Degrees of freedom approximations and rules-of-thumb

In complex samples, t-distributions are used when performing hypothesis tests and constructing confidence intervals. Rules-of-thumb are typically used to approximate degrees of freedom for the t-distributions. The standard rule is to set the degrees of freedom equal to the number of primary sampling units minus the number of strata. We illustrate some circumstances where these rules can be poor. A simple estimate of degrees of freedom is presented that leads to improved confidence interval coverage. © Statistics Sweden.