Skip to contents

Extract the self controlled case series (sccs) diagostic results

Source: R/EstimationQueries.R
getSccsDiagnosticsData.Rd

This function extracts the sccs diagnostics that examine whether the analyses were sufficiently powered and checks for different types of bias.

Usage

getSccsDiagnosticsData(
  connectionHandler,
  schema,
  sccsTablePrefix = "sccs_",
  cgTablePrefix = "cg_",
  databaseTable = "database_meta_data",
  targetIds = NULL,
  outcomeIds = NULL
)

Arguments

connectionHandler

A connection handler that connects to the database and extracts sql queries. Create a connection handler via `ResultModelManager::ConnectionHandler$new()`.

schema

The result database schema (e.g., 'main' for sqlite)

sccsTablePrefix

The prefix used for the cohort generator results tables

cgTablePrefix

The prefix used for the cohort generator results tables

databaseTable

The name of the table with the database details (default 'database_meta_data')

targetIds

A vector of integers corresponding to the target cohort IDs

outcomeIds

A vector of integers corresponding to the outcome cohort IDs

Value

Returns a data.frame with the columns:

  • databaseName the database name

  • analysisId the analysis unique identifier

  • description an analysis description

  • targetName the target name

  • targetId the target cohort id

  • outcomeName the outcome name

  • outcomeId the outcome cohort id

  • covariateName whether main or secondary analysis

  • mdrr the maximum passable minimum detectable relative risk (mdrr) value. If the mdrr is greater than this the diagnostics will fail.

  • ease The expected absolute systematic error (ease) measures residual bias.

  • timeTrendP The p for whether the mean monthly ratio between observed and expected is no greater than 1.25.

  • preExposureP One-sided p-value for whether the rate before expore is higher than after, against the null of no difference.

  • mdrrDiagnostic whether the mdrr (power) diagnostic passed or failed.

  • easeDiagnostic whether the ease diagnostic passed or failed.

  • timeTrendDiagnostic Pass / warning / fail / not evaluated classification of the time trend (unstalbe months) diagnostic.

  • preExposureDiagnostic Pass / warning / fail / not evaluated classification of the time trend (unstalbe months) diagnostic.

  • unblind whether the results can be unblinded.

  • unblindForEvidenceSynthesis whether the results can be unblinded for the meta analysis.

  • summaryValue summary of diagnostics results. FAIL, PASS or number of warnings.

Details

Specify the connectionHandler, the schema and the target/outcome cohort IDs

See also

Other Estimation: getCMEstimation(), getCmDiagnosticsData(), getCmMetaEstimation(), getSccsEstimation(), getSccsMetaEstimation(), plotCmEstimates(), plotSccsEstimates()

Examples

conDet <- getExampleConnectionDetails()

connectionHandler <- ResultModelManager::ConnectionHandler$new(conDet)
#> Connecting using SQLite driver

sccsDiag <- getSccsDiagnosticsData(
  connectionHandler = connectionHandler, 
  schema = 'main',
  targetIds = 1,
  outcomeIds = 3
)