83
75.9 (65.3 - 84.6)
78.9 ( 67.5 - 87)
-83.132 (65.85 - 95.6)
+83.150 (65.89 - 95.5)
0.06
@@ -571,7 +574,7 @@
20
25.0 ( 8.7 - 49.1)
14.8 ( 3.8 - 44)
-0.414 ( 0.28 - 29.9)
+0.425 ( 0.28 - 29.9)
0.59
@@ -583,7 +586,7 @@
23
65.2 (42.7 - 83.6)
44.8 ( 16.0 - 78)
-31.518 ( 0.40 - 81.1)
+31.506 ( 0.40 - 81.1)
0.38
@@ -693,19 +696,22 @@
outcome_01_adj_tbl %>%
filter(str_detect(numerator,"outcome")) %>%
- ggplot_prevalence_ii(
+ ggplot_prevalence(
denominator_level = denominator_level,
numerator = numerator,
proportion = prop,
proportion_upp = prop_upp,
proportion_low = prop_low) +
- theme(axis.text.x = element_text(angle = 0, vjust = 0, hjust=0)) +
- # coord_flip() +
- facet_wrap(denominator~.,scales = "free") +
- # facet_grid(denominator~.,scales = "free_y") +
- colorspace::scale_color_discrete_qualitative() +
- labs(title = "Prevalence of numerators across denominators",
- y = "Prevalence",x = "")
+ # theme(axis.text.x = element_text(angle = 0, vjust = 0, hjust=0)) +
+ scale_y_continuous(
+ labels = scales::percent_format(accuracy = 1),
+ breaks = scales::pretty_breaks(n = 5)) +
+ # coord_flip() +
+ facet_wrap(denominator~.,scales = "free") +
+ # facet_grid(denominator~.,scales = "free_y") +
+ colorspace::scale_color_discrete_qualitative() +
+ labs(title = "Prevalence of numerators across denominators",
+ y = "Prevalence",x = "")
diff --git a/docs/articles/howto-reprex_files/figure-html/unnamed-chunk-12-1.png b/docs/articles/howto-reprex_files/figure-html/unnamed-chunk-12-1.png
index 5e59e18..7a8e8ad 100644
Binary files a/docs/articles/howto-reprex_files/figure-html/unnamed-chunk-12-1.png and b/docs/articles/howto-reprex_files/figure-html/unnamed-chunk-12-1.png differ
diff --git a/docs/articles/index.html b/docs/articles/index.html
index 1987128..fdbb977 100644
--- a/docs/articles/index.html
+++ b/docs/articles/index.html
@@ -88,6 +88,9 @@
Workflow: How to use the serosurvey R package?
+
+ Introduction: serosurvey R package
+
@@ -121,6 +124,7 @@ All vignettes
diff --git a/docs/articles/intro.html b/docs/articles/intro.html
new file mode 100644
index 0000000..9ea4134
--- /dev/null
+++ b/docs/articles/intro.html
@@ -0,0 +1,357 @@
+
+
+
+
+
+
+
+Introduction: serosurvey R package • serosurvey
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ Introduction: serosurvey R package
+
+
+
+ intro.Rmd
+
+
+
+
+
+
+
+Introduction
+Here we present three examples, definitions and related references:
+
+
+
+1. survey: Estimate single prevalences
+
+-
+
From a srvyr survey design object, serosvy_proportion estimates:
+
+- weighted prevalence (
prop),
+- total population (
total),
+- raw proportion (
raw_prop),
+- coefficient of variability (
cv),
+- design effect (
deff)
+
+
+
+serosvy_proportion(design = design,
+ denominator = covariate_01,
+ numerator = outcome_one)
+#> # A tibble: 6 x 23
+#> denominator denominator_lev~ numerator numerator_level prop prop_low
+#> <chr> <fct> <chr> <fct> <dbl> <dbl>
+#> 1 covariate_~ E outcome_~ No 0.211 0.130
+#> 2 covariate_~ E outcome_~ Yes 0.789 0.675
+#> 3 covariate_~ H outcome_~ No 0.852 0.564
+#> 4 covariate_~ H outcome_~ Yes 0.148 0.0377
+#> 5 covariate_~ M outcome_~ No 0.552 0.224
+#> 6 covariate_~ M outcome_~ Yes 0.448 0.160
+#> # ... with 17 more variables: prop_upp <dbl>, prop_cv <dbl>,
+#> # prop_se <dbl>, total <dbl>, total_low <dbl>, total_upp <dbl>,
+#> # total_cv <dbl>, total_se <dbl>, total_deff <dbl>, total_den <dbl>,
+#> # total_den_low <dbl>, total_den_upp <dbl>, raw_num <int>,
+#> # raw_den <int>, raw_prop <dbl>, raw_prop_low <dbl>, raw_prop_upp <dbl>
+
+
+
+
+2. survey: Estimate multiple prevalences
+
+-
+
In the Article tab we provide a workflow to estimate multiple prevalences:
+
+- using different set of covariates and outcomes as numerators or denominators,
+- in one single pipe operation
+
+
+
+# crear matriz
+ #
+ # set 01 of denominator-numerator
+ #
+expand_grid(
+ design=list(design),
+ denominator=c("covariate_01","covariate_02"), # covariates
+ numerator=c("outcome_one","outcome_two") # outcomes
+ ) %>%
+ #
+ # set 02 of denominator-numerator (e.g. within main outcome)
+ #
+ union_all(
+ expand_grid(
+ design=list(design),
+ denominator=c("outcome_one","outcome_two"), # outcomes
+ numerator=c("covariate_02") # covariates
+ )
+ ) %>%
+ #
+ # create symbols (to be readed as arguments)
+ #
+ mutate(
+ denominator=map(denominator,dplyr::sym),
+ numerator=map(numerator,dplyr::sym)
+ ) %>%
+ #
+ # estimate prevalence
+ #
+ mutate(output=pmap(.l = select(.,design,denominator,numerator),
+ .f = serosvy_proportion)) %>%
+ #
+ # show the outcome
+ #
+ select(-design,-denominator,-numerator) %>%
+ unnest(cols = c(output)) %>%
+ print(n=Inf)
+#> # A tibble: 25 x 23
+#> denominator denominator_lev~ numerator numerator_level prop prop_low
+#> <chr> <fct> <chr> <fct> <dbl> <dbl>
+#> 1 covariate_~ E outcome_~ No 0.211 0.130
+#> 2 covariate_~ E outcome_~ Yes 0.789 0.675
+#> 3 covariate_~ H outcome_~ No 0.852 0.564
+#> 4 covariate_~ H outcome_~ Yes 0.148 0.0377
+#> 5 covariate_~ M outcome_~ No 0.552 0.224
+#> 6 covariate_~ M outcome_~ Yes 0.448 0.160
+#> 7 covariate_~ E outcome_~ (-0.1,50] 0.182 0.0499
+#> 8 covariate_~ E outcome_~ (50,100] 0.818 0.515
+#> 9 covariate_~ H outcome_~ (-0.1,50] 0.0769 0.00876
+#> 10 covariate_~ H outcome_~ (50,100] 0.923 0.560
+#> 11 covariate_~ M outcome_~ (50,100] 1.00 1.00
+#> 12 covariate_~ No outcome_~ No 1.00 1.00
+#> 13 covariate_~ Yes outcome_~ No 0.0334 0.00884
+#> 14 covariate_~ Yes outcome_~ Yes 0.967 0.882
+#> 15 covariate_~ No outcome_~ (-0.1,50] 0.218 0.0670
+#> 16 covariate_~ No outcome_~ (50,100] 0.782 0.479
+#> 17 covariate_~ Yes outcome_~ (-0.1,50] 0.0914 0.0214
+#> 18 covariate_~ Yes outcome_~ (50,100] 0.909 0.684
+#> 19 outcome_one No covariat~ No 0.939 0.778
+#> 20 outcome_one No covariat~ Yes 0.0615 0.0148
+#> 21 outcome_one Yes covariat~ Yes 1.00 1.00
+#> 22 outcome_two (-0.1,50] covariat~ No 0.549 0.294
+#> 23 outcome_two (-0.1,50] covariat~ Yes 0.451 0.219
+#> 24 outcome_two (50,100] covariat~ No 0.305 0.188
+#> 25 outcome_two (50,100] covariat~ Yes 0.695 0.546
+#> # ... with 17 more variables: prop_upp <dbl>, prop_cv <dbl>,
+#> # prop_se <dbl>, total <dbl>, total_low <dbl>, total_upp <dbl>,
+#> # total_cv <dbl>, total_se <dbl>, total_deff <dbl>, total_den <dbl>,
+#> # total_den_low <dbl>, total_den_upp <dbl>, raw_num <int>,
+#> # raw_den <int>, raw_prop <dbl>, raw_prop_low <dbl>, raw_prop_upp <dbl>
+
+
+
+
+3. serology: Estimate prevalence Under misclassification
+
+We gather one frequentist approach (Rogan and Gladen 1978), available in different Github repos, that deal with misclassification due to an imperfect diagnostic test (Azman et al. 2020; Takahashi, Greenhouse, and Rodríguez-Barraquer 2020). Check the Reference tab.
We provide tidy outputs for bayesian approaches developed in Daniel B. Larremore et al. (2020) here and Daniel B Larremore et al. (2020) here:
You can use them with purrr and furrr to efficiently iterate and parallelize this step for multiple prevalences. Check the workflow in Article tab.
+
+
+Known test performance - Bayesian method
+
+serosvy_known_sample_posterior(
+ #in population
+ positive_number_test = 321,
+ total_number_test = 321+1234,
+ # known performance
+ sensitivity = 0.93,
+ specificity = 0.975
+)
+
+
+
+
+
+Unknown test performance - Bayesian method
+
+
+- The test performance is called “unknown” or “uncertain” when test sensitivity and specificity are not known with certainty (Kritsotakis 2020; Diggle 2011; Gelman and Carpenter 2020) and lab validation data is available with a limited set of samples, tipically during a novel pathogen outbreak.
+
+serosvy_unknown_sample_posterior_ii(
+ #in population
+ positive_number_test = 321,
+ total_number_test = 321+1234,
+ # in lab (local validation study)
+ true_positive = 670,
+ true_negative = 640,
+ false_positive = 202,
+ false_negative = 74)
+
+
+
+
+
+
+
+Contributing
+Feel free to fill an issue or contribute with your functions or workflows in a pull request.
+Here are a list of publications with interesting approaches using R:
+
+Silveira et al. (2020) and Hallal et al. (2020) analysed a serological survey accounting for sampling design and test validity using parametric bootstraping, following Lewis and Torgerson (2012).
Flor et al. (2020) implemented a lot of frequentist and bayesian methods for test with known sensitivity and specificity. Code is available here.
Gelman and Carpenter (2020) also applied Bayesian inference with hierarchical regression and post-stratification to account for test uncertainty with unknown specificity and sensitivity. Here a case-study.
+
+
+
+References
+
+
+Azman, Andrew S, Stephen Lauer, M. Taufiqur Rahman Bhuiyan, Francisco J Luquero, Daniel T Leung, Sonia Hegde, Jason B Harris, et al. 2020. “Vibrio Cholerae O1 Transmission in Bangladesh: Insights from a Nationally- Representative Serosurvey,” March. https://doi.org/10.1101/2020.03.13.20035352.
+
+
+Diggle, Peter J. 2011. “Estimating Prevalence Using an Imperfect Test.” Epidemiology Research International 2011: 1–5. https://doi.org/10.1155/2011/608719.
+
+
+Flor, Matthias, Michael Weiß, Thomas Selhorst, Christine Müller-Graf, and Matthias Greiner. 2020. “Comparison of Bayesian and Frequentist Methods for Prevalence Estimation Under Misclassification.” BMC Public Health 20 (1). https://doi.org/10.1186/s12889-020-09177-4.
+
+
+Gelman, Andrew, and Bob Carpenter. 2020. “Bayesian Analysis of Tests with Unknown Specificity and Sensitivity.” Journal of the Royal Statistical Society: Series C (Applied Statistics), August. https://doi.org/10.1111/rssc.12435.
+
+
+Hallal, Pedro C, Fernando P Hartwig, Bernardo L Horta, Mariângela F Silveira, Claudio J Struchiner, Luı́s P Vidaletti, Nelson A Neumann, et al. 2020. “SARS-CoV-2 Antibody Prevalence in Brazil: Results from Two Successive Nationwide Serological Household Surveys.” The Lancet Global Health, September. https://doi.org/10.1016/s2214-109x(20)30387-9.
+
+
+Kritsotakis, Evangelos I. 2020. “On the Importance of Population-Based Serological Surveys of SARS-CoV-2 Without Overlooking Their Inherent Uncertainties.” Public Health in Practice 1 (November): 100013. https://doi.org/10.1016/j.puhip.2020.100013.
+
+
+Larremore, Daniel B, Bailey K Fosdick, Kate M Bubar, Sam Zhang, Stephen M Kissler, C. Jessica E. Metcalf, Caroline Buckee, and Yonatan Grad. 2020. “Estimating SARS-CoV-2 Seroprevalence and Epidemiological Parameters with Uncertainty from Serological Surveys.” medRxiv, April. https://doi.org/10.1101/2020.04.15.20067066.
+
+
+Larremore, Daniel B., Bailey K. Fosdick, Sam Zhang, and Yonatan H. Grad. 2020. “Jointly Modeling Prevalence, Sensitivity and Specificity for Optimal Sample Allocation.” bioRxiv, May. https://doi.org/10.1101/2020.05.23.112649.
+
+
+Lewis, Fraser I, and Paul R Torgerson. 2012. “A Tutorial in Estimating the Prevalence of Disease in Humans and Animals in the Absence of a Gold Standard Diagnostic.” Emerging Themes in Epidemiology 9 (1). https://doi.org/10.1186/1742-7622-9-9.
+
+
+Rogan, Walter J., and Beth Gladen. 1978. “Estimating Prevalence from the Results of A Screening Test.” American Journal of Epidemiology 107 (1): 71–76. https://doi.org/10.1093/oxfordjournals.aje.a112510.
+
+
+Silveira, Mariângela F., Aluı́sio J. D. Barros, Bernardo L. Horta, Lúcia C. Pellanda, Gabriel D. Victora, Odir A. Dellagostin, Claudio J. Struchiner, et al. 2020. “Population-Based Surveys of Antibodies Against SARS-CoV-2 in Southern Brazil.” Nature Medicine 26 (8): 1196–9. https://doi.org/10.1038/s41591-020-0992-3.
+
+
+Takahashi, Saki, Bryan Greenhouse, and Isabel Rodríguez-Barraquer. 2020. “Are SARS-CoV-2 seroprevalence estimates biased?” The Journal of Infectious Diseases, August. https://doi.org/10.1093/infdis/jiaa523.
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
diff --git a/docs/articles/intro_files/figure-html/unnamed-chunk-10-1.png b/docs/articles/intro_files/figure-html/unnamed-chunk-10-1.png
new file mode 100644
index 0000000..dbcb343
Binary files /dev/null and b/docs/articles/intro_files/figure-html/unnamed-chunk-10-1.png differ
diff --git a/docs/articles/intro_files/figure-html/unnamed-chunk-14-1.png b/docs/articles/intro_files/figure-html/unnamed-chunk-14-1.png
new file mode 100644
index 0000000..2412ab0
Binary files /dev/null and b/docs/articles/intro_files/figure-html/unnamed-chunk-14-1.png differ
diff --git a/docs/authors.html b/docs/authors.html
index 363b58f..ff75958 100644
--- a/docs/authors.html
+++ b/docs/authors.html
@@ -88,6 +88,9 @@
Workflow: How to use the serosurvey R package?
+
+ Introduction: serosurvey R package
+
diff --git a/docs/index.html b/docs/index.html
index f5a3217..9cf1f67 100644
--- a/docs/index.html
+++ b/docs/index.html
@@ -59,6 +59,9 @@
Workflow: How to use the serosurvey R package?
+
+ Introduction: serosurvey R package
+
@@ -81,6 +84,9 @@
+
+
Disclaimer
+This package is a work in progress. It has been released to get feedback from users that we can incorporate in future releases.
@@ -91,221 +97,33 @@
Installation
+You can install the developmental version of serosurvey from GitHub with:
-
+
-Example
-Three basic examples which shows you how to solve common problems:
-
-
-
-1. survey: Estimate single prevalences
-
+Brief description
+The current workflow is divided in two steps:
+
-
-
From a srvyr survey design object, serosvy_proportion estimates:
-
-- weighted prevalence (
prop),
-- total population (
total),
-- raw proportion (
raw_prop),
-- coefficient of variability (
cv),
-- design effect (
deff)
-
-
-
-serosvy_proportion(design = design,
- denominator = covariate_01,
- numerator = outcome_one)
-#> # A tibble: 6 x 23
-#> denominator denominator_lev~ numerator numerator_level prop prop_low
-#> <chr> <fct> <chr> <fct> <dbl> <dbl>
-#> 1 covariate_~ E outcome_~ No 0.211 0.130
-#> 2 covariate_~ E outcome_~ Yes 0.789 0.675
-#> 3 covariate_~ H outcome_~ No 0.852 0.564
-#> 4 covariate_~ H outcome_~ Yes 0.148 0.0377
-#> 5 covariate_~ M outcome_~ No 0.552 0.224
-#> 6 covariate_~ M outcome_~ Yes 0.448 0.160
-#> # ... with 17 more variables: prop_upp <dbl>, prop_cv <dbl>,
-#> # prop_se <dbl>, total <dbl>, total_low <dbl>, total_upp <dbl>,
-#> # total_cv <dbl>, total_se <dbl>, total_deff <dbl>, total_den <dbl>,
-#> # total_den_low <dbl>, total_den_upp <dbl>, raw_num <int>,
-#> # raw_den <int>, raw_prop <dbl>, raw_prop_low <dbl>, raw_prop_upp <dbl>
-
-
-
-
-2. survey: Estimate multiple prevalences
-
+survey: Estimate multiple prevalences, and
-
-
In the Article tab we provide a workflow to estimate multiple prevalences:
-
-- using different set of covariates and outcomes as numerators or denominators,
-- in one single pipe operation
-
-
-
-# crear matriz
- #
- # set 01 of denominator-numerator
- #
-expand_grid(
- design=list(design),
- denominator=c("covariate_01","covariate_02"), # covariates
- numerator=c("outcome_one","outcome_two") # outcomes
- ) %>%
- #
- # set 02 of denominator-numerator (e.g. within main outcome)
- #
- union_all(
- expand_grid(
- design=list(design),
- denominator=c("outcome_one","outcome_two"), # outcomes
- numerator=c("covariate_02") # covariates
- )
- ) %>%
- #
- # create symbols (to be readed as arguments)
- #
- mutate(
- denominator=map(denominator,dplyr::sym),
- numerator=map(numerator,dplyr::sym)
- ) %>%
- #
- # estimate prevalence
- #
- mutate(output=pmap(.l = select(.,design,denominator,numerator),
- .f = serosvy_proportion)) %>%
- #
- # show the outcome
- #
- select(-design,-denominator,-numerator) %>%
- unnest(cols = c(output)) %>%
- print(n=Inf)
-#> # A tibble: 25 x 23
-#> denominator denominator_lev~ numerator numerator_level prop prop_low
-#> <chr> <fct> <chr> <fct> <dbl> <dbl>
-#> 1 covariate_~ E outcome_~ No 0.211 0.130
-#> 2 covariate_~ E outcome_~ Yes 0.789 0.675
-#> 3 covariate_~ H outcome_~ No 0.852 0.564
-#> 4 covariate_~ H outcome_~ Yes 0.148 0.0377
-#> 5 covariate_~ M outcome_~ No 0.552 0.224
-#> 6 covariate_~ M outcome_~ Yes 0.448 0.160
-#> 7 covariate_~ E outcome_~ (-0.1,50] 0.182 0.0499
-#> 8 covariate_~ E outcome_~ (50,100] 0.818 0.515
-#> 9 covariate_~ H outcome_~ (-0.1,50] 0.0769 0.00876
-#> 10 covariate_~ H outcome_~ (50,100] 0.923 0.560
-#> 11 covariate_~ M outcome_~ (50,100] 1.00 1.00
-#> 12 covariate_~ No outcome_~ No 1.00 1.00
-#> 13 covariate_~ Yes outcome_~ No 0.0334 0.00884
-#> 14 covariate_~ Yes outcome_~ Yes 0.967 0.882
-#> 15 covariate_~ No outcome_~ (-0.1,50] 0.218 0.0670
-#> 16 covariate_~ No outcome_~ (50,100] 0.782 0.479
-#> 17 covariate_~ Yes outcome_~ (-0.1,50] 0.0914 0.0214
-#> 18 covariate_~ Yes outcome_~ (50,100] 0.909 0.684
-#> 19 outcome_one No covariat~ No 0.939 0.778
-#> 20 outcome_one No covariat~ Yes 0.0615 0.0148
-#> 21 outcome_one Yes covariat~ Yes 1.00 1.00
-#> 22 outcome_two (-0.1,50] covariat~ No 0.549 0.294
-#> 23 outcome_two (-0.1,50] covariat~ Yes 0.451 0.219
-#> 24 outcome_two (50,100] covariat~ No 0.305 0.188
-#> 25 outcome_two (50,100] covariat~ Yes 0.695 0.546
-#> # ... with 17 more variables: prop_upp <dbl>, prop_cv <dbl>,
-#> # prop_se <dbl>, total <dbl>, total_low <dbl>, total_upp <dbl>,
-#> # total_cv <dbl>, total_se <dbl>, total_deff <dbl>, total_den <dbl>,
-#> # total_den_low <dbl>, total_den_upp <dbl>, raw_num <int>,
-#> # raw_den <int>, raw_prop <dbl>, raw_prop_low <dbl>, raw_prop_upp <dbl>
-
-
-
-3. serology: Estimate prevalence Under misclassification
-
-We gather one frequentist approach (Rogan and Gladen 1978), available in different Github repos, that deal with misclassification due to an imperfect diagnostic test (Azman et al. 2020; Takahashi, Greenhouse, and Rodríguez-Barraquer 2020). Check the Reference tab.
We provide tidy outputs for bayesian approaches developed in Daniel B. Larremore et al. (2020) here and Daniel B Larremore et al. (2020) here:
You can use them with purrr and furrr to efficiently iterate and parallelize this step for multiple prevalences. Check the workflow in Article tab.
-
-
-Known test performance - Bayesian method
-
-serosvy_known_sample_posterior(
- #in population
- positive_number_test = 321,
- total_number_test = 321+1234,
- # known performance
- sensitivity = 0.93,
- specificity = 0.975
-)
-
-
+serology: Estimate prevalence Under misclassification for a device with Known or Unknown test performance
+
-
-
-Unknown test performance - Bayesian method
-
+
+
+More
-- The test performance is called “unknown” or “uncertain” when test sensitivity and specificity are not known with certainty (Kritsotakis 2020; Diggle 2011; Gelman and Carpenter 2020) and lab validation data is available with a limited set of samples, tipically during a novel pathogen outbreak.
+- In the Introductory article we provide detailed definitions and references of the methods available.
+- In the Workflow article we provide a reproducible example with this package.
-serosvy_unknown_sample_posterior_ii(
- #in population
- positive_number_test = 321,
- total_number_test = 321+1234,
- # in lab (local validation study)
- true_positive = 670,
- true_negative = 640,
- false_positive = 202,
- false_negative = 74)
-
-
-
-
-
-
Contributing
Feel free to fill an issue or contribute with your functions or workflows in a pull request.
-Here are a list of publications with interesting approaches using R:
-
-Silveira et al. (2020) and Hallal et al. (2020) analysed a serological survey accounting for sampling design and test validity using parametric bootstraping, following Lewis and Torgerson (2012).
Flor et al. (2020) implemented a lot of frequentist and bayesian methods for test with known sensitivity and specificity. Code is available here.
Gelman and Carpenter (2020) also applied Bayesian inference with hierarchical regression and post-stratification to account for test uncertainty with unknown specificity and sensitivity. Here a case-study.
-
-
-
-How to cite this R package
-citation("serosurvey")
-#>
-#> To cite package ‘serosurvey’ in publications use:
-#>
-#> Valle Campos A (2020). "serosurvey: Serological Survey Analysis
-#> For Prevalence Estimation Under Misclassification." _Zenodo_. doi:
-#> 10.5281/zenodo.4065080 (URL:
-#> https://doi.org/10.5281/zenodo.4065080), R package version 1.0,
-#> <URL: https://avallecam.github.io/serosurvey/>.
-#>
-#> A BibTeX entry for LaTeX users is
-#>
-#> @Article{,
-#> author = {Andree {Valle Campos}},
-#> title = {serosurvey: Serological Survey Analysis For Prevalence Estimation Under Misclassification},
-#> journal = {Zenodo},
-#> month = {oct},
-#> year = {2020},
-#> doi = {10.5281/zenodo.4065080},
-#> note = {R package version 1.0},
-#> url = {https://avallecam.github.io/serosurvey/},
-#> }
@@ -318,147 +136,34 @@
Acknowledgements
Many thanks to the Centro Nacional de Epidemiología, Prevención y Control de Enfermedades (CDC Perú) for the opportunity to work on this project.
-
+
-References
-Azman, Andrew S, Stephen Lauer, M. Taufiqur Rahman Bhuiyan, Francisco J Luquero, Daniel T Leung, Sonia Hegde, Jason B Harris, et al. 2020. “Vibrio Cholerae O1 Transmission in Bangladesh: Insights from a Nationally- Representative Serosurvey,” March. https://doi.org/10.1101/2020.03.13.20035352.
-Diggle, Peter J. 2011. “Estimating Prevalence Using an Imperfect Test.” Epidemiology Research International 2011: 1–5. https://doi.org/10.1155/2011/608719.
-Flor, Matthias, Michael Weiß, Thomas Selhorst, Christine Müller-Graf, and Matthias Greiner. 2020. “Comparison of Bayesian and Frequentist Methods for Prevalence Estimation Under Misclassification.” BMC Public Health 20 (1). https://doi.org/10.1186/s12889-020-09177-4.
-Gelman, Andrew, and Bob Carpenter. 2020. “Bayesian Analysis of Tests with Unknown Specificity and Sensitivity.” Journal of the Royal Statistical Society: Series C (Applied Statistics), August. https://doi.org/10.1111/rssc.12435.
-Hallal, Pedro C, Fernando P Hartwig, Bernardo L Horta, Mariângela F Silveira, Claudio J Struchiner, Luı́s P Vidaletti, Nelson A Neumann, et al. 2020. “SARS-CoV-2 Antibody Prevalence in Brazil: Results from Two Successive Nationwide Serological Household Surveys.” The Lancet Global Health, September. https://doi.org/10.1016/s2214-109x(20)30387-9.
-Kritsotakis, Evangelos I. 2020. “On the Importance of Population-Based Serological Surveys of SARS-CoV-2 Without Overlooking Their Inherent Uncertainties.” Public Health in Practice 1 (November): 100013. https://doi.org/10.1016/j.puhip.2020.100013.
-Larremore, Daniel B., Bailey K Fosdick, Kate M Bubar, Sam Zhang, Stephen M Kissler, C. Jessica E. Metcalf, Caroline Buckee, and Yonatan Grad.2020.“Estimating SARS-CoV-2 Seroprevalence and Epidemiological Parameters with Uncertainty from Serological Surveys.” medRxiv, April. https://doi.org/10.1101/2020.04.15.20067066.
-Larremore, Daniel B., Bailey K. Fosdick, Sam Zhang, and Yonatan Grad.2020.“Jointly Modeling Prevalence, Sensitivity and Specificity for Optimal Sample Allocation.” bioRxiv, May. https://doi.org/10.1101/2020.05.23.112649.
-Lewis, Fraser I, and Paul R Torgerson. 2012. “A Tutorial in Estimating the Prevalence of Disease in Humans and Animals in the Absence of a Gold Standard Diagnostic.” Emerging Themes in Epidemiology 9 (1). https://doi.org/10.1186/1742-7622-9-9.
-Rogan, Walter J., and Beth Gladen. 1978. “Estimating Prevalence from the Results of A Screening Test.” American Journal of Epidemiology 107 (1): 71–76. https://doi.org/10.1093/oxfordjournals.aje.a112510.
-Silveira, Mariângela F., Aluı́sio J. D. Barros, Bernardo L. Horta, Lúcia C. Pellanda, Gabriel D. Victora, Odir A. Dellagostin, Claudio J. Struchiner, et al. 2020. “Population-Based Surveys of Antibodies Against SARS-CoV-2 in Southern Brazil.” Nature Medicine 26 (8): 1196–9. https://doi.org/10.1038/s41591-020-0992-3.
-Takahashi, Saki, Bryan Greenhouse, and Isabel Rodríguez-Barraquer. 2020. “Are SARS-CoV-2 seroprevalence estimates biased?” The Journal of Infectious Diseases, August. https://doi.org/10.1093/infdis/jiaa523.
-
-
-
-
-Azman, Andrew S, Stephen Lauer, M. Taufiqur Rahman Bhuiyan, Francisco J
-Luquero, Daniel T Leung, Sonia Hegde, Jason B Harris, et al. 2020.
-“Vibrio Cholerae O1 Transmission in Bangladesh: Insights from a
-Nationally- Representative Serosurvey,” March.
-.
-
-
-
-
-
-
-Diggle, Peter J. 2011. “Estimating Prevalence Using an Imperfect Test.”
-*Epidemiology Research International* 2011: 1–5.
-.
-
-
-
-
-
-
-Flor, Matthias, Michael Weiß, Thomas Selhorst, Christine Müller-Graf,
-and Matthias Greiner. 2020. “Comparison of Bayesian and Frequentist
-Methods for Prevalence Estimation Under Misclassification.” *BMC Public
-Health* 20 (1). .
-
-
-
-
-
-
-Gelman, Andrew, and Bob Carpenter. 2020. “Bayesian Analysis of Tests
-with Unknown Specificity and Sensitivity.” *Journal of the Royal
-Statistical Society: Series C (Applied Statistics)*, August.
-.
-
-
-
-
-
-
-Hallal, Pedro C, Fernando P Hartwig, Bernardo L Horta, Mariângela F
-Silveira, Claudio J Struchiner, Luı́s P Vidaletti, Nelson A Neumann, et
-al. 2020. “SARS-CoV-2 Antibody Prevalence in Brazil: Results from Two
-Successive Nationwide Serological Household Surveys.” *The Lancet Global
-Health*, September. .
-
-
-
-
-
-
-Kritsotakis, Evangelos I. 2020. “On the Importance of Population-Based
-Serological Surveys of SARS-CoV-2 Without Overlooking Their Inherent
-Uncertainties.” *Public Health in Practice* 1 (November): 100013.
-.
-
-
-
-
-
-
-Larremore, Daniel B, Bailey K Fosdick, Kate M Bubar, Sam Zhang, Stephen
-M Kissler, C. Jessica E. Metcalf, Caroline Buckee, and Yonatan Grad.
-2020. “Estimating SARS-CoV-2 Seroprevalence and Epidemiological
-Parameters with Uncertainty from Serological Surveys.” *medRxiv*, April.
-.
-
-
-
-
-
-
-Larremore, Daniel B., Bailey K. Fosdick, Sam Zhang, and Yonatan H. Grad.
-2020. “Jointly Modeling Prevalence, Sensitivity and Specificity for
-Optimal Sample Allocation.” *bioRxiv*, May.
-.
-
-
-
-
-
-
-Lewis, Fraser I, and Paul R Torgerson. 2012. “A Tutorial in Estimating
-the Prevalence of Disease in Humans and Animals in the Absence of a Gold
-Standard Diagnostic.” *Emerging Themes in Epidemiology* 9 (1).
-.
-
-
-
-
-
-
-Rogan, Walter J., and Beth Gladen. 1978. “Estimating Prevalence from the
-Results of A Screening Test.” *American Journal of Epidemiology* 107
-(1): 71–76. .
-
-
-
-
-
-
-Silveira, Mariângela F., Aluı́sio J. D. Barros, Bernardo L. Horta, Lúcia
-C. Pellanda, Gabriel D. Victora, Odir A. Dellagostin, Claudio J.
-Struchiner, et al. 2020. “Population-Based Surveys of Antibodies Against
-SARS-CoV-2 in Southern Brazil.” *Nature Medicine* 26 (8): 1196–9.
-.
-
-
+How to cite this R package
+citation("serosurvey")
+#>
+#> To cite package ‘serosurvey’ in publications use:
+#>
+#> Valle Campos A (2020). "serosurvey: Serological Survey Analysis
+#> For Prevalence Estimation Under Misclassification." _Zenodo_. doi:
+#> 10.5281/zenodo.4065080 (URL:
+#> https://doi.org/10.5281/zenodo.4065080), R package version 1.0,
+#> <URL: https://avallecam.github.io/serosurvey/>.
+#>
+#> A BibTeX entry for LaTeX users is
+#>
+#> @Article{,
+#> author = {Andree {Valle Campos}},
+#> title = {serosurvey: Serological Survey Analysis For Prevalence Estimation Under Misclassification},
+#> journal = {Zenodo},
+#> month = {oct},
+#> year = {2020},
+#> doi = {10.5281/zenodo.4065080},
+#> note = {R package version 1.0},
+#> url = {https://avallecam.github.io/serosurvey/},
+#> }
-
-
-
-Takahashi, Saki, Bryan Greenhouse, and Isabel Rodríguez-Barraquer. 2020.
-“Are SARS-CoV-2 seroprevalence estimates biased?” *The Journal of
-Infectious Diseases*, August. .
-
-
-
-
-
- ggplot_prevalence(data, category, outcome, proportion, proportion_upp,
- proportion_low, breaks_n = 5)
-
-ggplot_prevalence_ii(data, denominator_level, numerator, proportion,
- proportion_upp, proportion_low, breaks_n = 5)
+ ggplot_prevalence(data, denominator_level, numerator, proportion,
+ proportion_upp, proportion_low)
Arguments
Fun
ggplot_prevalence: ggplot2 visualization of proportions
ggplot_prevalence_ii: ggplot_prevalence with new arguments
diff --git a/docs/reference/index.html b/docs/reference/index.html
index a8f4f01..8453798 100644
--- a/docs/reference/index.html
+++ b/docs/reference/index.html
@@ -88,6 +88,9 @@
Workflow: How to use the serosurvey R package?
+
+ Introduction: serosurvey R package
+
@@ -139,7 +142,7 @@ ggplot_prevalence() ggplot_prevalence_ii()
+
Visualization of proportions
diff --git a/docs/reference/rogan_gladen_stderr_unk.html b/docs/reference/rogan_gladen_stderr_unk.html
index 372364c..fbc602b 100644
--- a/docs/reference/rogan_gladen_stderr_unk.html
+++ b/docs/reference/rogan_gladen_stderr_unk.html
@@ -91,6 +91,9 @@
Workflow: How to use the serosurvey R package?
+
+ Introduction: serosurvey R package
+
diff --git a/docs/reference/sample_posterior_r_mcmc_hyperR.html b/docs/reference/sample_posterior_r_mcmc_hyperR.html
index 449b760..f022e15 100644
--- a/docs/reference/sample_posterior_r_mcmc_hyperR.html
+++ b/docs/reference/sample_posterior_r_mcmc_hyperR.html
@@ -91,6 +91,9 @@
Workflow: How to use the serosurvey R package?
+
+ Introduction: serosurvey R package
+
diff --git a/docs/reference/sample_posterior_r_mcmc_testun.html b/docs/reference/sample_posterior_r_mcmc_testun.html
index a3a4f5e..d9da228 100644
--- a/docs/reference/sample_posterior_r_mcmc_testun.html
+++ b/docs/reference/sample_posterior_r_mcmc_testun.html
@@ -91,6 +91,9 @@
Workflow: How to use the serosurvey R package?
+
+ Introduction: serosurvey R package
+
diff --git a/docs/reference/serosvy_known_sample_posterior.html b/docs/reference/serosvy_known_sample_posterior.html
index e194ce0..675cbea 100644
--- a/docs/reference/serosvy_known_sample_posterior.html
+++ b/docs/reference/serosvy_known_sample_posterior.html
@@ -91,6 +91,9 @@
Workflow: How to use the serosurvey R package?
+
+ Introduction: serosurvey R package
+
diff --git a/docs/reference/serosvy_unknown_sample_posterior.html b/docs/reference/serosvy_unknown_sample_posterior.html
index 62316cf..221e643 100644
--- a/docs/reference/serosvy_unknown_sample_posterior.html
+++ b/docs/reference/serosvy_unknown_sample_posterior.html
@@ -91,6 +91,9 @@
Workflow: How to use the serosurvey R package?
+
+ Introduction: serosurvey R package
+
diff --git a/docs/reference/srvyr_prop_step_01.html b/docs/reference/srvyr_prop_step_01.html
index c527187..1ac491e 100644
--- a/docs/reference/srvyr_prop_step_01.html
+++ b/docs/reference/srvyr_prop_step_01.html
@@ -91,6 +91,9 @@
Workflow: How to use the serosurvey R package?
+
+ Introduction: serosurvey R package
+
diff --git a/docs/reference/unite_dotwhiskers.html b/docs/reference/unite_dotwhiskers.html
index 1412cd1..7acf19d 100644
--- a/docs/reference/unite_dotwhiskers.html
+++ b/docs/reference/unite_dotwhiskers.html
@@ -91,6 +91,9 @@
Workflow: How to use the serosurvey R package?
+
+ Introduction: serosurvey R package
+
20
25.0 ( 8.7 - 49.1)
14.8 ( 3.8 - 44)
-0.414 ( 0.28 - 29.9)
+0.425 ( 0.28 - 29.9)
0.59
23
65.2 (42.7 - 83.6)
44.8 ( 16.0 - 78)
-31.518 ( 0.40 - 81.1)
+31.506 ( 0.40 - 81.1)
0.38
outcome_01_adj_tbl %>%
filter(str_detect(numerator,"outcome")) %>%
- ggplot_prevalence_ii(
+ ggplot_prevalence(
denominator_level = denominator_level,
numerator = numerator,
proportion = prop,
proportion_upp = prop_upp,
proportion_low = prop_low) +
- theme(axis.text.x = element_text(angle = 0, vjust = 0, hjust=0)) +
- # coord_flip() +
- facet_wrap(denominator~.,scales = "free") +
- # facet_grid(denominator~.,scales = "free_y") +
- colorspace::scale_color_discrete_qualitative() +
- labs(title = "Prevalence of numerators across denominators",
- y = "Prevalence",x = "")
+ # theme(axis.text.x = element_text(angle = 0, vjust = 0, hjust=0)) +
+ scale_y_continuous(
+ labels = scales::percent_format(accuracy = 1),
+ breaks = scales::pretty_breaks(n = 5)) +
+ # coord_flip() +
+ facet_wrap(denominator~.,scales = "free") +
+ # facet_grid(denominator~.,scales = "free_y") +
+ colorspace::scale_color_discrete_qualitative() +
+ labs(title = "Prevalence of numerators across denominators",
+ y = "Prevalence",x = "")
outcome_01_adj_tbl %>%
filter(str_detect(numerator,"outcome")) %>%
- ggplot_prevalence_ii(
+ ggplot_prevalence(
denominator_level = denominator_level,
numerator = numerator,
proportion = prop,
proportion_upp = prop_upp,
proportion_low = prop_low) +
- theme(axis.text.x = element_text(angle = 0, vjust = 0, hjust=0)) +
- # coord_flip() +
- facet_wrap(denominator~.,scales = "free") +
- # facet_grid(denominator~.,scales = "free_y") +
- colorspace::scale_color_discrete_qualitative() +
- labs(title = "Prevalence of numerators across denominators",
- y = "Prevalence",x = "")
All vignettes
Introduction: serosurvey R package
+ + + +intro.Rmd+Introduction
+Here we present three examples, definitions and related references:
+ +
+1. survey: Estimate single prevalences
+-
+
-
+
From a
+srvyrsurvey design object,serosvy_proportionestimates:-
+
- weighted prevalence (
prop),
+ - total population (
total),
+ - raw proportion (
raw_prop),
+ - coefficient of variability (
cv),
+ - design effect (
deff)
+
+ - weighted prevalence (
serosvy_proportion(design = design,
+ denominator = covariate_01,
+ numerator = outcome_one)
+#> # A tibble: 6 x 23
+#> denominator denominator_lev~ numerator numerator_level prop prop_low
+#> <chr> <fct> <chr> <fct> <dbl> <dbl>
+#> 1 covariate_~ E outcome_~ No 0.211 0.130
+#> 2 covariate_~ E outcome_~ Yes 0.789 0.675
+#> 3 covariate_~ H outcome_~ No 0.852 0.564
+#> 4 covariate_~ H outcome_~ Yes 0.148 0.0377
+#> 5 covariate_~ M outcome_~ No 0.552 0.224
+#> 6 covariate_~ M outcome_~ Yes 0.448 0.160
+#> # ... with 17 more variables: prop_upp <dbl>, prop_cv <dbl>,
+#> # prop_se <dbl>, total <dbl>, total_low <dbl>, total_upp <dbl>,
+#> # total_cv <dbl>, total_se <dbl>, total_deff <dbl>, total_den <dbl>,
+#> # total_den_low <dbl>, total_den_upp <dbl>, raw_num <int>,
+#> # raw_den <int>, raw_prop <dbl>, raw_prop_low <dbl>, raw_prop_upp <dbl>
+2. survey: Estimate multiple prevalences
+-
+
-
+
In the Article tab we provide a workflow to estimate multiple prevalences:
+-
+
- using different set of covariates and outcomes as numerators or denominators, +
- in one single pipe operation +
+
# crear matriz
+ #
+ # set 01 of denominator-numerator
+ #
+expand_grid(
+ design=list(design),
+ denominator=c("covariate_01","covariate_02"), # covariates
+ numerator=c("outcome_one","outcome_two") # outcomes
+ ) %>%
+ #
+ # set 02 of denominator-numerator (e.g. within main outcome)
+ #
+ union_all(
+ expand_grid(
+ design=list(design),
+ denominator=c("outcome_one","outcome_two"), # outcomes
+ numerator=c("covariate_02") # covariates
+ )
+ ) %>%
+ #
+ # create symbols (to be readed as arguments)
+ #
+ mutate(
+ denominator=map(denominator,dplyr::sym),
+ numerator=map(numerator,dplyr::sym)
+ ) %>%
+ #
+ # estimate prevalence
+ #
+ mutate(output=pmap(.l = select(.,design,denominator,numerator),
+ .f = serosvy_proportion)) %>%
+ #
+ # show the outcome
+ #
+ select(-design,-denominator,-numerator) %>%
+ unnest(cols = c(output)) %>%
+ print(n=Inf)
+#> # A tibble: 25 x 23
+#> denominator denominator_lev~ numerator numerator_level prop prop_low
+#> <chr> <fct> <chr> <fct> <dbl> <dbl>
+#> 1 covariate_~ E outcome_~ No 0.211 0.130
+#> 2 covariate_~ E outcome_~ Yes 0.789 0.675
+#> 3 covariate_~ H outcome_~ No 0.852 0.564
+#> 4 covariate_~ H outcome_~ Yes 0.148 0.0377
+#> 5 covariate_~ M outcome_~ No 0.552 0.224
+#> 6 covariate_~ M outcome_~ Yes 0.448 0.160
+#> 7 covariate_~ E outcome_~ (-0.1,50] 0.182 0.0499
+#> 8 covariate_~ E outcome_~ (50,100] 0.818 0.515
+#> 9 covariate_~ H outcome_~ (-0.1,50] 0.0769 0.00876
+#> 10 covariate_~ H outcome_~ (50,100] 0.923 0.560
+#> 11 covariate_~ M outcome_~ (50,100] 1.00 1.00
+#> 12 covariate_~ No outcome_~ No 1.00 1.00
+#> 13 covariate_~ Yes outcome_~ No 0.0334 0.00884
+#> 14 covariate_~ Yes outcome_~ Yes 0.967 0.882
+#> 15 covariate_~ No outcome_~ (-0.1,50] 0.218 0.0670
+#> 16 covariate_~ No outcome_~ (50,100] 0.782 0.479
+#> 17 covariate_~ Yes outcome_~ (-0.1,50] 0.0914 0.0214
+#> 18 covariate_~ Yes outcome_~ (50,100] 0.909 0.684
+#> 19 outcome_one No covariat~ No 0.939 0.778
+#> 20 outcome_one No covariat~ Yes 0.0615 0.0148
+#> 21 outcome_one Yes covariat~ Yes 1.00 1.00
+#> 22 outcome_two (-0.1,50] covariat~ No 0.549 0.294
+#> 23 outcome_two (-0.1,50] covariat~ Yes 0.451 0.219
+#> 24 outcome_two (50,100] covariat~ No 0.305 0.188
+#> 25 outcome_two (50,100] covariat~ Yes 0.695 0.546
+#> # ... with 17 more variables: prop_upp <dbl>, prop_cv <dbl>,
+#> # prop_se <dbl>, total <dbl>, total_low <dbl>, total_upp <dbl>,
+#> # total_cv <dbl>, total_se <dbl>, total_deff <dbl>, total_den <dbl>,
+#> # total_den_low <dbl>, total_den_upp <dbl>, raw_num <int>,
+#> # raw_den <int>, raw_prop <dbl>, raw_prop_low <dbl>, raw_prop_upp <dbl>
+3. serology: Estimate prevalence Under misclassification
+-
+
We gather one frequentist approach (Rogan and Gladen 1978), available in different Github repos, that deal with misclassification due to an imperfect diagnostic test (Azman et al. 2020; Takahashi, Greenhouse, and Rodríguez-Barraquer 2020). Check the Reference tab.
+We provide tidy outputs for bayesian approaches developed in Daniel B. Larremore et al. (2020) here and Daniel B Larremore et al. (2020) here:
+You can use them with
purrrandfurrrto efficiently iterate and parallelize this step for multiple prevalences. Check the workflow in Article tab.
+
+Known test performance - Bayesian method +
+serosvy_known_sample_posterior(
+ #in population
+ positive_number_test = 321,
+ total_number_test = 321+1234,
+ # known performance
+ sensitivity = 0.93,
+ specificity = 0.975
+)
+Unknown test performance - Bayesian method +
+-
+
- The test performance is called “unknown” or “uncertain” when test sensitivity and specificity are not known with certainty (Kritsotakis 2020; Diggle 2011; Gelman and Carpenter 2020) and lab validation data is available with a limited set of samples, tipically during a novel pathogen outbreak. +
serosvy_unknown_sample_posterior_ii(
+ #in population
+ positive_number_test = 321,
+ total_number_test = 321+1234,
+ # in lab (local validation study)
+ true_positive = 670,
+ true_negative = 640,
+ false_positive = 202,
+ false_negative = 74)
+Contributing
+Feel free to fill an issue or contribute with your functions or workflows in a pull request.
+Here are a list of publications with interesting approaches using R:
+-
+
Silveira et al. (2020) and Hallal et al. (2020) analysed a serological survey accounting for sampling design and test validity using parametric bootstraping, following Lewis and Torgerson (2012).
+Flor et al. (2020) implemented a lot of frequentist and bayesian methods for test with known sensitivity and specificity. Code is available here.
+Gelman and Carpenter (2020) also applied Bayesian inference with hierarchical regression and post-stratification to account for test uncertainty with unknown specificity and sensitivity. Here a case-study.
+
+References
+Azman, Andrew S, Stephen Lauer, M. Taufiqur Rahman Bhuiyan, Francisco J Luquero, Daniel T Leung, Sonia Hegde, Jason B Harris, et al. 2020. “Vibrio Cholerae O1 Transmission in Bangladesh: Insights from a Nationally- Representative Serosurvey,” March. https://doi.org/10.1101/2020.03.13.20035352.
+Diggle, Peter J. 2011. “Estimating Prevalence Using an Imperfect Test.” Epidemiology Research International 2011: 1–5. https://doi.org/10.1155/2011/608719.
+Flor, Matthias, Michael Weiß, Thomas Selhorst, Christine Müller-Graf, and Matthias Greiner. 2020. “Comparison of Bayesian and Frequentist Methods for Prevalence Estimation Under Misclassification.” BMC Public Health 20 (1). https://doi.org/10.1186/s12889-020-09177-4.
+Gelman, Andrew, and Bob Carpenter. 2020. “Bayesian Analysis of Tests with Unknown Specificity and Sensitivity.” Journal of the Royal Statistical Society: Series C (Applied Statistics), August. https://doi.org/10.1111/rssc.12435.
+Hallal, Pedro C, Fernando P Hartwig, Bernardo L Horta, Mariângela F Silveira, Claudio J Struchiner, Luı́s P Vidaletti, Nelson A Neumann, et al. 2020. “SARS-CoV-2 Antibody Prevalence in Brazil: Results from Two Successive Nationwide Serological Household Surveys.” The Lancet Global Health, September. https://doi.org/10.1016/s2214-109x(20)30387-9.
+Kritsotakis, Evangelos I. 2020. “On the Importance of Population-Based Serological Surveys of SARS-CoV-2 Without Overlooking Their Inherent Uncertainties.” Public Health in Practice 1 (November): 100013. https://doi.org/10.1016/j.puhip.2020.100013.
+Larremore, Daniel B, Bailey K Fosdick, Kate M Bubar, Sam Zhang, Stephen M Kissler, C. Jessica E. Metcalf, Caroline Buckee, and Yonatan Grad. 2020. “Estimating SARS-CoV-2 Seroprevalence and Epidemiological Parameters with Uncertainty from Serological Surveys.” medRxiv, April. https://doi.org/10.1101/2020.04.15.20067066.
+Larremore, Daniel B., Bailey K. Fosdick, Sam Zhang, and Yonatan H. Grad. 2020. “Jointly Modeling Prevalence, Sensitivity and Specificity for Optimal Sample Allocation.” bioRxiv, May. https://doi.org/10.1101/2020.05.23.112649.
+Lewis, Fraser I, and Paul R Torgerson. 2012. “A Tutorial in Estimating the Prevalence of Disease in Humans and Animals in the Absence of a Gold Standard Diagnostic.” Emerging Themes in Epidemiology 9 (1). https://doi.org/10.1186/1742-7622-9-9.
+Rogan, Walter J., and Beth Gladen. 1978. “Estimating Prevalence from the Results of A Screening Test.” American Journal of Epidemiology 107 (1): 71–76. https://doi.org/10.1093/oxfordjournals.aje.a112510.
+Silveira, Mariângela F., Aluı́sio J. D. Barros, Bernardo L. Horta, Lúcia C. Pellanda, Gabriel D. Victora, Odir A. Dellagostin, Claudio J. Struchiner, et al. 2020. “Population-Based Surveys of Antibodies Against SARS-CoV-2 in Southern Brazil.” Nature Medicine 26 (8): 1196–9. https://doi.org/10.1038/s41591-020-0992-3.
+Takahashi, Saki, Bryan Greenhouse, and Isabel Rodríguez-Barraquer. 2020. “Are SARS-CoV-2 seroprevalence estimates biased?” The Journal of Infectious Diseases, August. https://doi.org/10.1093/infdis/jiaa523.
+
Disclaimer
This package is a work in progress. It has been released to get feedback from users that we can incorporate in future releases.
Installation
+You can install the developmental version of serosurvey from GitHub with:
-Example
-Three basic examples which shows you how to solve common problems:
- -
-1. survey: Estimate single prevalences
--
+Brief description
+
-
-
From a
-srvyrsurvey design object,serosvy_proportionestimates:-
-
- weighted prevalence (
prop),
- - total population (
total),
- - raw proportion (
raw_prop),
- - coefficient of variability (
cv),
- - design effect (
deff)
-
- - weighted prevalence (
The current workflow is divided in two steps:
+serosvy_proportion(design = design,
- denominator = covariate_01,
- numerator = outcome_one)
-#> # A tibble: 6 x 23
-#> denominator denominator_lev~ numerator numerator_level prop prop_low
-#> <chr> <fct> <chr> <fct> <dbl> <dbl>
-#> 1 covariate_~ E outcome_~ No 0.211 0.130
-#> 2 covariate_~ E outcome_~ Yes 0.789 0.675
-#> 3 covariate_~ H outcome_~ No 0.852 0.564
-#> 4 covariate_~ H outcome_~ Yes 0.148 0.0377
-#> 5 covariate_~ M outcome_~ No 0.552 0.224
-#> 6 covariate_~ M outcome_~ Yes 0.448 0.160
-#> # ... with 17 more variables: prop_upp <dbl>, prop_cv <dbl>,
-#> # prop_se <dbl>, total <dbl>, total_low <dbl>, total_upp <dbl>,
-#> # total_cv <dbl>, total_se <dbl>, total_deff <dbl>, total_den <dbl>,
-#> # total_den_low <dbl>, total_den_upp <dbl>, raw_num <int>,
-#> # raw_den <int>, raw_prop <dbl>, raw_prop_low <dbl>, raw_prop_upp <dbl>
-2. survey: Estimate multiple prevalences
--
+
-
-
In the Article tab we provide a workflow to estimate multiple prevalences:
--
-
- using different set of covariates and outcomes as numerators or denominators, -
- in one single pipe operation -
-
survey: Estimate multiple prevalences, and
# crear matriz
- #
- # set 01 of denominator-numerator
- #
-expand_grid(
- design=list(design),
- denominator=c("covariate_01","covariate_02"), # covariates
- numerator=c("outcome_one","outcome_two") # outcomes
- ) %>%
- #
- # set 02 of denominator-numerator (e.g. within main outcome)
- #
- union_all(
- expand_grid(
- design=list(design),
- denominator=c("outcome_one","outcome_two"), # outcomes
- numerator=c("covariate_02") # covariates
- )
- ) %>%
- #
- # create symbols (to be readed as arguments)
- #
- mutate(
- denominator=map(denominator,dplyr::sym),
- numerator=map(numerator,dplyr::sym)
- ) %>%
- #
- # estimate prevalence
- #
- mutate(output=pmap(.l = select(.,design,denominator,numerator),
- .f = serosvy_proportion)) %>%
- #
- # show the outcome
- #
- select(-design,-denominator,-numerator) %>%
- unnest(cols = c(output)) %>%
- print(n=Inf)
-#> # A tibble: 25 x 23
-#> denominator denominator_lev~ numerator numerator_level prop prop_low
-#> <chr> <fct> <chr> <fct> <dbl> <dbl>
-#> 1 covariate_~ E outcome_~ No 0.211 0.130
-#> 2 covariate_~ E outcome_~ Yes 0.789 0.675
-#> 3 covariate_~ H outcome_~ No 0.852 0.564
-#> 4 covariate_~ H outcome_~ Yes 0.148 0.0377
-#> 5 covariate_~ M outcome_~ No 0.552 0.224
-#> 6 covariate_~ M outcome_~ Yes 0.448 0.160
-#> 7 covariate_~ E outcome_~ (-0.1,50] 0.182 0.0499
-#> 8 covariate_~ E outcome_~ (50,100] 0.818 0.515
-#> 9 covariate_~ H outcome_~ (-0.1,50] 0.0769 0.00876
-#> 10 covariate_~ H outcome_~ (50,100] 0.923 0.560
-#> 11 covariate_~ M outcome_~ (50,100] 1.00 1.00
-#> 12 covariate_~ No outcome_~ No 1.00 1.00
-#> 13 covariate_~ Yes outcome_~ No 0.0334 0.00884
-#> 14 covariate_~ Yes outcome_~ Yes 0.967 0.882
-#> 15 covariate_~ No outcome_~ (-0.1,50] 0.218 0.0670
-#> 16 covariate_~ No outcome_~ (50,100] 0.782 0.479
-#> 17 covariate_~ Yes outcome_~ (-0.1,50] 0.0914 0.0214
-#> 18 covariate_~ Yes outcome_~ (50,100] 0.909 0.684
-#> 19 outcome_one No covariat~ No 0.939 0.778
-#> 20 outcome_one No covariat~ Yes 0.0615 0.0148
-#> 21 outcome_one Yes covariat~ Yes 1.00 1.00
-#> 22 outcome_two (-0.1,50] covariat~ No 0.549 0.294
-#> 23 outcome_two (-0.1,50] covariat~ Yes 0.451 0.219
-#> 24 outcome_two (50,100] covariat~ No 0.305 0.188
-#> 25 outcome_two (50,100] covariat~ Yes 0.695 0.546
-#> # ... with 17 more variables: prop_upp <dbl>, prop_cv <dbl>,
-#> # prop_se <dbl>, total <dbl>, total_low <dbl>, total_upp <dbl>,
-#> # total_cv <dbl>, total_se <dbl>, total_deff <dbl>, total_den <dbl>,
-#> # total_den_low <dbl>, total_den_upp <dbl>, raw_num <int>,
-#> # raw_den <int>, raw_prop <dbl>, raw_prop_low <dbl>, raw_prop_upp <dbl>
-3. serology: Estimate prevalence Under misclassification
--
-
We gather one frequentist approach (Rogan and Gladen 1978), available in different Github repos, that deal with misclassification due to an imperfect diagnostic test (Azman et al. 2020; Takahashi, Greenhouse, and Rodríguez-Barraquer 2020). Check the Reference tab.
-We provide tidy outputs for bayesian approaches developed in Daniel B. Larremore et al. (2020) here and Daniel B Larremore et al. (2020) here:
-You can use them with
purrrandfurrrto efficiently iterate and parallelize this step for multiple prevalences. Check the workflow in Article tab.
-
-Known test performance - Bayesian method -
-serosvy_known_sample_posterior(
- #in population
- positive_number_test = 321,
- total_number_test = 321+1234,
- # known performance
- sensitivity = 0.93,
- specificity = 0.975
-)
serology: Estimate prevalence Under misclassification for a device with Known or Unknown test performance
+
-Unknown test performance - Bayesian method -
++More
-
-
- The test performance is called “unknown” or “uncertain” when test sensitivity and specificity are not known with certainty (Kritsotakis 2020; Diggle 2011; Gelman and Carpenter 2020) and lab validation data is available with a limited set of samples, tipically during a novel pathogen outbreak. +
- In the Introductory article we provide detailed definitions and references of the methods available. +
- In the Workflow article we provide a reproducible example with this package.
serosvy_unknown_sample_posterior_ii(
- #in population
- positive_number_test = 321,
- total_number_test = 321+1234,
- # in lab (local validation study)
- true_positive = 670,
- true_negative = 640,
- false_positive = 202,
- false_negative = 74)
Contributing
Feel free to fill an issue or contribute with your functions or workflows in a pull request.
-Here are a list of publications with interesting approaches using R:
--
-
Silveira et al. (2020) and Hallal et al. (2020) analysed a serological survey accounting for sampling design and test validity using parametric bootstraping, following Lewis and Torgerson (2012).
-Flor et al. (2020) implemented a lot of frequentist and bayesian methods for test with known sensitivity and specificity. Code is available here.
-Gelman and Carpenter (2020) also applied Bayesian inference with hierarchical regression and post-stratification to account for test uncertainty with unknown specificity and sensitivity. Here a case-study.
-
-How to cite this R package
-citation("serosurvey")
-#>
-#> To cite package ‘serosurvey’ in publications use:
-#>
-#> Valle Campos A (2020). "serosurvey: Serological Survey Analysis
-#> For Prevalence Estimation Under Misclassification." _Zenodo_. doi:
-#> 10.5281/zenodo.4065080 (URL:
-#> https://doi.org/10.5281/zenodo.4065080), R package version 1.0,
-#> <URL: https://avallecam.github.io/serosurvey/>.
-#>
-#> A BibTeX entry for LaTeX users is
-#>
-#> @Article{,
-#> author = {Andree {Valle Campos}},
-#> title = {serosurvey: Serological Survey Analysis For Prevalence Estimation Under Misclassification},
-#> journal = {Zenodo},
-#> month = {oct},
-#> year = {2020},
-#> doi = {10.5281/zenodo.4065080},
-#> note = {R package version 1.0},
-#> url = {https://avallecam.github.io/serosurvey/},
-#> }
@@ -318,147 +136,34 @@
Acknowledgements
Many thanks to the Centro Nacional de Epidemiología, Prevención y Control de Enfermedades (CDC Perú) for the opportunity to work on this project.
-References
-Azman, Andrew S, Stephen Lauer, M. Taufiqur Rahman Bhuiyan, Francisco J Luquero, Daniel T Leung, Sonia Hegde, Jason B Harris, et al. 2020. “Vibrio Cholerae O1 Transmission in Bangladesh: Insights from a Nationally- Representative Serosurvey,” March. https://doi.org/10.1101/2020.03.13.20035352.
-Diggle, Peter J. 2011. “Estimating Prevalence Using an Imperfect Test.” Epidemiology Research International 2011: 1–5. https://doi.org/10.1155/2011/608719.
-Flor, Matthias, Michael Weiß, Thomas Selhorst, Christine Müller-Graf, and Matthias Greiner. 2020. “Comparison of Bayesian and Frequentist Methods for Prevalence Estimation Under Misclassification.” BMC Public Health 20 (1). https://doi.org/10.1186/s12889-020-09177-4.
-Gelman, Andrew, and Bob Carpenter. 2020. “Bayesian Analysis of Tests with Unknown Specificity and Sensitivity.” Journal of the Royal Statistical Society: Series C (Applied Statistics), August. https://doi.org/10.1111/rssc.12435.
-Hallal, Pedro C, Fernando P Hartwig, Bernardo L Horta, Mariângela F Silveira, Claudio J Struchiner, Luı́s P Vidaletti, Nelson A Neumann, et al. 2020. “SARS-CoV-2 Antibody Prevalence in Brazil: Results from Two Successive Nationwide Serological Household Surveys.” The Lancet Global Health, September. https://doi.org/10.1016/s2214-109x(20)30387-9.
-Kritsotakis, Evangelos I. 2020. “On the Importance of Population-Based Serological Surveys of SARS-CoV-2 Without Overlooking Their Inherent Uncertainties.” Public Health in Practice 1 (November): 100013. https://doi.org/10.1016/j.puhip.2020.100013.
-Larremore, Daniel B., Bailey K Fosdick, Kate M Bubar, Sam Zhang, Stephen M Kissler, C. Jessica E. Metcalf, Caroline Buckee, and Yonatan Grad.2020.“Estimating SARS-CoV-2 Seroprevalence and Epidemiological Parameters with Uncertainty from Serological Surveys.” medRxiv, April. https://doi.org/10.1101/2020.04.15.20067066.
-Larremore, Daniel B., Bailey K. Fosdick, Sam Zhang, and Yonatan Grad.2020.“Jointly Modeling Prevalence, Sensitivity and Specificity for Optimal Sample Allocation.” bioRxiv, May. https://doi.org/10.1101/2020.05.23.112649.
-Lewis, Fraser I, and Paul R Torgerson. 2012. “A Tutorial in Estimating the Prevalence of Disease in Humans and Animals in the Absence of a Gold Standard Diagnostic.” Emerging Themes in Epidemiology 9 (1). https://doi.org/10.1186/1742-7622-9-9.
-Rogan, Walter J., and Beth Gladen. 1978. “Estimating Prevalence from the Results of A Screening Test.” American Journal of Epidemiology 107 (1): 71–76. https://doi.org/10.1093/oxfordjournals.aje.a112510.
-Silveira, Mariângela F., Aluı́sio J. D. Barros, Bernardo L. Horta, Lúcia C. Pellanda, Gabriel D. Victora, Odir A. Dellagostin, Claudio J. Struchiner, et al. 2020. “Population-Based Surveys of Antibodies Against SARS-CoV-2 in Southern Brazil.” Nature Medicine 26 (8): 1196–9. https://doi.org/10.1038/s41591-020-0992-3.
-Takahashi, Saki, Bryan Greenhouse, and Isabel Rodríguez-Barraquer. 2020. “Are SARS-CoV-2 seroprevalence estimates biased?” The Journal of Infectious Diseases, August. https://doi.org/10.1093/infdis/jiaa523.
-citation("serosurvey")
+#>
+#> To cite package ‘serosurvey’ in publications use:
+#>
+#> Valle Campos A (2020). "serosurvey: Serological Survey Analysis
+#> For Prevalence Estimation Under Misclassification." _Zenodo_. doi:
+#> 10.5281/zenodo.4065080 (URL:
+#> https://doi.org/10.5281/zenodo.4065080), R package version 1.0,
+#> <URL: https://avallecam.github.io/serosurvey/>.
+#>
+#> A BibTeX entry for LaTeX users is
+#>
+#> @Article{,
+#> author = {Andree {Valle Campos}},
+#> title = {serosurvey: Serological Survey Analysis For Prevalence Estimation Under Misclassification},
+#> journal = {Zenodo},
+#> month = {oct},
+#> year = {2020},
+#> doi = {10.5281/zenodo.4065080},
+#> note = {R package version 1.0},
+#> url = {https://avallecam.github.io/serosurvey/},
+#> }ggplot_prevalence(data, category, outcome, proportion, proportion_upp, - proportion_low, breaks_n = 5) - -ggplot_prevalence_ii(data, denominator_level, numerator, proportion, - proportion_upp, proportion_low, breaks_n = 5)+
ggplot_prevalence(data, denominator_level, numerator, proportion, + proportion_upp, proportion_low)
Arguments
Fun
ggplot_prevalence: ggplot2 visualization of proportions
ggplot_prevalence_ii: ggplot_prevalence with new arguments
diff --git a/docs/reference/index.html b/docs/reference/index.html
index a8f4f01..8453798 100644
--- a/docs/reference/index.html
+++ b/docs/reference/index.html
@@ -88,6 +88,9 @@
ggplot_prevalence: ggplot2 visualization of proportions
ggplot_prevalence_ii: ggplot_prevalence with new arguments
ggplot_prevalence() ggplot_prevalence_ii()
+
Visualization of proportions