Before we get into determining whether CSMC’s and MRDH’s Community Resource Coordinators are having a statistically significant effect on the department, let’s quickly look at their caseload from Feb 1, 2020 to Apr 30, 2023.
CRC Report
# A tibble: 2 × 2
metCRC n
<lgl> <int>
1 FALSE 15837
2 TRUE 4832
We can see that the CRCs had 4832 interactions with homeless patients. 15837 homeless encounters did not include a CRC interaction.
Effect on gap between visits
To test whether the CRCs’ work has a statistically significant effect on ED utilization frequency by homeless patients, we’ll perform a t-test to compare the average number of days between ED visits for patients who returned after encountering a CRC vs. those who returned after not encountering a CRC.
In this test, for patients who returned after encountering a CRC, n = 2480. For patients who returned after not encountering a CRC in their previous visit, n = 9002.
Welch Two Sample t-test
data: sawCRC and noCRC
t = 4.8616, df = 3636.8, p-value = 1.214e-06
alternative hypothesis: true difference in means is not equal to 0
95 percent confidence interval:
10.04624 23.62577
sample estimates:
mean of x mean of y
84.60161 67.76561
From this output, we can say that we’re 95% confident that CRC interactions had an impact on the rate of return for repeat homeless visitors seen between Feb 1, 2020 to Apr 30, 2023, equal to somewhere between 10 and 23.6 extra days between visits.
Effect on rate of visits over 90 days
To look further, we’ll compare the average number of visits in a 90-day period for patients who encountered CRCs vs. those who didn’t. Data used for this test is visits from Feb 1, 2020 to Jan 30, 2023, to allow for the appropriate 90-day measurement window.
In this test, for ED encounters by patients who met with a CRC, n = 4443. For ED encounters by patients who hadn’t met with a CRC, n = 14468.
Welch Two Sample t-test
data: sawCRC90days and noCRC90days
t = -9.4677, df = 9142.4, p-value < 2.2e-16
alternative hypothesis: true difference in means is not equal to 0
95 percent confidence interval:
-1.0534799 -0.6920755
sample estimates:
mean of x mean of y
1.952284 2.825062
From these results, we’re 95% confident that CRC interactions have a statistically significant impact on homeless patients’ rate of visits per 90 days, with patients who saw them being seen somewhere between 0.7 to 1.1 fewer times over the next 90 days.
Effect on rate of visits over 180 days
Expanding the window to 180 days also demonstrates value in the CRC program. Data used for this test is visits from Feb 1, 2020 to Nov 1, 2022, to allow for the appropriate 180-day measurement window.
In this test, for ED encounters by patients who met with a CRC, n = 4127. For ED encounters by patients who hadn’t met with a CRC, n = 13422.
Welch Two Sample t-test
data: sawCRC180days and noCRC180days
t = -9.4258, df = 8604.8, p-value < 2.2e-16
alternative hypothesis: true difference in means is not equal to 0
95 percent confidence interval:
-1.796176 -1.177710
sample estimates:
mean of x mean of y
3.080930 4.567874
From these results, we’re 95% confident that CRC interactions have a statistically significant impact on homeless patients’ rate of visits per 180 days, with patients who saw them being seen somewhere between 1.2 to 1.8 fewer times over the next 180 days.