This page provides an independent statistical analysis and educational interpretation of publicly reported results. ClinicalTrials.gov provides the official trial registry record. Numerical trial results on this page are restricted to the results posted in the ClinicalTrials.gov record; calculations added by Clinical Biostats are labelled as such.
1. Trial at a Glance
This page covers the registry results for Study of Efficacy and Safety of 300 IR Sublingual Immunotherapy (SLIT) Tablets in Adult Patients With Allergic Grass Pollen Rhinoconjunctivitis (NCT00955825), a randomized phase 3 study. The primary outcome is Combined Score (CS).
| Feature | Registry value |
|---|---|
| ClinicalTrials.gov identifier | NCT00955825 |
| Phase | Phase 3 |
| Condition | Allergic Rhinitis Due to Grass Pollens |
| Allocation | Randomized |
| Design model | Parallel |
| Masking | Quadruple |
| Enrollment | 473 |
| Arms in the primary outcome | 2 |
| Lead sponsor | Stallergenes Greer |
| Results posted | Yes |
2. Clinical Question
Population
Adults with allergic grass pollen rhinoconjunctivitis. The registry describes the condition as allergic rhinitis due to grass pollens. The primary efficacy population was the Full Analysis Set: participants who received at least one dose and had at least one Combined Score while on treatment during the pollen period.
Intervention
300 IR grass pollen allergen extract tablets, administered once daily according to the official study title. The registry lists the intervention as a drug and describes the tablet as containing grass pollen allergen extract.
Comparator
A placebo tablet. The registry describes the trial as placebo-controlled and lists placebo as the comparator intervention.
Primary question
During the pollen period, how did the mean daily Combined Score compare between the 300 IR and placebo groups? The score combines daily rhinoconjunctivitis symptoms and rescue medication use, with lower scores indicating better outcomes. The reported timeframe is the pollen period, described as an average of 42.8 days.
The primary endpoint brings together two aspects of the daily experience recorded in the trial: symptom severity and rescue medication. The symptom component covers six rhinoconjunctivitis symptoms, each scored from 0 to 3, for a total score from 0 to 18. The rescue medication component ranges from 0 to 3, with higher scores assigned to use of more intensive medication categories. The Combined Score scales the symptom score and combines it with the rescue medication score, treating the two components as equally important.
The comparison is therefore about the average combined score over the pollen period, not a single symptom, a particular medication, or a measure of long-term outcomes. The registry record reports an analysis of the mean score and an ANCOVA comparison with placebo. It does not report secondary outcomes in the posted results.
3. Trial Design
This was a randomized, double-blind, placebo-controlled, multicenter, phase III study with a parallel-group design. The registry lists quadruple masking. Participants were assigned to 300 IR grass pollen allergen extract tablets or placebo tablets. The official title specifies once-daily administration. The registry record does not report the allocation ratio, the randomization sequence method, or the identities of the groups encompassed by quadruple masking.
The study enrolled 473 participants and is marked completed. The recorded start was 2008-10, and primary completion was 2009-08. The sponsor was Stallergenes Greer. These are registry-record details; they do not by themselves describe the full conduct or duration of follow-up for each participant.
The primary efficacy population was the Full Analysis Set. It included participants who received at least one dose of the investigational product and had at least one Combined Score while on treatment during the pollen period. The registry says that this population was regarded as primary for efficacy evaluations. The posted arm summaries list 208.0 participants for 300 IR and 228.0 for placebo. The safety summaries list 233 participants at risk in the 300 IR group and 240 in the placebo group. The record does not explain the differences between those analysis populations or state whether all randomized participants were included in each analysis.
The design establishes a randomized comparison between an allergen-extract tablet and placebo, but the registry record does not report the trial's original sample-size justification, detailed eligibility criteria, dose-selection rationale, or full protocol. Those details should not be inferred from the phase, enrollment, or observed results.
4. Participant Flow and Accounting
The registry reports how participants moved through each stage of the study. All counts below are exactly as posted; missing counts are not inferred from other stages.
Overall Study
| Stage | 300 IR | Placebo |
|---|---|---|
| STARTED | 233 | 240 |
| COMPLETED | 207 | 223 |
| NOT COMPLETED | 26 | 17 |
Reasons for not completing this period:
| Reason | 300 IR | Placebo |
|---|---|---|
| Adverse Event | 15 | 2 |
| Withdrawal by Subject | 4 | 6 |
| Any other reason not above-mentioned | 7 | 9 |
Analysis population for the primary outcome, as defined in the registry: The Full Analysis Set (FAS) includes all patients who received at least one dose of the investigational product and had at least one Combined Score while on treatment during the pollen period. The FAS was regarded as primary for the efficacy evaluations.
5. Baseline Characteristics
The table reproduces the baseline characteristics posted in the registry, which describe the participants analysed at baseline and help show whether the randomized groups were comparable.
Population: The Full Analysis Set (FAS) includes all patients who received at least one dose of the investigational product and had at least one Combined Score while on treatment during the pollen period. The FAS was regarded as primary for the efficacy evaluations.
| Characteristic | Unit | 300 IR | Placebo | Total |
|---|---|---|---|---|
| Participants analysed | 210 | 228 | 438 | |
| Age, Continuous | years | 36.8 (SD 11.27) | 37.6 (SD 11.64) | 37.2 (SD 11.46) |
| Sex: Female, Male: Female | Participants | 109 | 125 | 234 |
| Sex: Female, Male: Male | Participants | 101 | 103 | 204 |
6. Primary Endpoint
The registry lists the primary outcome as Combined Score (CS), measured over Pollen period (average of 42.8 days).
| Element | Registry entry |
|---|---|
| Result type | Least Squares Mean |
| Measure of spread | Standard Error |
| Unit | Units on a scale (range: 0 to 3) |
| Endpoint classification | Continuous Endpoint |
The primary endpoint was the Combined Score (CS), a continuous daily measure that combines rhinoconjunctivitis symptoms and rescue medication use. The symptom component, the Rhinoconjunctivitis Total Symptom Score, sums six individual symptoms, each rated from 0 to 3; the total ranges from 0 to 18. The Rescue Medication Score ranges from 0 to 3. It assigns 0 to no rescue medication, 1 to antihistamine use, 2 to nasal corticosteroid use, and 3 to oral corticosteroid use.
The CS is calculated as (RTSS/6 + RMS)/2 and ranges from 0 to 3. This construction puts the symptom and rescue-medication components on a shared scale and gives them equivalent importance in the combined measure. Lower scores indicate better outcomes. The endpoint is useful for the trial's stated question because it captures both reported symptoms and rescue medication use rather than relying on either component alone.
The registry reports the least-squares mean for the pollen period, described as an average of 42.8 days. The primary efficacy population was the Full Analysis Set, defined by treatment exposure and availability of at least one on-treatment Combined Score during the pollen period. The record does not report a separate clinical-importance threshold for interpreting a change in this score.
7. Results Posted in the Registry
- 300 IR: mean 0.32 versus 0.45 on control; difference -0.13 (95% CI -0.22 to -0.04), standardized effect d = -0.27; z-test p = 0.005.
Mean difference: 300 IR
95% CI: -0.22 to -0.04
Recalculated from the posted summary statistics
8. Statistical Interpretation
The posted arm summaries show a mean Combined Score of 0.32 for 300 IR and 0.45 for placebo. Since lower scores are defined as better, the direction of the observed difference favors the lower score in the 300 IR group. These are descriptive arm summaries; they are not the registry's adjusted comparison.
The reported analysis used ANCOVA and gives a least-squares mean difference versus placebo of -0.126, with a 95% confidence interval from -0.194 to -0.058 and p < 0.001. The negative estimate indicates a lower adjusted mean score for 300 IR relative to placebo under the reported comparison. The confidence interval is entirely on the negative side of zero, and the reported p-value is small under the analysis model. These statistics describe the trial result; they do not establish the clinical importance of the difference, because a threshold for clinical importance is not reported in the registry record.
A separate simple, unadjusted re-calculation from the posted group summaries gives a mean difference of -0.13 and p = 0.005. It is not the same analysis as the ANCOVA result. The registry flags a discrepancy, so the sponsor's own analysis takes precedence. The re-calculation is useful as a check on the direction and approximate scale of the contrast, but it should not replace the reported ANCOVA estimate or be treated as an alternative primary result.
The endpoint combines symptom scores with rescue medication scores, so its group mean does not reveal how much of the contrast came from symptoms versus medication use. The registry record reports one primary outcome measure and one analysis, and no secondary outcomes are posted. Consequently, the posted efficacy results do not answer questions about individual symptoms, particular rescue medications, or outcomes beyond the defined pollen-period score.
The interpretation is also bounded by the analysis population and methods described in the record. The Full Analysis Set required at least one on-treatment score during the pollen period. Details of missing-score handling, covariate adjustment, and other analysis decisions are not reported in the registry record. The results therefore describe the posted analysis and population; they do not supply a complete account of every design or analysis choice.
9. Statistical Methods Explained
What does the reported ANCOVA estimate represent?
ANCOVA is a method for comparing an outcome between groups while accounting for covariates included in the model. In this trial, the registry identifies the reported parameter as the least-squares mean difference versus placebo. A least-squares mean is a model-based group mean, and the difference expresses the model-based contrast between 300 IR and placebo. The registry reports the ANCOVA method, but the covariates included in that model are not reported in the registry record. It is therefore not possible to describe which participant characteristics or baseline values were used for adjustment.
The estimate is -0.126. Because the comparison is 300 IR versus placebo and lower Combined Scores are defined as better, a negative difference corresponds to a lower adjusted mean score for 300 IR. The estimate remains tied to the model and outcome definition; it is not a percentage change, a probability of improvement, or a count of participants who improved.
How does the re-calculation differ?
The unadjusted re-calculation uses the posted arm-level means and standard errors to form a simple comparison. It does not reproduce the sponsor's ANCOVA model. The calculated mean difference is -0.13, with an unadjusted p-value of 0.005. The posted group means are 0.32 for 300 IR and 0.45 for placebo. The re-calculation also uses an approximate pooled standard deviation, listed as 0.480, and labels the standardized difference as -0.271.
These are distinct statistical summaries. An unadjusted calculation from group summaries does not account for the covariate structure of an ANCOVA, and the registry does not report enough model detail to reproduce the sponsor's analysis independently. Since a discrepancy is flagged, the sponsor's own analysis takes precedence. The re-calculation should be read as a descriptive check, not as a replacement for the reported analysis.
What do standard errors and confidence intervals convey?
A standard error describes the estimated sampling variability of a statistic under its analysis framework. The arm summaries give standard errors of 0.033 for 300 IR and 0.032 for placebo. Those standard errors describe uncertainty around the reported arm-level means; they are not measures of the spread of individual participant scores. The registry also reports a 95% confidence interval for the ANCOVA contrast, from -0.194 to -0.058.
A confidence interval gives a range of values compatible with the data and the method under its assumptions. It communicates precision as well as direction. Here, the reported interval is entirely negative, consistent with a lower adjusted mean score in the 300 IR group for this outcome. It does not establish whether the size of the difference meets a clinical-importance threshold, which is not reported in the registry record.
What does the p-value address?
A p-value assesses how compatible the observed result is with a specified null hypothesis under the statistical model. The ANCOVA analysis reports p < 0.001; the unadjusted re-calculation reports p = 0.005. These values belong to different analyses and should not be conflated. A p-value is not the probability that the null hypothesis is true, nor does it measure the probability that the result will be reproduced. Statistical evidence and clinical importance are separate questions.
Why can over-dispersion matter in general?
In general, over-dispersion means that observed variability is greater than a model expects. When a method assumes less variability than the data contain, standard errors can be too small and uncertainty can be understated. The posted primary outcome is continuous and the registry identifies ANCOVA, so a count-model over-dispersion adjustment is not described for this primary analysis. The record does not report diagnostic checks or model-assumption assessments. More generally, readers should distinguish the statistical model used from assumptions or diagnostics that are not documented.
What can be inferred from the analysis description?
The record supports identifying the outcome, the Full Analysis Set definition, the ANCOVA method, the least-squares mean contrast, the confidence interval, and the p-value. It does not report the covariates, model diagnostics, detailed missing-data procedure, or all protocol-level analysis decisions. Those omissions limit independent reconstruction of the reported analysis. They do not change the fact that the registry reports an ANCOVA result, but they narrow the methodological detail available to readers.
10. Confidence Intervals and Precision
The registry-reported ANCOVA estimate is a least-squares mean difference of -0.126 for 300 IR versus placebo. Its 95% confidence interval ranges from -0.194 to -0.058. In general, a confidence interval expresses the uncertainty around an estimate under the chosen analysis method: narrower intervals indicate greater precision, while wider intervals indicate less precision. The interval also shows the range of effect values compatible with the analysis and its assumptions.
Both confidence limits are negative. Given the score's definition, in which lower values indicate better outcomes, the interval is consistent with a lower adjusted Combined Score for 300 IR than for placebo. The interval does not cross zero, which aligns with the reported p-value of < 0.001. This does not mean that every participant had a lower score, nor does it identify the difference for any individual participant.
Precision is not the same as clinical importance. The registry record does not report a threshold for a clinically important difference in the Combined Score, so the confidence interval cannot be classified against such a threshold from this record alone. The interval also pertains to the ANCOVA estimate, not to all possible populations, outcomes, or analysis approaches.
The re-calculated unadjusted comparison is a distinct estimate based on posted summaries. Its interval endpoints are not repeated because the primary interpretation should remain anchored to the sponsor's reported ANCOVA analysis; the record flags a discrepancy, and the sponsor's own analysis takes precedence. The different methods and estimates reinforce the need to keep the adjusted reported result separate from a simple summary-statistic calculation.
11. Planning a Similar Trial: Sample Size
This is a planning illustration, not a re-evaluation of the original trial. It asks: if a new study wanted to detect a difference like the one observed, or a smaller one, how large would it need to be? It is deliberately not “observed power” of the finished trial, which is not a meaningful quantity.
| Effect to detect | Participants per arm, 80% power | Participants per arm, 90% power |
|---|---|---|
| 100% of the observed effect | 214 | 287 |
| 75% of the observed effect | 381 | 509 |
| 50% of the observed effect | 856 | 1,145 |
The planning figures are participants per arm, not total events. They are illustrations based on the observed effect, rather than the trial's original design justification. The planning assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. Each planning row uses the stated fraction of the observed effect as the effect to detect.
The 80% power column gives the planned number of participants per arm for an analysis with an 80% chance of detecting the specified effect under those assumptions, if that effect is the true one. The 90% power column gives the corresponding per-arm number for a 90% chance under the same assumptions. These are planning concepts, not guarantees about the result of a future trial. This is not observed power.
Read the rows by the effect size they target. Planning for 100% of the observed effect gives 214 participants per arm for 80% power and 287 participants per arm for 90% power. Planning for 75% of the observed effect gives 381 participants per arm for 80% power and 509 participants per arm for 90% power. Planning for 50% of the observed effect gives 856 participants per arm for 80% power and 1,145 participants per arm for 90% power. The pattern reflects a general planning principle: smaller effects are harder to detect and require more participants, all else equal.
The registry's own sample-size assumptions and justification are not reported in the registry record. The planning figures should therefore not be read as the trial's actual target enrollment or as evidence about the design choices made before the trial. They are calculations tied to the observed effect and the stated planning assumptions, and may be sensitive to uncertainty in that observed effect.
12. How the Sample Size Is Derived
Power is the probability that a study of a given size rejects the null hypothesis when a specific true effect exists. It depends on four things: the effect to detect, the variability of the outcome, the significance level (here a two-sided α of 0.05, so z1−α/2 = 1.960) and the desired power (z1−β = 0.842 for 80% and 1.282 for 90%).
Formula
n is the number of participants in each arm, Δ is the difference in means to detect and σ is the common standard deviation.
Worked calculation for this trial
- Observed difference Δ = -0.130; pooled standard deviation σ = 0.480.
- n = 2 × (1.96 + 0.842)2 × 0.4802 / -0.1302 = 213.8, rounded up to 214 participants per arm for 80% power.
The smaller-effect rows in the table above repeat the same calculation with the effect multiplied by 0.75 and 0.5 (for ratios, applied to the logarithm of the ratio).
R code
alpha <- 0.05
z_a <- qnorm(1 - alpha / 2) # two-sided
delta <- -0.13 # observed difference in means
sigma <- 0.479741981343716 # pooled standard deviation
n_per_arm <- function(power, frac = 1) {
ceiling(round(2 * (z_a + qnorm(power))^2 * sigma^2 / (delta * frac)^2, 6))
}
for (f in c(1, 0.75, 0.5))
cat(sprintf("%3.0f%% of observed effect: n per arm = %s (80%% power), %s (90%% power)\n", 100 * f,
format(n_per_arm(0.80, f), big.mark = ","), format(n_per_arm(0.90, f), big.mark = ",")))
# Check against R's built-in function (t-based, so very slightly larger)
cat("power.t.test:", round(power.t.test(delta = delta, sd = sigma, power = 0.80)$n, 1), "\n")
# Simulation: exact two-sample t-test using simulated means and variances
set.seed(955825)
n <- n_per_arm(0.80)
reps <- 20000
m_diff <- rnorm(reps, delta, sigma * sqrt(2 / n)) # difference in sample means
s2 <- sigma^2 * rchisq(reps, 2 * (n - 1)) / (2 * (n - 1)) # pooled sample variance
tstat <- m_diff / sqrt(s2 * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(tstat) > qt(0.975, 2 * (n - 1))), reps))
Output from running the code
100% of observed effect: n per arm = 214 (80% power), 287 (90% power)
75% of observed effect: n per arm = 381 (80% power), 509 (90% power)
50% of observed effect: n per arm = 856 (80% power), 1,145 (90% power)
power.t.test: 214.7
Simulated power at n = 214 per arm: 0.795 (20000 replicates)The simulation draws many sets of group means and variances at the planned sample size and counts how often the two-sample t-test rejects the null. It should land close to the target power; at very small required sample sizes it can fall below it, because the normal approximation is rough there.
13. Analyses Reported by the Sponsor
| Method | Estimate | 95% CI | P-value |
|---|---|---|---|
| ANCOVA | LS Mean difference vs. Placebo -0.126 | -0.194 to -0.058 | < 0.001 |
The registry-reported sponsor analysis is an ANCOVA comparing the least-squares mean Combined Score for 300 IR with placebo. It reports a difference of -0.126, a 95% confidence interval from -0.194 to -0.058, and p < 0.001. This is the analysis to prioritize when describing the trial's primary result.
The simple re-calculation from the posted arm summaries is unadjusted. It estimates a mean difference of -0.13 and reports p = 0.005. It uses the arm-level summaries rather than the sponsor's ANCOVA model. Since the registry record flags a discrepancy, the sponsor's own analysis takes precedence; the re-calculation should not be substituted for it or treated as a second sponsor result.
The record does not report enough ANCOVA detail to reproduce the sponsor's model, including its covariates. The two estimates should therefore be presented as outputs from different approaches, without attributing their numerical difference to any specific adjustment or model choice that the record does not document. The re-calculation can serve as a basic unadjusted comparison, while the sponsor analysis remains the primary reported inferential result.
14. Multiplicity, Missing Data and Analysis Populations
The registry record lists one outcome measure and one analysis. It reports the Combined Score as the primary endpoint and does not post secondary outcomes. This limited set of posted results means that the record does not allow a broad assessment of how multiple endpoints, time points, or subgroup analyses were handled.
A multiplicity strategy addresses the increased chance of false-positive findings when several statistical hypotheses are tested. In general, a prespecified hierarchy or adjustment can help control that issue. The registry record does not report whether a multiplicity procedure was planned, whether other outcomes were measured but not posted, or whether subgroup or sensitivity analyses were conducted. The number of posted outcomes and analyses alone does not establish that there were no additional analyses in the full study.
The primary efficacy population was the Full Analysis Set, defined as participants with at least one dose and at least one Combined Score while on treatment during the pollen period. The record says that this was regarded as primary for efficacy evaluations. It does not give a detailed account of exclusions from that set, protocol deviations, or how observations were handled when scores were missing. The missing-data method, including any imputation or model-based handling, is not reported in the registry record.
These gaps matter because analysis populations and missing-data decisions can affect the estimate and its uncertainty. The posted definition identifies who could enter the primary efficacy set, but does not explain how participants lacking a qualifying score were treated or whether other analysis populations were used. The record also does not report a comparison of results across alternative missing-data assumptions. Consequently, the reported ANCOVA result can be interpreted as the primary posted efficacy analysis, while its sensitivity to unreported analysis choices cannot be assessed from the registry record.
15. Safety Results
The registry reports serious adverse events as affected participants divided by participants at risk.
| Arm | Participants with serious adverse events | Participants at risk | Percentage |
|---|---|---|---|
| 300 IR | 2 | 233 | 0.9% |
| Placebo | 2 | 240 | 0.8% |
Other (non-serious) adverse events
Participants with at least one non-serious event at or above the registry's 5% reporting threshold.
| Arm | Participants affected of at risk |
|---|---|
| 300 IR | 161 of 233 |
| Placebo | 114 of 240 |
Most frequent serious adverse event terms
| Event term | Organ system | 300 IR | Placebo |
|---|---|---|---|
| HAEMATOCHEZIA | Gastrointestinal disorders | 0 of 233 | 1 of 240 |
| INTESTINAL OBSTRUCTION | Gastrointestinal disorders | 0 of 233 | 1 of 240 |
| PALATAL DISORDER | Gastrointestinal disorders | 1 of 233 | 0 of 240 |
| GASTROENTERITIS | Infections and infestations | 0 of 233 | 1 of 240 |
| NEUROENDOCRINE CARCINOMA | Neoplasms benign, malignant and unspecified (incl cysts and polyps) | 1 of 233 | 0 of 240 |
Most frequent non-serious adverse event terms
| Event term | Organ system | 300 IR | Placebo |
|---|---|---|---|
| NASOPHARYNGITIS | Infections and infestations | 40 of 233 | 42 of 240 |
| ORAL PRURITUS | Gastrointestinal disorders | 57 of 233 | 11 of 240 |
| THROAT IRRITATION | Respiratory, thoracic and mediastinal disorders | 54 of 233 | 6 of 240 |
| HEADACHE | Nervous system disorders | 15 of 233 | 30 of 240 |
| UPPER RESPIRATORY TRACT INFECTION | Infections and infestations | 17 of 233 | 21 of 240 |
| NASAL CONGESTION | Respiratory, thoracic and mediastinal disorders | 17 of 233 | 15 of 240 |
| EAR PRURITUS | Ear and labyrinth disorders | 31 of 233 | 1 of 240 |
| OROPHARYNGEAL PAIN | Respiratory, thoracic and mediastinal disorders | 18 of 233 | 12 of 240 |
| SINUSITIS | Infections and infestations | 14 of 233 | 15 of 240 |
| OEDEMA MOUTH | Gastrointestinal disorders | 22 of 233 | 1 of 240 |
Serious events with the highest arm-level rate: palatal disorder (0.4%), neuroendocrine carcinoma (0.4%), haematochezia (0.4%), intestinal obstruction (0.4%), gastroenteritis (0.4%).
The safety summaries list 233 participants at risk in the 300 IR group and 240 in the placebo group. The serious adverse event figures show 2 affected participants in each group. The registry lists 161 participants affected for other adverse events in the 300 IR group and 114 in the placebo group. These counts use different safety categories and should be read in their stated categories rather than combined into a single measure.
The record lists PALATAL DISORDER, NEUROENDOCRINE CARCINOMA, HAEMATOCHEZIA, INTESTINAL OBSTRUCTION, and GASTROENTERITIS among the leading serious-event terms, each at 0.4%. The record does not give enough detail to infer the duration, severity beyond the serious classification, relatedness assessment, or number of events per affected participant for each term. Deaths are not reported in the registry record.
These safety counts are descriptive registry entries. They do not by themselves establish a comparative safety profile, and the count of affected participants does not describe the full clinical context or event timing. Differences in the size of the safety groups and the absence of detailed event-level information also limit interpretation. The figures should be read alongside the trial's reported categories and denominators, without treating them as evidence that an event was caused by a particular intervention.
16. What the Result Does, and Does Not, Mean
The posted primary result is a model-based comparison of average daily Combined Scores during the pollen period. The 300 IR group had a lower arm-level mean than placebo, and the reported ANCOVA estimate was -0.126 for 300 IR versus placebo. The 95% confidence interval ranged from -0.194 to -0.058, with p < 0.001. Since lower Combined Scores indicate better outcomes, the direction of the result is toward a lower adjusted score in the 300 IR group.
This result describes the average of a combined measure. It does not reveal whether the difference arose mainly from symptom scores, rescue medication scores, or both. It does not show how individual participants responded, how outcomes varied over time, or whether a particular symptom changed. The registry record does not post secondary outcomes that could answer those questions.
Statistical evidence is not the same as evidence of clinical importance. The registry record does not report a threshold for a clinically important difference on the Combined Score. The reported confidence interval conveys uncertainty around the model-based estimate, but it cannot determine clinical importance without that context.
The result also applies to the Full Analysis Set and the defined pollen-period endpoint. It should not be extended to populations, settings, time periods, or outcomes that are not described in the record. The trial was randomized and placebo-controlled, but details such as the allocation ratio, model covariates, and missing-data procedures are not reported in the registry record. Those gaps limit how completely the analysis can be reconstructed.
The record therefore supports a focused conclusion about the posted primary analysis: the adjusted mean Combined Score was lower in the 300 IR group than in the placebo group, with the reported uncertainty and p-value. It does not justify broader claims about all symptoms, longer-term effects, individual outcomes, clinical importance, or unposted safety and efficacy analyses.
17. Why This Trial Matters Statistically
This trial illustrates why the endpoint definition matters when interpreting a treatment comparison. The Combined Score brings symptom severity and rescue medication use into one continuous measure and assigns the two components equivalent importance. A difference in that score is therefore not interchangeable with a difference in symptoms alone or medication use alone. Understanding the score's construction is necessary to give the direction of the result its intended meaning.
It also shows the distinction between an adjusted primary analysis and a calculation based on arm summaries. The registry reports an ANCOVA least-squares mean difference, while a separate unadjusted re-calculation gives a related but distinct estimate. A reader should not collapse these into a single result or choose between them by inspecting the p-values alone. The record flags a discrepancy, making the sponsor's reported analysis the primary inferential result.
Finally, the trial record demonstrates that a statistically clear estimate can still leave important questions open. The confidence interval describes precision under the reported model, but a clinical-importance threshold is not reported. The record also omits details of covariate adjustment, missing-data handling, original sample-size planning, and multiplicity procedures. These omissions do not erase the posted result; they define the limits of what can be independently evaluated from the registry record.
18. Limitations
- The posted summary statistics are the only data these results rest on; patient-level data, full protocols and statistical analysis plans are not available.
- Recalculated results are simple, unadjusted calculations from posted summaries. They do not replace the sponsor's prespecified analysis.
Several trial-specific limitations follow from the detail available in the registry record. The reported ANCOVA estimate is not accompanied by the covariates included in the model, so the adjustment cannot be independently reconstructed. The record also does not report model diagnostics or the handling of missing Combined Scores. These details are relevant to understanding how the adjusted estimate and its uncertainty were obtained.
The primary efficacy analysis used the Full Analysis Set, which required at least one dose and at least one on-treatment score during the pollen period. The record does not explain the composition of participants excluded from that set or report whether alternative analysis populations were used. The posted efficacy arm counts and safety denominators differ, and the registry does not explain the relationship between them.
The record does not report the original sample-size justification, allocation ratio, detailed randomization procedure, multiplicity plan, or clinical-importance threshold for the Combined Score. It posts one primary outcome measure and one analysis, with no secondary outcomes. That limits the ability to assess other measured outcomes or the possibility of unposted analyses from this record alone.
For safety, the registry gives affected counts and selected serious-event terms but does not report deaths, which are not reported in the registry record, or detailed event-level context. It is not possible from these entries alone to assess event timing, relatedness, or the number of events per participant. These limitations concern the scope of interpretation supported by the record; they do not change the numerical results that are posted.
19. Related Tutorials
20. Related Statistical Calculators
21. Sources
- ClinicalTrials.gov: Study of Efficacy and Safety of 300 IR Sublingual Immunotherapy (SLIT) Tablets in Adult Patients With Allergic Grass Pollen Rhinoconjunctivitis — NCT00955825.
- Registry record last updated 2016-05-19; status last verified 2016-04.
- Results first posted 2016-05-19.
- Data retrieved from ClinicalTrials.gov on 2026-11-09.
- Group sizes, means, event counts and sponsor-reported p-values are reproduced as posted. Effect estimates, confidence intervals and p-values not attributed to the sponsor are independently calculated from the posted summary statistics.
Continue through the Clinical Biostats statistical pathway
Use this trial's endpoint as a starting point for deeper study of effect measures, confidence intervals, and sample-size planning.
22. Record Summary
The registry record describes a completed, randomized, quadruple-masked, parallel, placebo-controlled, multicenter phase III study of 300 IR grass pollen allergen extract tablets in adults with allergic grass pollen rhinoconjunctivitis. It lists enrollment of 473, a start of 2008-10, and primary completion in 2009-08.
The primary endpoint was the daily Combined Score during the pollen period, an average of 42.8 days, with lower scores indicating better outcomes. The reported ANCOVA difference versus placebo was -0.126, with a 95% confidence interval from -0.194 to -0.058 and p < 0.001. A discrepancy is flagged between the sponsor analysis and a simple unadjusted re-calculation, so the sponsor's own analysis takes precedence.
The record posts no secondary outcomes and does not report the original sample-size justification, model covariates, missing-data procedure, or multiplicity plan. Safety summaries list 2 participants with serious adverse events in each group; deaths are not reported in the registry record.