[Customer Contribution] NPS

This post is from one of our customers!

Some handy snippets for calculating NPS and accuracy.

[nps]

((promoters/total ) - (detractors/total))

[nps_var]

((1 - [NPS]) ^ 2 * promoters/total + (0 -  [NPS]) ^ 2 * neutral/total + (-1 - [NPS]) ^ 2 * detractors/total)

Suggested Usage:

select
  npsdate
  , total as sample_size
  , [NPS] as nps
  , (sqrt([NPS_VAR]) / sqrt(total))  as moe2
  , (sqrt([NPS_VAR]) / sqrt(total))  as moe
  , [NPS] - (sqrt([NPS_VAR]) / sqrt(total)) as moe_lower
from
  (
    select
      [created:aggregation] as npsdate
      , count(1)::float as total
      , count(
        case
          when recommend <= 5
            then 1
        end )::float as detractors
      , count(
        case
          when recommend > 5
          and recommend < 9
            then 1
        end )::float as neutral
      , count(
        case
          when recommend >= 9
            then 1
        end )::float as promoters
    from
      your_nps_survey_table
    group by
      1
  )
  as respondents

You can use moe_lower, moe and moe2 to show error bars on results. Make moe_lower the same color as the background.

Updated 03-02-2023

CDT