cervical_validation {pogit}

Cervical cancer valiation data

Description

Additionally to the main study sample (see cervical), validation data are available that give information on how likely physicians from different countries are to identify and correctly report a true cervical cancer death. In that study, a sample of physicians in each country completed a death certificate for one specific patient who had died of cervical cancer and the number of correct death certificates in each country was recorded. Validation data are therefore available on country level but provide no information on the reporting probability specific for age.

Usage

data(cervical_validation)

Format

A data frame with 4 rows and 6 variables:

v

number of correct death certificates in each country in the validation sample

m

size of validation sample in each country

country

factor variable of European countries

W.1, W.2, W.3

predictor variables for country effects using dummy coding (i.e. England, France, Italy)

Note

Belgium is used as the reference category.

Source

Kelson, M. and Farebrother, M. (1987). The Effect of Inaccuracies in Death Certification and Coding Practices in the European Economic Community (EEC) on International Cancer Mortality Statistics. International Journal of Epidemiology, 16, 3, 411-414.

Whittemore, A. S. and Gong, G. (1991). Poisson regression with missclassified counts: Application to cervical cancer mortality rates. Applied Statistics, 40, 81-93.

See Also

cervical, pogitBvs