Post on 13-Jan-2016
Quality Assurance & Quality Control
University of New Mexico Kristin Vanderbilt William Michener James Brunt Troy Maddux
University of South Carolina Don Edwards
Instruction Materials Primary References
Michener and Brunt (2000) Ecological Data: Design, Management and Processing. Blackwell Science.
Edwards (2000) Ch. 4 Brunt (2000) Ch. 2 Michener (2000) Ch. 7
Dux, J.P. 1986. Handbook of Quality Assurance for the Analytical Chemistry Laboratory. Van Nostrand Reinhold Company
Mullins, E. 1994. Introduction to Control Charts in the Analytical Laboratory: Tutorial Review. Analyst 119: 369 – 375.
Outline:
Define QA/QC QC procedures
Designing data sheets Data entry using validation rules, filters,
lookup tables QA procedures
Graphics and Statistics Outlier detection
Samples Simple linear regression
QA/QC “mechanisms [that] are designed to prevent
the introduction of errors into a data set, a process known as data contamination”
Brunt 2000
Errors (2 types)
Commission: Incorrect or inaccurate data in a dataset
Can be easy to find Malfunctioning instrumentation
Sensor drift Low batteries Damage Animal mischief
Data entry errors
Omission Difficult or impossible to find Inadequate documentation of data values, sampling
methods, anomalies in field, human errors
Quality Control “mechanisms that are applied in advance,
with a priori knowledge to ‘control’ data quality during the data acquisition process”
Brunt 2000
Quality Assurance “mechanisms [that] can be applied after
the data have been collected, entered in a computer and analyzed to identify errors of omission and commission” graphics statistics
Brunt 2000
QA/QC Activities Defining and enforcing standards for
formats, codes, measurement units and metadata.
Checking for unusual or unreasonable patterns in data.
Checking for comparability of values between data sets.
Brunt 2000
Outline:
Define QA/QC QC procedures
Designing data sheets Data entry using validation rules, filters,
lookup tables QA procedures
Graphics and Statistics Outlier detection
Samples Simple linear regression
Flowering Plant Phenology – Data Entry Form Design
Four sites, each with 3 transects Each species will have
phenological class recorded
Plant Life Stage______________ _____________________________ _____________________________ _____________________________ _____________________________ _____________________________ _____________________________ _____________________________ _______________
What’s wrong with this data sheet?
Data Collection Form Development:
Plant Life Stageardi P/G V B FL FR M S D NParpu P/G V B FL FR M S D NPatca P/G V B FL FR M S D NPbamu P/G V B FL FR M S D NPzigr P/G V B FL FR M S D NP
P/G V B FL FR M S D NPP/G V B FL FR M S D NP
PHENOLOGY DATA SHEETCollectors:_________________________________Date:___________________ Time:_________Location: black butte, deep well, five points, goat draw
Transect: 1 2 3
Notes: _________________________________________
P/G = perennating or germinating M = dispersingV = vegetating S = senescingB = budding D = deadFL = flowering NP = not presentFR = fruiting
Outline:
Define QA/QC QC procedures
Designing data sheets Data entry using validation rules, filters,
lookup tables QA procedures
Graphics and Statistics Outlier detection
Samples Simple linear regression
Other methods for preventing data contamination
Double-keying of data by independent data entry technicians followed by computer verification for agreement
Randomly check 10% of data to calculate frequency of errors
Use text-to-speech program to read data back Filters for “illegal” data
Computer/database programs Legal range of values Sanity checks
Edwards 2000
Table ofPossibleValues
and Ranges
Raw DataFile
Illegal DataFilter
Report ofProbable
Errors
Flow of Information in Filtering “Illegal” Data
Edwards 2000
Illegal-data filter in SASData Checkum; Set all;
Message=repeat(“ ”,39);If Y1<0 or Y1>1 then do; message=“Y1 is not
on the interval [0,1]”; output; end;If Y3>Y4 then do; message=“Y3 is larger than
Y4”; output; end;…….(add as many checks as desired)If message NE repeat(“ ”, 39);Keep ID message;
Proc Print Data=Checkum;
Outline:
Define QA/QC QC procedures
Designing data sheets Data entry using validation rules, filters,
lookup tables QA procedures
Graphics and Statistics Outlier detection
Samples Simple linear regression
Identifying Sensor Errors: Comparison of data from three Met stations, Sevilleta LTER
Identification of Sensor Errors: Comparison of data from three Met stations, Sevilleta LTER
QA/QC in the Lab: Using Control Charts
Laboratory quality control using statistical process control charts:
Determine whether analytical system is “in control” by examining Mean Variability (range)
All control charts have three basic components:
a centerline, usually the mathematical average of all the samples plotted.
upper and lower statistical control limits that define the constraints of common cause variations.
performance data plotted over time.
16
18
20
22
24
26
0 2 4 6 8 10 12 14 16 18 20
Time
Mean
LCL
UCL
X-Bar Control Chart
Constructing an X-Bar control chart
Each point represents a check standard run with each group of 20 samples, for example
UCL = mean + 3*standard deviation
Things to look for in a control chart:
The point of making control charts is to look at variation, seeking patterns or statistically unusual values. Look for: 1 data point falling outside the control limits 6 or more points in a row steadily increasing
or decreasing 8 or more points in a row on one side of the
centerline 14 or more points alternating up and down
Linear trend
0
2
4
6
8
10
12
0 2 4 6 8 10 12
time
Outline:
Define QA/QC QC procedures
Designing data sheets Data entry using validation rules, filters,
lookup tables QA procedures
Graphics and Statistics Outlier detection
Samples Simple linear regression
Outliers An outlier is “an unusually extreme value
for a variable, given the statistical model in use”
The goal of QA is NOT to eliminate outliers! Rather, we wish to detect unusually extreme values.
Edwards 2000
Outlier Detection
“the detection of outliers is an intermediate step in the elimination of [data] contamination” Attempt to determine if contamination is
responsible and, if so, flag the contaminated value.
If not, formally analyse with and without “outlier(s)” and see if results differ.
Edwards 2000
Methods for Detecting Outliers Graphics
Scatter plots Box plots Histograms Normal probability plots
Formal statistical methods Grubbs’ test
Edwards 2000
X-Y scatter plots of gopher tortoise morphometrics
Michener 2000
Example of exploratory data analysis using SAS Insight®Michener 2000
Box Plot Interpretation
Upper quartileMedian
Lower quartile
Upper adjacent value
Pts. > upper adjacent value
Lower adjacent valuePts. < lower adjacent value
Inter-quartile range
Box Plot Interpretation
Inter-quartile range
IQR = Q(75%) – Q(25%)
Upper adjacent value = largest observation < (Q(75%) + (1.5 X IQR))
Lower adjacent value = smallest observation > (Q(25%) - (1.5 X IQR))
Box Plots Depicting Statistical Distribution of Soil Temperature
Statistical tests for outliers assume that the data are normally distributed….
CHECK THIS ASSUMPTION!
Y
-3 -2 -1 0 1 2 3
0.0
0.1
0.2
0.3
0.4
a. The Normal Frequency Curve
Y
-3 -2 -1 0 1 2 3
0.0
0.2
0.4
0.6
0.8
1.0
b. Cumulative Normal Curve Areas
Normal density and Cumulative Distribution Functions
Edwards 2000
Quantiles of Standard Normal
Y
-2 -1 0 1 2
78
910
1112
Normal Plot of 30 Observations from a Normal Distribution
Edwards 2000
Quantiles of Standard Normal
Y
-2 -1 0 1 2
01
23
4
a. a right skewed distribution
Quantiles of Standard Normal
Y
-2 -1 0 1 2
0.0
1.0
2.0
3.0
b. a left-truncated Normal distribution
Quantiles of Standard Normal
Y
-2 -1 0 1 2
-50
5
c. a heavy-tailed distribution
Quantiles of Standard Normal
Y
-2 -1 0 1 22
46
810
12
14
16
d. a contaminated Normal distribution
Edwards 2000
Normal Plots from Non-normally Distributed Data
Grubbs’ Text is a Statistical Test to determine if a point is an outlier.
Grubbs’ test for outlier detection:
Tn = (Yn – Ybar)/S
where Yn is the possible outlier,
Ybar is the mean of the sample, and
S is the standard deviation of the sample
Contamination exists if Tn is greater than T.01[n]
Example of Grubbs’ test for outliers: rainfall in acre-feet from seeded clouds (Simpson et al. 1975)
4.1 7.7 17.5 31.432.7 40.6 92.4 115.3118.3 119.0 129.6 198.6200.7 242.5 255.0 274.7274.7 302.8 334.1 430.0489.1 703.4 978.0 1656.01697.8 2745.6T26 = 3.539 > 3.029; Contaminated
Edwards 2000But Grubbs’ test is sensitive to non-normality……
0 500 1500 2500
05
10
15
20
rainfall
a. rainfall
Quantiles of Standard Normal
rain
fall
-2 -1 0 1 2
0500
1500
2500
b. Normal plot
0.5 1.5 2.5 3.5
02
46
810
log10(rainfall)
c. log10(rainfall)
Quantiles of Standard Normal
log10(r
ain
fall)
-2 -1 0 1 2
0.5
1.5
2.5
3.5
d. Normal plot
Edwards 2000
Checking Assumptions on Rainfall Data
Contaminated
Normallydistributed
Simple Linear Regression:check for model-based……
Outliers Influential (leverage) points
Influential points in simple linear regression:
A “leverage” point is a point with an unusual regressor value that has more weight in determining regression coefficients than the other data values.
Edmonds 2000
x
y
0 10 20 30 40 50
50
100
150
outlier andleverage pt
leverage pt
outlier
Edwards 2000
Influential Data Points in a Simple Linear Regression
x
y
0 10 20 30 40 50
50
100
150
outlier andleverage pt
leverage pt
outlier
Edwards 2000
Influential Data Points in a Simple Linear Regression
x
y
0 10 20 30 40 50
50
100
150
outlier andleverage pt
leverage pt
outlier
Edwards 2000
Influential Data Points in a Simple Linear Regression
x
y
0 10 20 30 40 50
50
100
150
outlier andleverage pt
leverage pt
outlier
Edwards 2000
Influential Data Points in a Simple Linear Regression
body weight (kg)
bra
in w
eig
ht (g
)
0 2000 4000 6000
01000
2000
3000
4000
5000
African Elephant
Asian Elephant
Man
Edwards 2000
Brain weight vs. body weight, 63 species of terrestrial mammals
Leverage pts.
“Outliers”
log10 body weight (kg)
log10 b
rain
weig
ht (g
)
-2 -1 0 1 2 3 4
-10
12
3
Elephants
Man
Chinchilla
mispunched point
Edwards 2000
Logged brain weight vs. logged body weight
“Outliers”
Outliers in simple linear regression
0
50
100
150
200
250
0 50 100 150 200 250 300 350 400 450
Beta-Glucosidase
Ph
os
ph
ata
se
Observation 62
Outliers: identify using studentized residuals Contamination may exist if
|ri| > t /2, n-3
= 0.01
Simple linear regression:Outlier identification
n = 86
t/2,83 = 1.98
Simple linear regression:detecting leverage points
hi = (1/n) + (xi – x)2/(n-1)Sx2
A point is a leverage point if hi > 4/n, where n is the number of points used to fit the regression
Regression with leverage point:Soil nitrate vs. soil moisture
Regression without leverage point
Observation 46
Output from SAS:Leverage points
n = 336
hi cutoff value: 4/336=0.012
Process from raw data to verified data to validated data (reviewed by a qualified scientist) is called data maturity, and implies increasing
confidence in the quality of the data through time
Data Quality (Confidenc
e in the Data)
Data Maturity
Raw Data
Verified Data
Validated Data