Function list_distributions() and convert_params_to_summary_stats()

[chloerice48]

Feedback from WG4 google document: Function list_distributions() is it possible to also list the pathogen/variant info in the output?

Function convert_params_to_summary_stats(), could the IQR, 95% percentile also be provided?

[joshwlambert]

Feedback from WG4 google document: Function list_distributions() is it possible to also list the pathogen/variant info in the output?

This change has been made in pull request #321. The list_distribution() function has been renamed parameter_tbl() now shows the pathogen. Here is an example:

library(epiparameter)
db <- epidist_db()
#> Returning 122 results that match the criteria (99 are parameterised). 
#> Use subset to filter by entry variables or single_epidist to return a single entry. 
#> To retrieve the citation for each use the 'get_citation' function
parameter_tbl(db)
#> # Parameter table:
#> # A data frame:    122 × 7
#>    disease  pathogen epi_distribution prob_distribution author  year sample_size
#>    <chr>    <chr>    <chr>            <chr>             <chr>  <dbl>       <dbl>
#>  1 Adenovi… Adenovi… incubation peri… lnorm             Lessl…  2009          14
#>  2 Human C… Human_C… incubation peri… lnorm             Lessl…  2009          13
#>  3 SARS     SARS-Co… incubation peri… lnorm             Lessl…  2009         157
#>  4 Influen… Influen… incubation peri… lnorm             Lessl…  2009         151
#>  5 Influen… Influen… incubation peri… lnorm             Lessl…  2009          90
#>  6 Influen… Influen… incubation peri… lnorm             Lessl…  2009          78
#>  7 Measles  Measles… incubation peri… lnorm             Lessl…  2009          55
#>  8 Parainf… Parainf… incubation peri… lnorm             Lessl…  2009          11
#>  9 RSV      RSV      incubation peri… lnorm             Lessl…  2009          24
#> 10 Rhinovi… Rhinovi… incubation peri… lnorm             Lessl…  2009          28
#> # ℹ 112 more rows

^{Created on 2024-05-30 with reprex v2.1.0}

[joshwlambert]

Function convert_params_to_summary_stats(), could the IQR, 95% percentile also be provided?

It is not clear to me what this is requesting. Converting from IQR or 95th percentile will not be done by convert_params_to_summary_stats(), but would be in extract_param() (as it would likely require numerical estimation).

The extract_param() function can already extract from percentiles, here is an example:

library(epiparameter)
extract_param(
  type = "percentiles", 
  values = c(5, 25), 
  distribution = "gamma", 
  percentiles = c(0.05, 0.95)
)
#> Stochastic numerical optimisation used. 
#> Rerun function multiple times to check global optimum is found
#>    shape    scale 
#> 4.589714 2.912114

^{Created on 2024-05-30 with reprex v2.1.0}

I will give some thought to adding extraction from interquartile range to the extract_param() function.

[joshwlambert]

Moving this to v0.4.0 milestone.