Regression Analysis — SeekingChartis Corpus

🛡️ Public data only — no PHI permitted on this instance.

37.0%

R²

36.7%

Adj R²

4,858

Observations

Features

135.1

F-Statistic

0.1498

RMSE (avg error)

R² = fraction of variance explained (1.0 = perfect, 0 = no signal). RMSE = root mean squared error (average prediction miss in target units). F-statistic tests whether the model explains more than random chance.

Intercept Interpretation

Value: -0.0607

SE: 0.0021

Target Mean: -0.0607

Target Range: -0.5000 — 1.0000

When all features are at their mean values, the predicted operating margin is -0.06

Coefficients (Standardized)

Target: Operating Margin. Standardized coefficients (-1.0 to +1.0): a one-SD increase in the feature produces this fraction of the strongest effect. *** p<0.001, ** p<0.01, * p<0.05.

Variable	Strength	t	p-value	Sig	95% CI
Revenue Per Bed	+1.000	27.5	0.0000	***	[0.234, 0.270]
Expense Per Bed	-0.925	27.4	0.0000	***	[-0.250, -0.217]
Net Income	+0.207	19.2	0.0000	***	[0.047, 0.057]
Bed Days Available	+0.195	2.8	0.0056	**	[0.014, 0.084]
Total Patient Days	-0.189	1.9	0.0515	ns	[-0.096, 0.000]
Occupancy Rate	+0.136	9.7	0.0000	***	[0.027, 0.041]
Medicare Intensity	-0.124	1.4	0.1580	ns	[-0.074, 0.012]
Medicare Days	+0.097	1.1	0.2791	ns	[-0.020, 0.069]
Operating Expenses	-0.088	7.4	0.0000	***	[-0.028, -0.016]
Contractual Allowances	+0.077	6.1	0.0000	***	[0.013, 0.026]
Medicaid Day Pct	-0.065	6.5	0.0000	***	[-0.021, -0.011]
Revenue Per Day	-0.056	5.3	0.0000	***	[-0.019, -0.009]
Net Patient Revenue	-0.051	3.7	0.0002	***	[-0.020, -0.006]
Gross Patient Revenue	+0.049	5.8	0.0000	***	[0.008, 0.016]
Size Quartile	+0.043	2.6	0.0087	**	[0.003, 0.019]
Medicare Day Pct	+0.042	5.4	0.0000	***	[0.007, 0.014]
Medicaid Days	+0.041	2.9	0.0039	**	[0.003, 0.017]
Net To Gross Ratio	+0.011	1.0	0.3260	ns	[-0.003, 0.008]
Payer Diversity	-0.006	0.5	0.6110	ns	[-0.008, 0.004]
Beds	+0.005	0.0	0.9632	ns	[-0.050, 0.053]
Commercial Pct	-0.002	0.2	0.8272	ns	[-0.004, 0.004]

Univariate Correlations with Target

Pearson r for each feature vs Operating Margin. Shows raw linear relationship before controlling for other variables.

Feature	r	Strength
Net Income	0.415	Moderate
Occupancy Rate	0.193	Weak
Size Quartile	0.106	Weak
Medicaid Day Pct	-0.098	Weak
Revenue Per Bed	0.090	Weak
Contractual Allowances	0.089	Weak
Commercial Pct	0.087	Weak
Gross Patient Revenue	0.082	Weak
Net To Gross Ratio	-0.074	Weak
Medicare Days	0.062	Weak
Expense Per Bed	-0.059	Weak
Net Patient Revenue	0.048	Weak
Total Patient Days	0.048	Weak
Payer Diversity	-0.046	Weak
Bed Days Available	0.043	Weak
Medicare Intensity	0.041	Weak
Operating Expenses	-0.037	Weak
Revenue Per Day	0.037	Weak
Beds	0.034	Weak
Medicare Day Pct	-0.025	Weak
Medicaid Days	-0.008	Weak

Hospital Outliers (Residual Analysis)

Hospitals with the largest standardized residuals. >2σ = model underpredicts/overpredicts — investigate for deal opportunities or data quality issues.

Hospital	State	Actual	Predicted	Residual
FRED HUTCHINSON CANCER CENTER	WA	-0.5000	-2.2188	+11.47σ
MIDWESTERN REGIONAL MEDICAL CENTER	IL	0.8047	2.4469	-10.96σ
NATIONAL JEWISH HEALTH	CO	-0.5000	-1.5663	+7.12σ
HEARTLAND REGIONAL MEDICAL CENTER	IL	1.0000	0.0190	+6.55σ
GALESBURG COTTAGE HOSPITAL	IL	0.8244	-0.0193	+5.63σ
MERCY WALWORTH HOSPITAL	WI	0.0443	0.8091	-5.10σ
WENATCHEE VALLEY HOSPITAL	WA	-0.0488	0.6332	-4.55σ
SPECTRUM HEALTH REED CITY	MI	0.2124	-0.4488	+4.41σ
IZARD REGIONAL HOSPITAL	AR	-0.5000	0.1544	-4.37σ
PARKLAND HLTH CTR - BONNE TERRE	MO	0.0305	0.6483	-4.12σ
MEMORIAL HOSPITAL FOR CANCER AND AL	NY	-0.3248	-0.8979	+3.83σ
UNIVERSITY HEALTH SYSTEM	TX	-0.5000	-1.0518	+3.68σ
STANFORD HEALTH CARE	CA	0.0367	0.5649	-3.53σ
CLEVELAND CLINIC HOSPITAL	OH	-0.1769	-0.7044	+3.52σ
MASSACHUSETTS GENERAL HOSPITAL	MA	-0.4491	-0.9746	+3.51σ

Variance Inflation Factors

VIF > 10 = severe multicollinearity (coefficient estimates unreliable). VIF > 5 = moderate. Consider removing high-VIF features.

Feature	VIF	Status
Net Patient Revenue	999.0	High
Operating Expenses	999.0	High
Medicare Day Pct	999.0	High
Medicaid Day Pct	999.0	High
Net Income	999.0	High
Gross Patient Revenue	999.0	High
Contractual Allowances	999.0	High
Commercial Pct	999.0	High
Beds	148.3	High
Total Patient Days	129.8	High
Medicare Days	110.6	High
Medicare Intensity	105.6	High

Model Fit by State

How well the national model predicts within each state. Low R² states have unique market dynamics not captured by national features — consider state-specific models.

State	n	R²	Mean Residual
DE	8	79.7%	0.0000
AK	18	64.3%	0.0000
NH	27	62.7%	-0.0000
GA	149	51.3%	0.0000
TX	320	51.2%	0.0000
SC	68	47.3%	0.0000
FL	192	46.9%	0.0000
CA	317	44.9%	-0.0000
OR	57	44.6%	-0.0000
NE	77	44.1%	0.0000
NJ	79	43.5%	-0.0000
NV	49	42.6%	-0.0000
AL	87	40.3%	-0.0000
NM	36	40.2%	0.0000
TN	72	40.1%	0.0000

Top Pairwise Correlations

Variable 1	Variable 2	r
Gross Patient Revenue	Contractual Allowances	0.992
Beds	Bed Days Available	0.984
Net Patient Revenue	Operating Expenses	0.982
Total Patient Days	Bed Days Available	0.976
Beds	Total Patient Days	0.962
Medicare Days	Medicare Intensity	0.955
Revenue Per Bed	Expense Per Bed	0.953
Net Patient Revenue	Gross Patient Revenue	0.912
Total Patient Days	Medicare Days	0.901
Operating Expenses	Gross Patient Revenue	0.891
Beds	Medicare Intensity	0.881
Net Patient Revenue	Total Patient Days	0.879
Medicare Days	Bed Days Available	0.874
Operating Expenses	Total Patient Days	0.869
Total Patient Days	Gross Patient Revenue	0.863

Market Heatmap Analysis Hub Regression JSON API Operating Margin Revenue/Bed Occupancy Net-to-Gross