Overview

Analysis Overview

ANCOVA Configuration

Analysis overview and configuration

Configuration

Analysis TypeAncova
CompanyMental Health Research Center
ObjectiveDo different therapy types lead to different treatment outcomes after controlling for baseline symptom severity, Age, and sleep quality?
Analysis Date2026-03-07
Processing Idtest_1772903575
Total Observations500

Module Parameters

ParameterValue_row
confidence_level0.95confidence_level
reference_groupreference_group
covariate_columnsSymptom Severity (1-10),Age,Sleep Quality (1-10)covariate_columns
outcome_columnTreatment Progress (1-10)outcome_column
group_columnTherapy Typegroup_column
effect_size_typeeta_squaredeffect_size_type
Ancova analysis for Mental Health Research Center

Interpretation

Purpose

This ANCOVA analysis evaluates whether four therapy types (Cognitive Behavioral, Dialectical Behavioral, Interpersonal, and Mindfulness-Based) produce significantly different treatment outcomes after statistically controlling for baseline symptom severity, age, and sleep quality. The analysis uses 500 patient observations to isolate the effect of therapy type from confounding variables.

Key Findings

  • F-statistic (Therapy Type): 0.324 with p-value = 0.808 - No statistically significant difference in outcomes across therapy types
  • Partial Eta-Squared: 0.002 (negligible) - Therapy type explains virtually none of the outcome variance
  • Adjusted Means Range: 7.33–7.55 on the outcome scale - All therapies cluster within 0.22 points, indicating practical equivalence
  • Pairwise Comparisons: All 6 therapy contrasts show p-values > 0.76 (non-significant) with confidence intervals crossing zero
  • Covariate Effects: Sleep Quality approached significance (p = 0.058, η² = 0.01); Symptom Severity and Age showed negligible effects

Interpretation

After controlling for baseline characteristics, the four therapy types produce statistically indistinguishable treatment outcomes. The neglig

Data Preparation

Data Preprocessing

Data Quality & Completeness

Data preprocessing and column mapping

Data Quality

Initial Rows500
Final Rows500
Rows Removed0
Retention Rate100

Data Quality

MetricValue
Initial Rows500
Final Rows500
Rows Removed0
Retention Rate100%
Processed 500 observations, retained 500 (100.0%) after cleaning

Interpretation

Purpose

This section documents the data preprocessing pipeline for the ANCOVA analysis comparing four therapy types. Perfect data retention (100%) indicates no rows were removed during cleaning, meaning all 500 observations proceeded to statistical analysis without exclusions or transformations. This is critical for understanding whether the final results represent the complete dataset or a filtered subset.

Key Findings

  • Initial Rows: 500 observations entered the preprocessing pipeline
  • Final Rows: 500 observations retained after cleaning (100% retention rate)
  • Rows Removed: 0 — no observations were excluded during data quality checks
  • Data Integrity: No missing values, duplicates, or outliers triggered removal; the assumption tests confirmed 0 outliers using studentized residuals (|studentized| > 3)

Interpretation

The perfect retention rate suggests either exceptionally clean source data or minimal preprocessing criteria applied. This is consistent with the ANCOVA results, where no outliers were detected and all 500 cases contributed to the F-statistic (F=0.324, p=0.808). The complete dataset strengthens statistical power for detecting group differences, though the negligible effect size (partial η²=0.002) reflects genuine similarity between therapy types rather than data limitations.

Context

No train/test split was performed, indicating this is a confirmatory analysis rather than predictive modeling.

Executive Summary

Executive Summary

Key Findings & Recommendations

Key Metrics

total_observations
500
f_statistic
0.324
p_value
0.8083
partial_eta_sq
0.002
effect_size
negligible
assumptions_met
False

Key Findings

FindingValue
Sample Size500
Groups Compared4
F-statistic0.324
p-value0.8083
Effect Sizenegligible (η² = 0.002)
Assumptions MetNo

Summary

Bottom Line: No significant differences found between therapy groups after adjusting for covariates (F = 0.32, p = 0.8083). Groups perform similarly after accounting for baseline differences.

Key Findings:
• Analyzed 500 observations across 4 therapy groups
• Controlled for 3 covariate(s): Symptom Severity (1-10), Age, Sleep Quality (1-10)
• Effect size: negligible (partial η² = 0.002, 0.2% variance explained)
• ⚠️ Some assumptions violated - interpret with caution

Recommendation: Therapy type may not be the primary driver of outcomes. Focus on optimizing covariate factors (baseline severity, Age, sleep quality) which may have stronger impact on treatment success.

Interpretation

Purpose

This analysis evaluated whether four therapy types (Cognitive Behavioral, Dialectical Behavioral, Interpersonal, and Mindfulness-Based) produce meaningfully different outcomes in a sample of 500 patients. Using ANCOVA to control for baseline symptom severity, age, and sleep quality, the analysis tests whether therapy selection drives treatment effectiveness after accounting for these confounding factors.

Key Findings

  • F-statistic (0.324) with p-value (0.808): No statistically significant differences exist between therapy groups; results are consistent with random variation
  • Partial Eta-Squared (0.002): Therapy type explains only 0.2% of outcome variance—a negligible effect size
  • Adjusted Group Means (7.33–7.55): All four therapies cluster tightly around 7.44, with confidence intervals substantially overlapping
  • Assumption Violation: Normality test failed (p < 0.001), though homogeneity of variance and slope homogeneity passed, limiting statistical reliability

Interpretation

The data provide no evidence that therapy type meaningfully influences patient outcomes in this cohort. After adjusting for baseline differences in symptom severity, age, and sleep quality, all four therapeutic approaches yield statistically indistinguishable results. The negligible effect size indicates therapy selection accounts

Table 4

ANCOVA Results

Type III Analysis of Covariance

Type III ANCOVA results testing group differences after covariate adjustment

StatisticValue
F-statistic0.324
p-value0.8083
Partial η²0.002
Effect Sizenegligible
Groups4
Sample Size500

Interpretation

Purpose

This section presents the Type III ANCOVA omnibus test, which evaluates whether the four therapy types produce significantly different treatment outcomes after statistically controlling for three covariates (Symptom Severity, Age, Sleep Quality). This is the primary hypothesis test determining whether therapy type meaningfully influences the outcome variable.

Key Findings

  • F-statistic (0.324): Extremely low test statistic indicates minimal between-group variance relative to within-group error, suggesting therapy groups are highly similar on the outcome.
  • p-value (0.808): Far exceeds the 0.05 significance threshold, providing no evidence of group differences after covariate adjustment.
  • Partial η² (0.002): Negligible effect size shows therapy type accounts for only 0.2% of outcome variance, with covariates explaining the remainder.
  • Covariate Pattern: Sleep Quality approached significance (p = 0.058, η² = 0.01), while Symptom Severity and Age showed no meaningful effects.

Interpretation

The analysis found no statistically significant differences among the four therapy types in treatment progress. After adjusting for baseline symptom severity, age, and sleep quality, all therapy groups converged to nearly identical adjusted means (7.33–7.55 range). This suggests therapy type selection does not substantially influence

Figure 5

Adjusted Marginal Means

Group Means After Covariate Adjustment

Estimated marginal means (adjusted group means) with 95% confidence intervals

Interpretation

Purpose

Adjusted marginal means isolate the effect of therapy type by statistically controlling for baseline differences in symptom severity, age, and sleep quality. This section provides "apples-to-apples" comparisons across the four therapy groups, showing what average progress would be if all participants started from equivalent positions on measured covariates.

Key Findings

  • Mean Range: 7.33–7.55 on a 1–10 scale (0.21-point spread) — minimal practical separation between groups
  • Confidence Interval Overlap: All four 95% CIs substantially overlap (lower bounds: 7.04–7.24; upper bounds: 7.63–7.85), indicating no statistically significant pairwise differences
  • Standard Error Consistency: SE values cluster tightly around 0.15, reflecting balanced group sizes and stable precision across therapy types
  • Highest Adjusted Mean: Interpersonal Therapy (7.55); Lowest: Mindfulness-Based Therapy (7.33)

Interpretation

Despite covariate adjustment, the four therapy approaches yield nearly identical adjusted outcomes, with differences of ≤0.21 points. The overlapping confidence intervals confirm the ANCOVA's non-significant F-statistic (p = 0.808), indicating that therapy type explains negligible variance in progress

Figure 6

Pairwise Comparisons

Tukey-Adjusted Group Differences

Tukey-adjusted pairwise comparisons between all therapy groups

Interpretation

Purpose

This section tests whether any therapy type produces meaningfully different outcomes compared to others. By examining all 6 possible pairwise comparisons with Tukey adjustment, the analysis controls for multiple testing errors while identifying which specific therapy pairs differ significantly. This directly addresses whether therapy type influences the outcome measure.

Key Findings

  • Total Comparisons: 6 pairs tested across 4 therapy types
  • Significant Pairs: 0 out of 6 comparisons showed adjusted p < 0.05
  • Effect Size Range: Estimates range from -0.13 to +0.21 (mean = 0.03), all negligible
  • Confidence Intervals: All 95% CIs cross zero, confirming no significant differences
  • Adjusted p-values: Range from 0.76 to 1.00, all well above significance threshold

Interpretation

Despite comparing four distinct therapy approaches, no pairwise differences reached statistical significance after Tukey correction. The largest observed difference (Interpersonal vs. Mindfulness-Based: 0.21 points) remains non-significant (p = 0.76). All confidence intervals encompass zero, indicating the true population differences are statistically indistinguishable from zero. This aligns with the overall ANCOVA finding (F = 0.324, p

Figure 7

Linearity Assumption

Outcome vs Primary Covariate by Group

Linearity assumption check - scatterplot of outcome vs primary covariate by group

Interpretation

Purpose

This section validates the linearity assumption required for ANCOVA—that each covariate maintains a linear (straight-line) relationship with the outcome across all therapy groups. Violations of linearity reduce statistical power and can bias treatment effect estimates, making this check essential before interpreting therapy type differences.

Key Findings

  • Covariate Range: Values span 5–10 (mean=7.48, SD=1.71), with left-skewed distribution suggesting clustering toward higher severity levels
  • Outcome Spread: Outcomes range 5–10 (mean=7.44, SD=1.73) with right-skewed distribution, showing greater variability than fitted values
  • Fitted Values Consistency: Fitted values cluster tightly (SD=0.16, range 7.05–7.83), indicating stable linear predictions across groups
  • Group Distribution: Balanced representation across four therapy types (124–130 observations each)

Interpretation

The tight clustering of fitted values relative to raw outcome variability suggests the linear model captures the central trend well, with residual scatter reflecting genuine outcome variation rather than systematic non-linearity. The slope homogeneity test (p=0.243, PASS) confirms that covariate-outcome relationships do not differ meaningfully across therapy groups, supporting the validity of parallel regression lines assumed in

Figure 8

Normality Diagnostic

QQ Plot of Residuals

Normality of residuals assumption (Shapiro-Wilk test + QQ plot)

Interpretation

Purpose

This section evaluates whether the residuals from the ANCOVA model follow a normal distribution—a key assumption for valid statistical inference. The Shapiro-Wilk test and QQ plot together provide evidence about whether the model's prediction errors are normally distributed, which affects the reliability of p-values and confidence intervals in comparing therapy types.

Key Findings

  • Shapiro-Wilk p-value: 0.0000 - Statistically significant deviation from normality detected
  • Assumption Status: FAIL - Residuals do not meet the normality requirement (p < 0.05)
  • QQ Plot Pattern: Sample quantiles show systematic deviation from the theoretical diagonal, particularly in the tails, indicating heavier tails than expected under normality

Interpretation

The residuals exhibit non-normal behavior, with observed values deviating more from the mean than a normal distribution would predict. However, with n=500, the ANCOVA analysis remains robust to this violation due to the Central Limit Theorem. The negligible effect sizes and non-significant therapy comparisons (all p > 0.76) are unlikely to be artifacts of this assumption violation, as the large sample size provides protection against moderate departures from normality.

Context

This violation does not invalidate the main findings regarding therapy type differences. The homogeneity of variance assumption

Table 9

Assumption Diagnostics

Complete Assumption Test Results

Complete summary of assumption tests and diagnostic checks

teststatisticp_valueconclusion
Slope HomogeneityF = 1.3970.243PASS (p > 0.05)
Normality (Shapiro-Wilk)W = 0.9413.62e-13FAIL (p < 0.05)
Homogeneity of Variance (Levene)F = 0.3110.817PASS (p > 0.05)
Outliers (|studentized| > 3)0 outliersPASS (no outliers)

Interpretation

Purpose

This section validates whether the ANCOVA model meets its four critical statistical assumptions: homogeneity of regression slopes, normality of residuals, homogeneity of variance, and independence of observations. These assumptions are essential for ensuring that the comparison of therapy type effects on outcomes is statistically valid and reliable.

Key Findings

  • Normality Assumption: FAILED (p < 0.001) - Residuals deviate significantly from normal distribution, as shown in the Q-Q plot where sample quantiles diverge from theoretical values
  • Homogeneity of Variance: PASSED (Levene's p = 0.817) - Variance is equal across therapy groups, supporting valid group comparisons
  • Slope Homogeneity: PASSED (p = 0.243) - Regression slopes are consistent across groups, validating the covariate adjustment approach
  • Outliers: NONE DETECTED - All 500 observations are retained with no extreme values (|studentized| > 3)

Interpretation

The analysis reveals a critical violation: residuals are non-normally distributed despite adequate sample size (n=500) and absence of outliers. This suggests the outcome variable may have inherent distributional properties that violate ANCOVA's normality requirement. However, the non-significant main effect (F=0.324

Table 10

Covariate Effects

Individual Covariate Contributions

Individual covariate contributions to the model

covariatef_statp_valueeta_sq
Symptom Severity (1-10)0.0480.8260
Age0.110.7410
Sleep Quality (1-10)3.620.05770.007

Interpretation

Purpose

This section isolates the independent contribution of each baseline characteristic (symptom severity, age, sleep quality) to the outcome, after accounting for therapy type and other covariates. Significant covariates act as confounders that may differ across therapy groups; controlling for them ensures observed therapy differences reflect true treatment effects rather than pre-existing baseline imbalances.

Key Findings

  • Sleep Quality (1-10): F = 3.62, p = 0.058, η² = 0.01 — Marginally non-significant but the strongest covariate effect, explaining ~1% of outcome variance
  • Symptom Severity (1-10): F = 0.05, p = 0.826, η² = 0 — Negligible contribution; essentially no independent relationship with outcome
  • Age: F = 0.11, p = 0.741, η² = 0 — Minimal effect; age differences do not meaningfully predict outcome variation

Interpretation

None of the three covariates reached statistical significance (all p > 0.05), indicating that baseline differences in symptom severity, age, and sleep quality do not substantially confound the therapy comparison. Sleep quality approached significance but still failed to meet the 0.05 threshold. This suggests the therapy groups were reasonably balanced on these characteristics, and

Want to run this analysis on your own data? Upload CSV — Free Analysis See Pricing