Project 001 Memo

MemoA05

ClientDr. ABC

Client OrganizationABC Department

Version2.0

StatusDraft

ClassificationInternal use only

Note: The primary model uses emergency stay and CTAS. The cohort is the linked subset from Memo A04, not every hospitalized visit.

1 Overview

1.1 Introduction

The primary model asks whether emergency department length of stay and CTAS are associated with inpatient length of stay. The cohort consists of the visits that Memo A04 linked to a DAD abstract, not all hospitalized visits. Memo A04 compares linked and unlinked visits on CTAS and emergency stay. Other covariates are in the appendix. A sensitivity analysis repeats the primary model with acute length of stay, which removes alternate-level-of-care days.

The primary outcome is los_days. Memo A00 defines it as the calendar days from the admission date to the discharge date. Total emergency stay is the stay measure for this question. The concern that minutes after the disposition decision follow the admission decision applies to predicting hospitalization, not to length of stay among patients already admitted. The coefficient is a difference in days, not an odds ratio. A result is statistically significant when its t-test p value is below 0.05. Significant rows and their interpretations are shown on a yellow background. These are associations in synthetic records, not causal effects.

Data preparation is completed in Memo A00. Linkage is completed in Memo A04. This memo does not rebuild either step.

The model is fitted by ordinary least squares. For visit \(i\),

\[\mathrm{StayDays}_i = \beta_0 + \beta_1 x_i + \varepsilon_i.\]

\(\mathrm{StayDays}_i\) is los_days. Reference levels match Memo A03: CTAS level 1, sex F, health zone Edmonton, and arrival mode Walk-in. Binary indicators use 0 as the reference. Duration terms are fitted per minute. The table also shows the coefficient rescaled to 60 minutes; the p value is unchanged because it comes from the same test.

1.2 Data

Training data notice: The visits are randomly generated synthetic records. This is the linked subset of hospitalized visits, not every hospitalized visit.

Inpatient length of stay in the linked cohort

Cohort	Visits	Mean calendar stay, days	Median calendar stay, days	Mean acute stay, days	Median acute stay, days	Minimum	Maximum
A04 linked visits	4633	4.79	4	4.57	4	1	29

2 Primary model

The primary model enters emergency department length of stay and CTAS together. CTAS uses level 1 as the reference. The two single-covariate models are shown first so the adjusted result can be compared with the unadjusted one.

2.1 Emergency department length of stay

\[ \mathrm{StayDays}_i = \beta_0 + \beta_{\mathrm{LOS}}\,\mathrm{LOS}_i + \varepsilon_i \]

Emergency department length of stay alone

Term	Coefficient, days	95% CI	P value
Emergency department length of stay	0.002	0.002 to 0.003	<0.001
Emergency department length of stay, per 60 minutes	0.147	0.102 to 0.192	<0.001

In this single-covariate model, each additional minute of emergency department length of stay is associated with an inpatient stay 0.002 days longer (coefficient 0.002, 95% CI 0.002 to 0.003, p <0.001). Rescaled to 60 minutes, the coefficient is 0.147 days (95% CI 0.102 to 0.192). This association is statistically significant.

2.2 CTAS level

\[ \begin{aligned} \mathrm{StayDays}_i &= \beta_0 + \beta_{2}\,\mathbf{1}(\mathrm{CTAS}_i = 2) + \beta_{3}\,\mathbf{1}(\mathrm{CTAS}_i = 3) \\ &\quad {}+ \beta_{4}\,\mathbf{1}(\mathrm{CTAS}_i = 4) + \beta_{5}\,\mathbf{1}(\mathrm{CTAS}_i = 5) + \varepsilon_i \end{aligned} \]

CTAS level alone

Term	Coefficient, days	95% CI	P value
CTAS level: 2 vs 1	-1.134	-1.310 to -0.957	<0.001
CTAS level: 3 vs 1	-1.678	-1.869 to -1.487	<0.001
CTAS level: 4 vs 1	-2.248	-2.505 to -1.991	<0.001
CTAS level: 5 vs 1	-2.759	-3.188 to -2.330	<0.001

In this single-covariate model, compared with CTAS 1, CTAS 2 is associated with an inpatient stay 1.134 days shorter (coefficient -1.134, 95% CI -1.310 to -0.957, p <0.001). This association is statistically significant.

In this single-covariate model, compared with CTAS 1, CTAS 3 is associated with an inpatient stay 1.678 days shorter (coefficient -1.678, 95% CI -1.869 to -1.487, p <0.001). This association is statistically significant.

In this single-covariate model, compared with CTAS 1, CTAS 4 is associated with an inpatient stay 2.248 days shorter (coefficient -2.248, 95% CI -2.505 to -1.991, p <0.001). This association is statistically significant.

In this single-covariate model, compared with CTAS 1, CTAS 5 is associated with an inpatient stay 2.759 days shorter (coefficient -2.759, 95% CI -3.188 to -2.330, p <0.001). This association is statistically significant.

This is the primary model. It enters emergency department length of stay and CTAS together. CTAS level 1 remains the reference. Each coefficient is adjusted for the other covariate.

\[ \begin{aligned} \mathrm{StayDays}_i &= \beta_0 + \beta_{\mathrm{LOS}}\,\mathrm{LOS}_i + \beta_{2}\,\mathbf{1}(\mathrm{CTAS}_i = 2) \\ &\quad {}+ \beta_{3}\,\mathbf{1}(\mathrm{CTAS}_i = 3) + \beta_{4}\,\mathbf{1}(\mathrm{CTAS}_i = 4) \\ &\quad {}+ \beta_{5}\,\mathbf{1}(\mathrm{CTAS}_i = 5) + \varepsilon_i \end{aligned} \]

Calendar stay on emergency stay and CTAS

Term	Coefficient, days	95% CI	P value
Emergency department length of stay	-0.0002	-0.0009 to 0.0006	0.622
Emergency department length of stay, per 60 minutes	-0.011	-0.056 to 0.034	0.622
CTAS level: 2 vs 1	-1.141	-1.320 to -0.962	<0.001
CTAS level: 3 vs 1	-1.691	-1.888 to -1.494	<0.001
CTAS level: 4 vs 1	-2.264	-2.529 to -1.999	<0.001
CTAS level: 5 vs 1	-2.779	-3.214 to -2.343	<0.001

Interpretation

After adjustment for the other covariates in this model, each additional minute of emergency department length of stay is associated with an inpatient stay 0.0002 days shorter (coefficient -0.0002, 95% CI -0.0009 to 0.0006, p 0.622). Rescaled to 60 minutes, the coefficient is -0.011 days (95% CI -0.056 to 0.034). This association is not statistically significant.

After adjustment for the other covariates in this model, compared with CTAS 1, CTAS 2 is associated with an inpatient stay 1.141 days shorter (coefficient -1.141, 95% CI -1.320 to -0.962, p <0.001). This association is statistically significant.

After adjustment for the other covariates in this model, compared with CTAS 1, CTAS 3 is associated with an inpatient stay 1.691 days shorter (coefficient -1.691, 95% CI -1.888 to -1.494, p <0.001). This association is statistically significant.

After adjustment for the other covariates in this model, compared with CTAS 1, CTAS 4 is associated with an inpatient stay 2.264 days shorter (coefficient -2.264, 95% CI -2.529 to -1.999, p <0.001). This association is statistically significant.

After adjustment for the other covariates in this model, compared with CTAS 1, CTAS 5 is associated with an inpatient stay 2.779 days shorter (coefficient -2.779, 95% CI -3.214 to -2.343, p <0.001). This association is statistically significant.

3 Sensitivity: acute length of stay

acute_los_days is calendar stay after alternate-level-of-care days are removed. The specification is otherwise the same as the primary model. This checks whether the emergency-stay and CTAS associations depend on whether those days are counted.

\[ \begin{aligned} \mathrm{AcuteDays}_i &= \beta_0 + \beta_{\mathrm{LOS}}\,\mathrm{LOS}_i + \beta_{2}\,\mathbf{1}(\mathrm{CTAS}_i = 2) \\ &\quad {}+ \beta_{3}\,\mathbf{1}(\mathrm{CTAS}_i = 3) + \beta_{4}\,\mathbf{1}(\mathrm{CTAS}_i = 4) \\ &\quad {}+ \beta_{5}\,\mathbf{1}(\mathrm{CTAS}_i = 5) + \varepsilon_i \end{aligned} \]

Acute stay on emergency stay and CTAS

Term	Coefficient, days	95% CI	P value
Emergency department length of stay	-0.0001	-0.0009 to 0.0006	0.733
Emergency department length of stay, per 60 minutes	-0.008	-0.054 to 0.038	0.733
CTAS level: 2 vs 1	-1.143	-1.325 to -0.962	<0.001
CTAS level: 3 vs 1	-1.699	-1.899 to -1.498	<0.001
CTAS level: 4 vs 1	-2.181	-2.450 to -1.912	<0.001
CTAS level: 5 vs 1	-2.695	-3.137 to -2.252	<0.001

Interpretation

After adjustment for the other covariates in this model, each additional minute of emergency department length of stay is associated with an acute stay 0.0001 days shorter (coefficient -0.0001, 95% CI -0.0009 to 0.0006, p 0.733). Rescaled to 60 minutes, the coefficient is -0.008 days (95% CI -0.054 to 0.038). This association is not statistically significant.

After adjustment for the other covariates in this model, compared with CTAS 1, CTAS 2 is associated with an acute stay 1.143 days shorter (coefficient -1.143, 95% CI -1.325 to -0.962, p <0.001). This association is statistically significant.

After adjustment for the other covariates in this model, compared with CTAS 1, CTAS 3 is associated with an acute stay 1.699 days shorter (coefficient -1.699, 95% CI -1.899 to -1.498, p <0.001). This association is statistically significant.

After adjustment for the other covariates in this model, compared with CTAS 1, CTAS 4 is associated with an acute stay 2.181 days shorter (coefficient -2.181, 95% CI -2.450 to -1.912, p <0.001). This association is statistically significant.

After adjustment for the other covariates in this model, compared with CTAS 1, CTAS 5 is associated with an acute stay 2.695 days shorter (coefficient -2.695, 95% CI -3.137 to -2.252, p <0.001). This association is statistically significant.

4 Appendix

The models below are exploratory. They do not answer the research question. ambulance_flag is omitted because it is a recode of arrival mode. Pre-disposition stay is not entered alongside total emergency stay.

4.1 Age

\[ \mathrm{StayDays}_i = \beta_0 + \beta_{\mathrm{Age}}\,\mathrm{Age}_i + \varepsilon_i \]

Age alone

Term	Coefficient, days	95% CI	P value
Age	0.022	0.018 to 0.026	<0.001

In this single-covariate model, each additional year of age is associated with an inpatient stay 0.022 days longer (coefficient 0.022, 95% CI 0.018 to 0.026, p <0.001). This association is statistically significant.

4.2 Sex

\[ \mathrm{StayDays}_i = \beta_0 + \beta_{\text{M}}\,\mathbf{1}(\mathrm{Sex}_i = \text{M}) + \varepsilon_i \]

Sex alone

Term	Coefficient, days	95% CI	P value
Sex: M vs F	-0.121	-0.270 to 0.027	0.109

In this single-covariate model, compared with F, M is associated with an inpatient stay 0.121 days shorter (coefficient -0.121, 95% CI -0.270 to 0.027, p 0.109). This association is not statistically significant.

4.3 Health zone

\[ \begin{aligned} \mathrm{StayDays}_i &= \beta_0 + \beta_{\text{Calgary}}\,\mathbf{1}(\mathrm{Zone}_i = \text{Calgary}) + \beta_{\text{Central}}\,\mathbf{1}(\mathrm{Zone}_i = \text{Central}) \\ &\quad {}+ \beta_{\text{North}}\,\mathbf{1}(\mathrm{Zone}_i = \text{North}) + \beta_{\text{South}}\,\mathbf{1}(\mathrm{Zone}_i = \text{South}) + \varepsilon_i \end{aligned} \]

Health zone alone

Term	Coefficient, days	95% CI	P value
Health zone: Calgary vs Edmonton	-0.064	-0.243 to 0.116	0.487
Health zone: Central vs Edmonton	-0.046	-0.296 to 0.203	0.715
Health zone: North vs Edmonton	0.013	-0.275 to 0.301	0.928
Health zone: South vs Edmonton	-0.177	-0.423 to 0.070	0.161

In this single-covariate model, compared with Edmonton, Calgary is associated with an inpatient stay 0.064 days shorter (coefficient -0.064, 95% CI -0.243 to 0.116, p 0.487). This association is not statistically significant.

In this single-covariate model, compared with Edmonton, Central is associated with an inpatient stay 0.046 days shorter (coefficient -0.046, 95% CI -0.296 to 0.203, p 0.715). This association is not statistically significant.

In this single-covariate model, compared with Edmonton, North is associated with an inpatient stay 0.013 days longer (coefficient 0.013, 95% CI -0.275 to 0.301, p 0.928). This association is not statistically significant.

In this single-covariate model, compared with Edmonton, South is associated with an inpatient stay 0.177 days shorter (coefficient -0.177, 95% CI -0.423 to 0.070, p 0.161). This association is not statistically significant.

4.4 Arrival mode

\[ \mathrm{StayDays}_i = \beta_0 + \beta_{\text{Ground ambulance}}\,\mathbf{1}(\mathrm{Arrival}_i = \text{Ground ambulance}) + \varepsilon_i \]

Arrival mode alone

Term	Coefficient, days	95% CI	P value
Arrival mode: Ground ambulance vs Walk-in	0.358	0.159 to 0.557	<0.001

In this single-covariate model, compared with Walk-in, Ground ambulance is associated with an inpatient stay 0.358 days longer (coefficient 0.358, 95% CI 0.159 to 0.557, p <0.001). This association is statistically significant.

4.5 Injury indicator

\[ \mathrm{StayDays}_i = \beta_0 + \beta_{\mathrm{Injury}}\,\mathrm{Injury}_i + \varepsilon_i \]

Injury indicator alone

Term	Coefficient, days	95% CI	P value
Injury indicator	-0.216	-0.499 to 0.067	0.135

In this single-covariate model, a value of 1 on the injury indicator, compared with 0, is associated with an inpatient stay 0.216 days shorter (coefficient -0.216, 95% CI -0.499 to 0.067, p 0.135). This association is not statistically significant.

4.6 Mental health indicator

\[ \mathrm{StayDays}_i = \beta_0 + \beta_{\mathrm{MH}}\,\mathrm{MH}_i + \varepsilon_i \]

Mental health indicator alone

Term	Coefficient, days	95% CI	P value
Mental health indicator	-0.277	-0.711 to 0.157	0.211

In this single-covariate model, a value of 1 on the mental health indicator, compared with 0, is associated with an inpatient stay 0.277 days shorter (coefficient -0.277, 95% CI -0.711 to 0.157, p 0.211). This association is not statistically significant.

4.7 Pain score

\[ \mathrm{StayDays}_i = \beta_0 + \beta_{\mathrm{Pain}}\,\mathrm{Pain}_i + \varepsilon_i \]

Pain score alone

Term	Coefficient, days	95% CI	P value
Pain score	0.014	-0.009 to 0.038	0.228

In this single-covariate model, each additional point on the pain score is associated with an inpatient stay 0.014 days longer (coefficient 0.014, 95% CI -0.009 to 0.038, p 0.228). This association is not statistically significant.

4.8 Triage wait

\[ \mathrm{StayDays}_i = \beta_0 + \beta_{\mathrm{TriageWait}}\,\mathrm{TriageWait}_i + \varepsilon_i \]

Triage wait alone

Term	Coefficient, days	95% CI	P value
Triage wait	-0.120	-0.139 to -0.100	<0.001
Triage wait, per 60 minutes	-7.174	-8.363 to -5.985	<0.001

In this single-covariate model, each additional minute of triage wait is associated with an inpatient stay 0.120 days shorter (coefficient -0.120, 95% CI -0.139 to -0.100, p <0.001). Rescaled to 60 minutes, the coefficient is -7.174 days (95% CI -8.363 to -5.985). This association is statistically significant.

4.9 Physician wait

\[ \mathrm{StayDays}_i = \beta_0 + \beta_{\mathrm{PhysWait}}\,\mathrm{PhysWait}_i + \varepsilon_i \]

Physician wait alone

Term	Coefficient, days	95% CI	P value
Physician wait	-0.055	-0.063 to -0.048	<0.001
Physician wait, per 60 minutes	-3.329	-3.785 to -2.873	<0.001

In this single-covariate model, each additional minute of physician wait is associated with an inpatient stay 0.055 days shorter (coefficient -0.055, 95% CI -0.063 to -0.048, p <0.001). Rescaled to 60 minutes, the coefficient is -3.329 days (95% CI -3.785 to -2.873). This association is statistically significant.

4.10 Pre-disposition stay

These minutes are already included in total emergency stay, so this appendix model is not entered alongside it. The primary model uses total emergency stay.

\[ \mathrm{StayDays}_i = \beta_0 + \beta_{\mathrm{PreLOS}}\,\mathrm{PreLOS}_i + \varepsilon_i \]

Pre-disposition stay alone

Term	Coefficient, days	95% CI	P value
Pre-disposition stay	0.003	0.002 to 0.003	<0.001
Pre-disposition stay, per 60 minutes	0.158	0.112 to 0.204	<0.001

In this single-covariate model, each additional minute before the disposition decision is associated with an inpatient stay 0.003 days longer (coefficient 0.003, 95% CI 0.002 to 0.003, p <0.001). Rescaled to 60 minutes, the coefficient is 0.158 days (95% CI 0.112 to 0.204). This association is statistically significant.

4.11 All selected covariates

This exploratory model includes every covariate from the simple models except pre-disposition stay. Each coefficient is adjusted for the other covariates. The linked cohort is small relative to the number of parameters, so these estimates are less stable than those of the primary model.

\[ \begin{aligned} \mathrm{StayDays}_i &= \beta_0 + \beta_{\mathrm{LOS}}\,\mathrm{LOS}_i + \beta_{2}\,\mathbf{1}(\mathrm{CTAS}_i = 2) \\ &\quad {}+ \beta_{3}\,\mathbf{1}(\mathrm{CTAS}_i = 3) + \beta_{4}\,\mathbf{1}(\mathrm{CTAS}_i = 4) \\ &\quad {}+ \beta_{5}\,\mathbf{1}(\mathrm{CTAS}_i = 5) + \beta_{\mathrm{Age}}\,\mathrm{Age}_i \\ &\quad {}+ \beta_{\text{M}}\,\mathbf{1}(\mathrm{Sex}_i = \text{M}) + \beta_{\text{Calgary}}\,\mathbf{1}(\mathrm{Zone}_i = \text{Calgary}) \\ &\quad {}+ \beta_{\text{Central}}\,\mathbf{1}(\mathrm{Zone}_i = \text{Central}) + \beta_{\text{North}}\,\mathbf{1}(\mathrm{Zone}_i = \text{North}) \\ &\quad {}+ \beta_{\text{South}}\,\mathbf{1}(\mathrm{Zone}_i = \text{South}) + \beta_{\text{Ground ambulance}}\,\mathbf{1}(\mathrm{Arrival}_i = \text{Ground ambulance}) \\ &\quad {}+ \beta_{\mathrm{Injury}}\,\mathrm{Injury}_i + \beta_{\mathrm{MH}}\,\mathrm{MH}_i \\ &\quad {}+ \beta_{\mathrm{Pain}}\,\mathrm{Pain}_i + \beta_{\mathrm{TriageWait}}\,\mathrm{TriageWait}_i \\ &\quad {}+ \beta_{\mathrm{PhysWait}}\,\mathrm{PhysWait}_i + \varepsilon_i \end{aligned} \]

Calendar stay on all selected covariates together

Term	Coefficient, days	95% CI	P value
Emergency department length of stay	-0.0002	-0.0010 to 0.0005	0.563
CTAS level: 2 vs 1	-1.112	-1.301 to -0.923	<0.001
CTAS level: 3 vs 1	-1.647	-1.882 to -1.412	<0.001
CTAS level: 4 vs 1	-2.177	-2.510 to -1.844	<0.001
CTAS level: 5 vs 1	-2.613	-3.130 to -2.097	<0.001
Age	0.012	0.008 to 0.016	<0.001
Sex: M vs F	-0.098	-0.239 to 0.042	0.171
Health zone: Calgary vs Edmonton	-0.009	-0.179 to 0.161	0.917
Health zone: Central vs Edmonton	-0.036	-0.272 to 0.201	0.767
Health zone: North vs Edmonton	-0.034	-0.307 to 0.239	0.807
Health zone: South vs Edmonton	-0.102	-0.335 to 0.132	0.393
Arrival mode: Ground ambulance vs Walk-in	0.039	-0.151 to 0.230	0.685
Injury indicator	0.029	-0.241 to 0.300	0.831
Mental health indicator	-0.093	-0.505 to 0.319	0.659
Pain score	0.014	-0.008 to 0.036	0.209
Triage wait	0.005	-0.021 to 0.030	0.717
Physician wait	0.001	-0.010 to 0.013	0.807

Interpretation

Sentences highlighted in yellow are statistically significant; the others are not.

After adjustment for the other covariates in this model, each additional minute of emergency department length of stay is associated with an inpatient stay 0.0002 days shorter (coefficient -0.0002, 95% CI -0.0010 to 0.0005, p 0.563). Rescaled to 60 minutes, the coefficient is -0.013 days (95% CI -0.058 to 0.032). This association is not statistically significant.

After adjustment for the other covariates in this model, compared with CTAS 1, CTAS 2 is associated with an inpatient stay 1.112 days shorter (coefficient -1.112, 95% CI -1.301 to -0.923, p <0.001). This association is statistically significant.

After adjustment for the other covariates in this model, compared with CTAS 1, CTAS 3 is associated with an inpatient stay 1.647 days shorter (coefficient -1.647, 95% CI -1.882 to -1.412, p <0.001). This association is statistically significant.

After adjustment for the other covariates in this model, compared with CTAS 1, CTAS 4 is associated with an inpatient stay 2.177 days shorter (coefficient -2.177, 95% CI -2.510 to -1.844, p <0.001). This association is statistically significant.

After adjustment for the other covariates in this model, compared with CTAS 1, CTAS 5 is associated with an inpatient stay 2.613 days shorter (coefficient -2.613, 95% CI -3.130 to -2.097, p <0.001). This association is statistically significant.

After adjustment for the other covariates in this model, each additional year of age is associated with an inpatient stay 0.012 days longer (coefficient 0.012, 95% CI 0.008 to 0.016, p <0.001). This association is statistically significant.

After adjustment for the other covariates in this model, compared with F, M is associated with an inpatient stay 0.098 days shorter (coefficient -0.098, 95% CI -0.239 to 0.042, p 0.171). This association is not statistically significant.

After adjustment for the other covariates in this model, compared with Edmonton, Calgary is associated with an inpatient stay 0.009 days shorter (coefficient -0.009, 95% CI -0.179 to 0.161, p 0.917). This association is not statistically significant.

After adjustment for the other covariates in this model, compared with Edmonton, Central is associated with an inpatient stay 0.036 days shorter (coefficient -0.036, 95% CI -0.272 to 0.201, p 0.767). This association is not statistically significant.

After adjustment for the other covariates in this model, compared with Edmonton, North is associated with an inpatient stay 0.034 days shorter (coefficient -0.034, 95% CI -0.307 to 0.239, p 0.807). This association is not statistically significant.

After adjustment for the other covariates in this model, compared with Edmonton, South is associated with an inpatient stay 0.102 days shorter (coefficient -0.102, 95% CI -0.335 to 0.132, p 0.393). This association is not statistically significant.

After adjustment for the other covariates in this model, compared with Walk-in, Ground ambulance is associated with an inpatient stay 0.039 days longer (coefficient 0.039, 95% CI -0.151 to 0.230, p 0.685). This association is not statistically significant.

After adjustment for the other covariates in this model, a value of 1 on the injury indicator, compared with 0, is associated with an inpatient stay 0.029 days longer (coefficient 0.029, 95% CI -0.241 to 0.300, p 0.831). This association is not statistically significant.

After adjustment for the other covariates in this model, a value of 1 on the mental health indicator, compared with 0, is associated with an inpatient stay 0.093 days shorter (coefficient -0.093, 95% CI -0.505 to 0.319, p 0.659). This association is not statistically significant.

After adjustment for the other covariates in this model, each additional point on the pain score is associated with an inpatient stay 0.014 days longer (coefficient 0.014, 95% CI -0.008 to 0.036, p 0.209). This association is not statistically significant.

After adjustment for the other covariates in this model, each additional minute of triage wait is associated with an inpatient stay 0.005 days longer (coefficient 0.005, 95% CI -0.021 to 0.030, p 0.717). Rescaled to 60 minutes, the coefficient is 0.285 days (95% CI -1.256 to 1.825). This association is not statistically significant.

After adjustment for the other covariates in this model, each additional minute of physician wait is associated with an inpatient stay 0.001 days longer (coefficient 0.001, 95% CI -0.010 to 0.013, p 0.807). Rescaled to 60 minutes, the coefficient is 0.084 days (95% CI -0.587 to 0.755). This association is not statistically significant.

5 Shared release

This memo uses unified synthetic release 2.0-2026-10-09, built from the same NACRS/DAD source files as A07–A09. Hospital location and patient residence are separate variables. See A00 for definitions and provenance.

These legacy descriptive regression specifications use conventional model-based standard errors. They do not account for the hospital clustering introduced in release 2.0, so their significance tests are for illustration only. A07–A09 explicitly handle the hospital structure for the asthma questions.