From c9bf9da58fde0ca3524d5a53c76080558a13314c Mon Sep 17 00:00:00 2001 From: Koen Derks Date: Thu, 7 Mar 2024 13:51:47 +0100 Subject: [PATCH] Update sample-evaluation.Rmd --- vignettes/articles/sample-evaluation.Rmd | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/vignettes/articles/sample-evaluation.Rmd b/vignettes/articles/sample-evaluation.Rmd index 530d2c459..b7ad8af54 100644 --- a/vignettes/articles/sample-evaluation.Rmd +++ b/vignettes/articles/sample-evaluation.Rmd @@ -271,7 +271,7 @@ summary(result_pp) In this scenario, the output indicates that the estimated misstatement in the population is 4.18 percent, with the 95 percent credible interval extending from -3.29 percent to 5.33 percent. Note that this population estimate is considerably +3.28 percent to 5.36 percent. Note that this population estimate is considerably less uncertain compared to the no pooling approach. Similarly to the no pooling approach, the stratum estimates differ from each other but are closer together and exhibit less uncertainty. This can be explained by the fact that the partial @@ -424,8 +424,8 @@ print(result) ``` The output indicates that the estimated misstatement in the population is -15.42 percent. The 95 percent credible interval spans from 14.65 percent to -16.3 percent. The precision of the population estimate is therefore 1.65 +15.32 percent. The 95 percent credible interval spans from 14.65 percent to +16.29 percent. The precision of the population estimate is therefore 1.64 percent, which is lower than that of the classical approach. The estimates for each stratum are visualized below using the `plot(..., type = "estimates)` command but their actual values can be once again be obtained using the