Study guide
11.2 Longitudinal Load Modeling: ACWR, EWMA, Monotony, Strain, and Change Detection
NSCA Certified Performance and Sport Scientist CPSS
Track your progress as you read
Finished sections get a check mark.
1 Introduction: CPSS Exam Overview, Eligibility, and Case-Study Strategy
1.1 CPSS Exam Format, Eligibility Pathways, and the 2026 Blueprint 1.2 Mastering Athlete Case Studies and Research Review Scenarios
2 Chapter 1: Scientific Process, Adaptation Theory, and Periodization (Domain 1)
2.1 Training Principles, Adaptation Models, and Injury-Risk Mitigation 2.2 Evaluating Performance Programs Using the Scientific Process 2.3 Periodization Paradigms, Fitness-Fatigue Models, and Tapering
3 Chapter 2: Scientific Disciplines in Athlete Preparation (Domain 1)
3.1 Exercise Physiology, Bioenergetics, and Systemic Adaptations 3.2 Applied Biomechanics, Force-Time Kinetics, and Force-Velocity Profiling 3.3 Motor Learning, Skill Acquisition, and Constraints-Led Practice Design 3.4 Performance Nutrition, Recovery Modalities, and Sport Psychology
4 Chapter 3: Technology Review, Research Appraisal, and Knowledge Translation (Domain 1)
4.1 Critically Reviewing Sport Performance Products, Technologies, and Trends 4.2 Evaluating Research Studies: Design, Validity, and Practical Relevance 4.3 Communicating Research Findings to Support Evidence-Based Practice
5 Chapter 4: Sport Demands Analysis, KPIs, and Resource Strategy (Domain 2)
5.1 Researching Biomechanical, Tactical, and Technical Sport Demands 5.2 Physiological Demands, Injury Epidemiology, and Environmental Constraints 5.3 Qualitative and Mixed-Methods Research for Sport Demands Analysis 5.4 Collaborating with Stakeholders to Establish Key Performance Indicators 5.5 Identifying Resources and Strategies for Short- and Long-Term Goals
6 Chapter 5: Profiling Benchmarks and Needs Analysis Communication (Domain 2)
6.1 Developing Normative Benchmarks: Z-Scores, T-Scores, and Percentiles 6.2 Multidimensional Athlete Profiling and Return-to-Performance Milestones 6.3 Communicating Needs Analysis Results to Multidisciplinary Stakeholders
7 Chapter 6: Assessment Ethics, Safety Standards, and Tool Psychometrics (Domain 3)
7.1 Ethical, Legal, and Privacy Considerations in Athlete Data Collection 7.2 Evaluating Assessment Environments, Equipment, and Safety Standards 7.3 Validity, Reliability (ICC, CV%, TE), and Smallest Worthwhile Change
8 Chapter 7: Applied Assessment and Load-Monitoring Systems (Domain 3)
8.1 Movement Tracking Systems: GNSS/GPS, LPS, IMUs, and Optical Tracking 8.2 Neuromuscular Testing: Force Platforms, Isometric Pulls/Pushes, and VBT 8.3 Internal Load, Autonomic Readiness (HRV), Biomarkers, and PROMs
9 Chapter 8: Quality Assurance, Protocols, and Assessment Efficacy (Domain 3)
9.1 Applying Quality Assurance Techniques in Sport Science Data Collection 9.2 Developing, Documenting, and Standardizing Data Collection Protocols 9.3 Systematically Reevaluating Assessments, Protocols, and Interventions
10 Chapter 9: Data Governance, Storage Architecture, and Cleaning (Domain 4)
10.1 Data Privacy, Security Protocols, and Protecting Organizational Information 10.2 Designing Plans for Data Collection, Storage, Analysis, and AMS Workflows 10.3 Evaluating Data Quality, Signal Integrity, Outliers, and Cleaning Procedures
11 Chapter 10: Statistical Modeling, Feedback Delivery, and Analytical Limitations (Domain 4)
11.1 Inferential Statistics, Correlation, Regression, ANOVA, and Effect Sizes 11.2 Longitudinal Load Modeling: ACWR, EWMA, Monotony, Strain, and Change Detection 11.3 Data Visualization, Dashboard Design, and Timely Stakeholder Feedback 11.4 Communicating Analytical Limitations, Bias, and Uncertainty
11.2 Longitudinal Load Modeling: ACWR, EWMA, Monotony, Strain, and Change Detection
Key Takeaways Explain This Topic AI
Foster's Training Monotony equals Mean Daily Load divided by the 7-day Standard Deviation of Daily Load; prescribing identical moderate loads every day shrinks the SD and spikes Monotony (> 2.0, a unitless ratio), whereas undulating hard and easy days expands the SD and keeps Monotony low (< 1.5).
Training Strain equals Weekly Total Load multiplied by Training Monotony, capturing the synergistic maladaptive stress of high cumulative volume combined with inadequate day-to-day recovery contrast.
In rolling-average Acute:Chronic Workload Ratio (ACWR) models, including the current 7-day acute week inside the 28-day chronic denominator creates mathematical coupling that caps the maximum possible ratio at 4.0 and generates spurious correlations.
Exponentially Weighted Moving Averages (EWMA, where lambda = 2 / [N + 1]) weight recent training loads more heavily than distant sessions (lambda = 0.25 for 7-day acute; lambda ≈ 0.069 for 28-day chronic), better reflecting Banister's physiological fitness-fatigue decay kinetics.
Individual time-series change detection relies on Statistical Process Control (Shewhart I-MR and CUSUM charts) and rolling intra-individual Z-scores paired with Smallest Worthwhile Change (SWC) and Typical Error (TE) bounds.
Last updated: October 2026
11.2 Longitudinal Load Modeling: ACWR, EWMA, Monotony, Strain, and Change Detection
Quick Answer: Evaluating weekly workload totals in isolation hides how load is distributed across the microcycle and how current stress compares to historical conditioning. Foster's Training Monotony ( Mean Daily Load / 7-Day SD \text{Mean Daily Load} / \text{7-Day SD} Mean Daily Load / 7-Day SD ) and Training Strain ( Weekly Load × Monotony \text{Weekly Load} \times \text{Monotony} Weekly Load × Monotony ) penalize unvaried schedules that lack recovery troughs. For multi-week progression, Uncoupled Rolling Averages avoid the mathematical coupling of traditional 7 : 28 7:28 7 : 28 ratios, while Exponentially Weighted Moving Averages ( EWMA \text{EWMA} EWMA , λ a = 2 / [ N + 1 ] \lambda_a = 2/[N+1] λ a = 2/ [ N + 1 ] ) model non-linear physiological decay. However, because workload ratios suffer from scaling artifacts, practitioners should pair longitudinal load tracking with Statistical Process Control ( SPC \text{SPC} SPC ) and rolling intra-individual Z -scores Z\text{-scores} Z -scores .
Foster's Training Monotony and Training Strain: Quantifying Microcycle Distribution
Developed by Carl Foster (1998), the Session Rating of Perceived Exertion ( sRPE \text{sRPE} sRPE ) method quantifies daily internal training load in Arbitrary Units ( AU \text{AU} AU ) by multiplying the athlete's post-session CR-10 RPE score by session duration in minutes ( sRPE Load = RPE × Minutes \text{sRPE Load} = \text{RPE} \times \text{Minutes} sRPE Load = RPE × Minutes ). When an athlete completes multiple sessions in one day, daily load is the sum of those sessions, and Weekly Training Load is the 7-day total ( ∑ i = 1 7 Load i \sum_{i=1}^{7} \text{Load}_i ∑ i = 1 7 Load i ).
However, two microcycles with the exact same Weekly Training Load ( 2,800 AU 2{,}800\text{ AU} 2 , 800 AU ) can induce vastly different physiological adaptations depending on day-to-day variability: Training Monotony = Mean Daily Load (7-Day Average) Standard Deviation of Daily Load (7-Day SD) \text{Training Monotony} = \frac{\text{Mean Daily Load (7-Day Average)}}{\text{Standard Deviation of Daily Load (7-Day SD)}} Training Monotony = Standard Deviation of Daily Load (7-Day SD) Mean Daily Load (7-Day Average) Training Strain = Weekly Total Training Load × Training Monotony \text{Training Strain} = \text{Weekly Total Training Load} \times \text{Training Monotony} Training Strain = Weekly Total Training Load × Training Monotony
Why Identical Moderate Days Spike Monotony and Strain
The Mathematical Mechanism: Because the 7-day Standard Deviation ( SD \text{SD} SD ) sits in the denominator of the Training Monotony equation, prescribing nearly identical moderate workouts every day causes the day-to-day SD \text{SD} SD to approach zero. Dividing the mean daily load by a tiny SD \text{SD} SD drives Training Monotony above the commonly cited risk threshold of 2.0 2.0 2.0 (Monotony is a unitless ratio).
The Undulating Solution: Alternating high-intensity/high-volume acquisition days ( MD-4 , MD-3 , and Match Day MD ) with true off days ( 0 AU 0\text{ AU} 0 AU ) and low-load regeneration/activation days ( MD+1 , MD-1 ) creates a large 7-day SD \text{SD} SD , keeping Training Monotony low ( < 1.5 < 1.5 < 1.5 ) even during high-volume blocks.
Physiological Consequence of High Strain: When high Weekly Total Load combines with high Monotony ( > 2.0 > 2.0 > 2.0 ), Training Strain spikes dramatically. Prolonged high Training Strain blunts autonomic heart rate variability ( lnRMSSD \text{lnRMSSD} lnRMSSD ), suppresses mucosal immunity (salivary secretory immunoglobulin A, sIgA \text{sIgA} sIgA ), increases upper respiratory tract infection ( URTI \text{URTI} URTI ) incidence, and precipitates non-functional overreaching ( NFOR \text{NFOR} NFOR ) and overuse tissue pathology.
Acute:Chronic Workload Ratio (ACWR): Rolling Averages, EWMA, and Methodological Critiques
Inspired by Banister's two-factor impulse-response model—where performance equals Fitness (long-term chronic load) minus Fatigue (short-term acute load)—the Acute:Chronic Workload Ratio ( ACWR \text{ACWR} ACWR ) compares an athlete's acute workload (typically 7 days 7\text{ days} 7 days ) against their chronic workload (typically 28 days 28\text{ days} 28 days ).
1. Coupled vs. Uncoupled Rolling Average ACWR
Coupled Rolling ACWR \text{ACWR} ACWR : Divides the current 7-day acute load ( W 4 W_4 W 4 ) by the 4-week rolling average that includes the current week in the denominator: Coupled ACWR = W 4 0.25 × ( W 1 + W 2 + W 3 + W 4 ) \text{Coupled ACWR} = \frac{W_4}{0.25 \times (W_1 + W_2 + W_3 + W_4)} Coupled ACWR = 0.25 × ( W 1 + W 2 + W 3 + W 4 ) W 4
As demonstrated by Lolli et al. and Impellizzeri et al., including W 4 W_4 W 4 in both the numerator and denominator creates mathematical coupling : the numerator and denominator are intrinsically correlated even when generated from random numbers, and the ratio is mathematically capped at a maximum possible value of 4.0 4.0 4.0 (which occurs when W 1 = W 2 = W 3 = 0 W_1 = W_2 = W_3 = 0 W 1 = W 2 = W 3 = 0 ).
Uncoupled Rolling ACWR \text{ACWR} ACWR : Removes the acute week from the chronic denominator, dividing current acute load ( W 4 W_4 W 4 ) strictly by the average of the preceding 3 3 3 (or 4 4 4 ) independent weeks : Uncoupled ACWR = W 4 1 3 ( W 1 + W 2 + W 3 ) \text{Uncoupled ACWR} = \frac{W_4}{\frac{1}{3}(W_1 + W_2 + W_3)} Uncoupled ACWR = 3 1 ( W 1 + W 2 + W 3 ) W 4
2. Exponentially Weighted Moving Average (EWMA, Williams et al., 2017)
A fundamental physiological flaw of any simple rolling average (coupled or uncoupled) is equal time-weighting : a 28-day rolling average assigns the exact same weight ( 1 / 28 ≈ 3.57 % 1/28 \approx 3.57\% 1/28 ≈ 3.57% ) to a training session performed 27 days 27\text{ days} 27 days ago as it does to a grueling match played yesterday, and then abruptly drops Day 1's physiological stimulus to zero on Day 29.
To reflect the continuous exponential decay of physiological fitness and fatigue, Williams et al. (2017) introduced the Exponentially Weighted Moving Average ( EWMA \text{EWMA} EWMA ) : EWMA today = Load today × λ a + ( 1 − λ a ) × EWMA yesterday where λ a = 2 N + 1 \text{EWMA}_{\text{today}} = \text{Load}_{\text{today}} \times \lambda_a + (1 - \lambda_a) \times \text{EWMA}_{\text{yesterday}} \quad \text{where } \lambda_a = \frac{2}{N + 1} EWMA today = Load today × λ a + ( 1 − λ a ) × EWMA yesterday where λ a = N + 1 2
Acute Decay Constant ( N = 7 days N = 7\text{ days} N = 7 days ): λ acute = 2 7 + 1 = 2 8 = 0.250 \lambda_{\text{acute}} = \frac{2}{7 + 1} = \frac{2}{8} = 0.250 λ acute = 7 + 1 2 = 8 2 = 0.250
Today's workload receives a 25.0 % 25.0\% 25.0% weight, while yesterday's acute EWMA \text{EWMA} EWMA retains a 75.0 % 75.0\% 75.0% weight ( 1 − 0.25 = 0.75 1 - 0.25 = 0.75 1 − 0.25 = 0.75 ).
Chronic Decay Constant ( N = 28 days N = 28\text{ days} N = 28 days ): λ chronic = 2 28 + 1 = 2 29 ≈ 0.069 \lambda_{\text{chronic}} = \frac{2}{28 + 1} = \frac{2}{29} \approx 0.069 λ chronic = 28 + 1 2 = 29 2 ≈ 0.069
Today's workload receives a 6.9 % 6.9\% 6.9% weight, while yesterday's chronic EWMA \text{EWMA} EWMA retains a 93.1 % 93.1\% 93.1% weight. Because EWMA \text{EWMA} EWMA weights recent sessions more heavily, it exhibits significantly higher sensitivity to acute workload spikes than rolling averages.
3. Impellizzeri et al. Methodological Critiques of ACWR
While early observational papers popularized an ACWR \text{ACWR} ACWR " 0.80 – 1.30 0.80\text{–}1.30 0.80 – 1.30 sweet spot" and a " > 1.50 > 1.50 > 1.50 danger zone," Impellizzeri et al. (2020, 2021) established why practitioners must never treat ACWR \text{ACWR} ACWR thresholds as deterministic injury predictors :
Spurious Correlation from Coupling: Coupled ratios manufacture artificial statistical associations between the ratio and injury incidence.
Ratio Scaling Artifacts (Failure of Isometric Scaling): Ratios assume the numerator scales proportionally with the denominator across the entire range of chronic loads. In reality, an athlete returning from rehab with a very low chronic load ( 100 m 100\text{ m} 100 m of sprint distance) who runs 180 m 180\text{ m} 180 m records a terrifying ACWR = 1.80 \text{ACWR} = 1.80 ACWR = 1.80 despite trivial absolute tissue stress, whereas an elite winger with a huge chronic base ( 1,000 m 1{,}000\text{ m} 1 , 000 m ) who spikes to 1,350 m 1{,}350\text{ m} 1 , 350 m ( + 350 m +350\text{ m} + 350 m absolute spike) records a benign-looking ACWR = 1.35 \text{ACWR} = 1.35 ACWR = 1.35 .
Discretization Loss of Information: Slicing continuous workload metrics into arbitrary categorical buckets ( < 0.80 , 0.80 – 1.30 , > 1.50 < 0.80, 0.80\text{–}1.30, > 1.50 < 0.80 , 0.80 – 1.30 , > 1.50 ) discards statistical power and ignores baseline tissue capacity (eccentric strength, aerobic fitness, prior injury history).
- Complete Worked 7-Day Calculation Example: Monotony, Strain, ACWR, and EWMA
- Part A: Comparing Two 7-Day Microcycles with Identical Weekly Load ( 2,800 AU 2{,}800\text{ AU} 2 , 800 AU )
Day of Microcycle Schedule A: Monotonous Microcycle ( AU \text{AU} AU ) Schedule B: Undulating / Polarized Microcycle ( AU \text{AU} AU )
- Monday ( MD+1 Recovery) 360 360 360 0 0 0 (Complete Off Day)
- Tuesday ( MD+2 Regen) 440 440 440 300 300 300
- Wednesday ( MD-4 Strength/Speed) 360 360 360 750 750 750
- Thursday ( MD-3 Intensive/Extensive) 440 440 440 600 600 600
- Friday ( MD-2 Tactical Speed) 360 360 360 250 250 250
- Saturday ( MD-1 Captain's Run) 440 440 440 100 100 100
- Sunday ( MD Match Day) 400 400 400 800 800 800
Weekly Total Load ( ∑ Load \sum \text{Load} ∑ Load ) 2,800 AU 2{,}800\text{ AU} 2 , 800 AU 2,800 AU 2{,}800\text{ AU} 2 , 800 AU
Mean Daily Load ( μ 7 d \mu_{7\text{d}} μ 7 d ) 400.0 AU 400.0\text{ AU} 400.0 AU 400.0 AU 400.0\text{ AU} 400.0 AU
7-Day Standard Deviation ( SD 7 d \text{SD}_{7\text{d}} SD 7 d , sample) 40.0 AU 40.0\text{ AU} 40.0 AU 317.5 AU 317.5\text{ AU} 317.5 AU
Training Monotony ( μ / SD \mu / \text{SD} μ / SD , unitless) 400 / 40.0 = 10.0 400 / 40.0 = 10.0 400/40.0 = 10.0 (even a schedule with SD = 160 \text{SD} = 160 SD = 160 would give 2.50 > 2.0 2.50 > 2.0 2.50 > 2.0 ) 400 / 317.5 = 1.26 400 / 317.5 = 1.26 400/317.5 = 1.26 (below 1.50 1.50 1.50 )
Training Strain ( Weekly Load × Monotony \text{Weekly Load} \times \text{Monotony} Weekly Load × Monotony ) 2,800 × 10.0 = 28,000 AU 2{,}800 \times 10.0 = 28{,}000\text{ AU} 2 , 800 × 10.0 = 28 , 000 AU (or 7,000 AU 7{,}000\text{ AU} 7 , 000 AU at Monotony = 2.50 = 2.50 = 2.50 ) 2,800 × 1.26 = 3,528 AU 2{,}800 \times 1.26 = 3{,}528\text{ AU} 2 , 800 × 1.26 = 3 , 528 AU
Part B: Worked Coupled vs. Uncoupled ACWR
Suppose an athlete's weekly loads across 4 consecutive weeks are W 1 = 2,000 AU W_1 = 2{,}000\text{ AU} W 1 = 2 , 000 AU , W 2 = 2,200 AU W_2 = 2{,}200\text{ AU} W 2 = 2 , 200 AU , W 3 = 2,400 AU W_3 = 2{,}400\text{ AU} W 3 = 2 , 400 AU , and current acute week W 4 = 3,400 AU W_4 = 3{,}400\text{ AU} W 4 = 3 , 400 AU :
Coupled 4-Week Chronic Average: 2,000 + 2,200 + 2,400 + 3,400 4 = 10,000 4 = 2,500 AU → Coupled ACWR = 3,400 2,500 = 1.36 \frac{2{,}000 + 2{,}200 + 2{,}400 + 3{,}400}{4} = \frac{10{,}000}{4} = 2{,}500\text{ AU} \rightarrow \text{Coupled ACWR} = \frac{3{,}400}{2{,}500} = 1.36 4 2 , 000 + 2 , 200 + 2 , 400 + 3 , 400 = 4 10 , 000 = 2 , 500 AU → Coupled ACWR = 2 , 500 3 , 400 = 1.36 .
Uncoupled 3-Week Preceding Average: 2,000 + 2,200 + 2,400 3 = 6,600 3 = 2,200 AU → Uncoupled ACWR = 3,400 2,200 = 1.55 \frac{2{,}000 + 2{,}200 + 2{,}400}{3} = \frac{6{,}600}{3} = 2{,}200\text{ AU} \rightarrow \text{Uncoupled ACWR} = \frac{3{,}400}{2{,}200} = 1.55 3 2 , 000 + 2 , 200 + 2 , 400 = 3 6 , 600 = 2 , 200 AU → Uncoupled ACWR = 2 , 200 3 , 400 = 1.55 .
Notice how the coupled formula ( 1.36 1.36 1.36 ) masked a 55 % 55\% 55% workload surge above the preceding 3-week baseline ( 1.55 1.55 1.55 ) because the acute spike inflated its own denominator!
Part C: Worked 1-Step EWMA Update
Assume yesterday's acute EWMA \text{EWMA} EWMA ( N = 7 , λ a = 0.25 N=7, \lambda_a = 0.25 N = 7 , λ a = 0.25 ) was 400 AU 400\text{ AU} 400 AU and yesterday's chronic EWMA \text{EWMA} EWMA ( N = 28 , λ c = 0.069 N=28, \lambda_c = 0.069 N = 28 , λ c = 0.069 ) was 380 AU 380\text{ AU} 380 AU . Today the athlete completes Match Day ( MD ) with Load today = 800 AU \text{Load}_{\text{today}} = 800\text{ AU} Load today = 800 AU :
EWMA acute, today = ( 800 × 0.25 ) + ( 400 × 0.75 ) = 200 + 300 = 500.0 AU \text{EWMA}_{\text{acute, today}} = (800 \times 0.25) + (400 \times 0.75) = 200 + 300 = 500.0\text{ AU} EWMA acute, today = ( 800 × 0.25 ) + ( 400 × 0.75 ) = 200 + 300 = 500.0 AU .
EWMA chronic, today = ( 800 × 0.069 ) + ( 380 × 0.931 ) = 55.20 + 353.78 = 408.98 AU \text{EWMA}_{\text{chronic, today}} = (800 \times 0.069) + (380 \times 0.931) = 55.20 + 353.78 = 408.98\text{ AU} EWMA chronic, today = ( 800 × 0.069 ) + ( 380 × 0.931 ) = 55.20 + 353.78 = 408.98 AU .
EWMA ACWR today = 500.0 408.98 ≈ 1.22 \text{EWMA ACWR}_{\text{today}} = \frac{500.0}{408.98} \approx 1.22 EWMA ACWR today = 408.98 500.0 ≈ 1.22 .
Statistical Process Control (SPC) and Individual Time-Series Change Detection
To monitor individual athlete time series without relying on flawed group ratios, sport scientists deploy industrial Statistical Process Control ( SPC \text{SPC} SPC ) and rolling intra-individual standardization:
Shewhart Individual Moving-Range ( I - M R I\text{-}MR I - MR ) Control Charts: Plots an individual athlete's daily metric (e.g., morning lnRMSSD \text{lnRMSSD} lnRMSSD or CMJ \text{CMJ} CMJ flight-time:contraction-time ratio) around their healthy rolling baseline mean ( μ indiv \mu_{\text{indiv}} μ indiv ) with Upper and Lower Control Limits ( ± 2 SD \pm 2\text{ SD} ± 2 SD warning limits and ± 3 SD \pm 3\text{ SD} ± 3 SD action limits, estimated from the average moving range M R ‾ / d 2 \overline{MR} / d_2 MR / d 2 ). Practitioners apply Nelson / Western Electric run rules —flagging not only a single extreme point beyond control limits, but also 7 – 8 7\text{–}8 7 – 8 consecutive points falling on the same side of the mean line (which detects a systematic baseline shift).
Cumulative Sum ( CUSUM \text{CUSUM} CUSUM ) Charts: Calculates the cumulative sum of deviations from an athlete's target baseline mean ( S t = max [ 0 , S t − 1 + ( X t − μ 0 − k ) ] S_t = \max[0, S_{t-1} + (X_t - \mu_0 - k)] S t = max [ 0 , S t − 1 + ( X t − μ 0 − k )] ). Because CUSUM \text{CUSUM} CUSUM accumulates small, persistent daily deficits (such as a − 0.6 SD -0.6\text{ SD} − 0.6 SD suppression sustained for 6 straight days), it detects insidious non-functional overreaching far earlier than single-day threshold alerts.
Rolling Intra-Individual Z -Scores Z\text{-Scores} Z -Scores ( Z indiv = [ X today − μ 28 d ] / σ 28 d Z_{\text{indiv}} = [X_{\text{today}} - \mu_{28\text{d}}] / \sigma_{28\text{d}} Z indiv = [ X today − μ 28 d ] / σ 28 d ): Standardizes today's readiness score against the athlete's own 28-day rolling mean and SD \text{SD} SD , overlaid with Smallest Worthwhile Change ( SWC = 0.2 × SD \text{SWC} = 0.2 \times \text{SD} SWC = 0.2 × SD ) and Typical Error ( ± TE \pm \text{TE} ± TE ) bands to confirm that a flagged shift exceeds daily measurement noise.