Closed iamstein closed 1 year ago
In the script for xgx_conf_int, the function is coded as follows:
if (distribution == "normal") { mu <- mean(y) qtt <- stats::qt(percentile_value, length(y)) s_v = sqrt(stats::var(y) / length(y)) conf_int_out <- data.frame( y = mu, ymin = mu - qtt * s_v, ymax = mu + qtt * s_v ) }
Could you explain why it is 'length(y)' and not 'length(y) -1' as for a t distribution df should be 'n-1'?
Issue has been resolved in version 1.1.3
In the script for xgx_conf_int, the function is coded as follows:
Could you explain why it is 'length(y)' and not 'length(y) -1' as for a t distribution df should be 'n-1'?