svyPVttest: Computation of a t-test for data from a complex survey design...

In manuelreif/svyPVpack: A package for complex surveys including plausible values

Description

Computes a one-sample or two-sample t-test for data from a complex survey design with usage of plausible values.

Usage

svyPVttest(formula, design, placeholder = 1:10)

Arguments

formula	Formula, outcome~group for two-sample, outcome~0 or outcome~1 for one-sample (all variables have to be part of a survey design objecct created by the survey package). For a notation description for the plausible values see in 'details'.
design	a survey design which was generated by the survey package.
placeholder	a vector of symbols, which were used for numbering the plausible values. For a detailed description see in 'details'.

Details

All variables mentioned in the formula object must be part of the survey design object. Instead of the symbols, which were used for numbering the plausible values use '..' as notation (e.g. placeholder = 1:5 and PVLIT.. stands for PVLIT1, PVLIT2, PVLIT3, PVLIT4, PVLIT5). Missing values are deleted listwise.

Value

The function returns a list, which includes the following three dataframes.

DESC	Shows mean and SE for each group.
TEST	Shows the test statistic (t.value, degf and Pr.t).
N	Shows the unweighted number of cases and the sum of weights (NA's excluded) within each group.

Author(s)

Jakob Peterbauer

References

Lumley, T. (2010). Complex Surveys. Hoboken, NJ: Wiley.

Saerndal, C.-E. & Swensson, B. & Wretman, J. (1992). Model Assisted Survey Sampling. New York: Springer.

Chaudhuri, A. & Stenger, H. (2005). Survey Sampling. Theory and Methods. Boka Raton, FL: Chapman & Hall/CRC. .

See Also

svyttest, svyPVpm, svyPVglm

Examples

data(svy_example1)
res <- svyPVttest(plaus.. ~ sex, svy.exrep, placeholder = 1:3)

res

manuelreif/svyPVpack documentation built on May 21, 2019, 11:26 a.m.