handsome-library-89124
12/05/2022, 7:22 AMhelpful-application-7107
12/05/2022, 10:59 PMhandsome-library-89124
12/06/2022, 6:37 AMhandsome-library-89124
12/08/2022, 6:30 AMhelpful-application-7107
12/12/2022, 5:07 PMhandsome-library-89124
12/13/2022, 11:10 AMgreen-jordan-83609
01/10/2023, 2:16 PMhelpful-application-7107
01/10/2023, 5:56 PMhelpful-application-7107
01/10/2023, 10:02 PMhelpful-application-7107
01/10/2023, 10:04 PMgreen-jordan-83609
01/11/2023, 8:30 AMgreen-jordan-83609
01/11/2023, 8:37 AM...all previous steps... ,
__stats as (
-- One row per variation/dimension with aggregations
SELECT
d.variation,
d.dimension,
SUM(IFF(m.value is null, 1, 0)) as num_nulls_numerator,
SUM(IFF(d.value is null, 1, 0)) as num_nulls_denominator
FROM
__userDenominator d
LEFT JOIN __userMetric m ON (d.user_id = m.user_id)
GROUP BY
d.variation,
d.dimension
)
select *
FROM __stats
To check if this final join gets any null (i.e. some users might be in the denominator and not in the numerator, therefore retrieving a null in m.value
). That’s not the case, as this query retrieves 0 in both cases.green-jordan-83609
01/11/2023, 8:55 AMgreen-jordan-83609
01/11/2023, 8:57 AMmean=query_mean
and std = query_stddev / sqrt(num_users)
?
Thanks a lot and let us know if we can help with anything else!helpful-application-7107
01/11/2023, 3:18 PMview queries
, can you share the results from the ratio metric?helpful-application-7107
01/11/2023, 3:18 PMhelpful-application-7107
01/11/2023, 3:41 PMgbstats
and the values in your case are small (mean) and uncertain (variance), and the log approximation can suffer when the mean values are close to zero. We have a check built in gbstats
here that returns no meaningful information for the posterior distribution when this check fails, since the log approximation could be inexact.helpful-application-7107
01/11/2023, 3:42 PMgreen-jordan-83609
01/11/2023, 3:49 PMhelpful-application-7107
01/11/2023, 3:51 PM