
setting process, organizations ensure that expectations are
relevant, meaningful, and reflective of stakeholder needs and
preferences.
– Stakeholder input promotes buy-in, ownership, and
accountability for achieving performance goals and
outcomes.
 Establishing Performance
Expectations
Benefits of Establishing Performance Expectations:
• Alignment: Establishing clear performance expectations ensures
alignment with organizational goals, mission, and values.
• Motivation: Clearly defined expectations motivate employees,
teams, and stakeholders to strive for excellence and achieve
desired outcomes.
• Accountability: Performance expectations hold individuals and
teams accountable for delivering results and meeting
organizational standards.
• Continuous Improvement: Performance expectations provide a
framework for monitoring progress, identifying areas for
improvement, and driving continuous learning and innovation.
 Comparative Performance Data
for Assessment Purposes
Definition and Purpose:
• Comparative performance data refers to data that allows for
comparison of performance metrics across different entities,
such as organizations, departments, or time periods.
• The primary purpose of using comparative performance data is
to assess performance relative to peers, benchmarks, or
historical performance, enabling organizations to identify
strengths, weaknesses, and opportunities for improvement.
 Comparative Performance Data
for Assessment Purposes
Types of Comparative Performance Data:
1. External Benchmarks:
– External benchmarks are performance metrics derived from
external sources, such as industry standards, best practices,
or peer organizations.
– By comparing performance against external benchmarks,
organizations can assess their relative performance standing
and identify areas where they may be lagging behind or
excelling.
 Comparative Performance Data
for Assessment Purposes
Types of Comparative Performance Data:
2. Internal Benchmarks:
– Internal benchmarks are performance metrics derived from
internal data sources, such as historical performance data or
performance targets.
– Comparing current performance against internal benchmarks
allows organizations to track progress over time, measure
performance against established goals, and identify trends
and patterns.
 Comparative Performance Data
for Assessment Purposes
Types of Comparative Performance Data:
3. Peer Comparisons:
– Peer comparisons involve comparing performance metrics
with similar entities or organizations operating in the same
industry or geographical area.
– Peer comparisons provide context and perspective on
performance relative to comparable organizations, allowing
for a more accurate assessment of performance standing and
potential areas for improvement.
 Comparative Performance Data
for Assessment Purposes
Benefits of Comparative Performance Data:
• Informative Insights: Comparative performance data provide
informative insights into performance relative to peers,
benchmarks, and historical performance, facilitating data-driven
decision-making.
• Performance Improvement: By identifying performance gaps and
opportunities for improvement, comparative performance data
enable organizations to implement targeted interventions and
quality improvement initiatives.
• Accountability: Comparing performance against external
benchmarks or peer institutions promotes accountability and
transparency, encouraging organizations to strive for excellence
and continuous improvement.
 CONCLUSION
By examining different types of measurement
data reporting, including descriptive
statistics, graphical representation, and
Data Reporting and tabular presentation, we learned how to
Interpretation interpret healthcare performance
measurement data using trend analysis,
variance analysis, and root cause analysis.

Role of Performance
Targets and Expectations

Utilization of Comparative
The role of performance targets is crucial
Performance Data in guiding performance improvement
efforts and resource allocation. Techniques
Comparative performance data is crucial for evaluating for setting and monitoring performance
performance against internal and external benchmarks. It targets emphasize the importance of
helps identify strengths, weaknesses, and opportunities for establishing realistic and achievable goals.
improvement by accurately assessing sources and methods
25 April 2024 102
of obtaining and interpreting this data.
 THANK YOU

25 April 2024 103