pool_cor function

Calculates the pooled correlation coefficient and Confidence intervals

pool_cor Calculates the pooled correlation coefficient and Confidence intervals.

pool_cor(
  data,
  conf.level = 0.95,
  dfcom = NULL,
  statistic = TRUE,
  df_small = TRUE,
  approxim = "tdistr"
)

Arguments

• data: An object of class 'mistats' ('Multiply Imputed Statistical Analysis'.) or a m x 2 matrix with C-index values and standard errors in the first and second column. For the latter option dfcom has to be provided.
• conf.level: conf.level Confidence level of the confidence intervals.
• dfcom: Number of completed-data analysis degrees of freedom. Default number is taken from function cindex
• statistic: if TRUE (default) the test statistic and p-value are provided, if FALSE these are not shown. See details.
• df_small: if TRUE (default) the (Barnard & Rubin) small sample correction for the degrees of freedom is applied, if FALSE the old number of degrees of freedom is calculated.
• approxim: if "tdistr" a t-distribution is used (default), if "zdistr" a z-distribution is used to derive a p-value for the test statistic.

Returns

An object of class mipool from which the following objects can be extracted:

• cor correlation coefficient
• SE standard error
• t t-value (for confidence interval)
• low_r lower limit of confidence interval
• high_r upper limit of confidence interval
• statistic test statistic
• pval p-value

Details

Rubin's Rules are used for pooling. The correlation coefficient is first transformed using Fisher z transformation (function cor2fz) before pooling and finally back transformed (function fz2cor). The test statistic and p-values are obtained using the Fisher z transformation.

Examples

imp_dat <- df2milist(lbpmilr, impvar="Impnr")
 res_stats <- with(data=imp_dat,
  expr = cor_est(y=BMI, x=Age))
 res <- pool_cor(res_stats)
 res

See Also

with.milist, cor_est

Author(s)

Martijn Heymans, 2022