Fundraising 2010/Report/Draft Test 10

From Meta, a Wikimedia project coordination wiki

[edit]

For additional documentation on the testing methodology please see the following pages:


Banners[edit]

Sue. This is a static banner and features the text "Please read: A personal appeal from Wikimedia Executive Director Sue Gardner.".


Jimmy. This is a static banner and features the text "Please read: An personal appeal from Wikipedia founder Jimmy Wales.".


Result[edit]

Test Time: 2010-12-13 15:05:00 UTC - 2010-12-13 16:53:00 UTC
Sampling Interval = 6 minutes
Testing Interval = 108 minutes
Total Number of Samples per Class = 18

Donations / Impression*: "Jimmy" banner won by 65.69%.
Amount50 / Impression**: "Jimmy" banner won by 58.77%.

WINNER: "Jimmy"


(*) The rate of donations per banner impression over a fixed time interval.

(**) The rate of amount50 per banner impression over a fixed time interval. Amount50 is the dollar amount raised from donations initiated under a given banner where all donations of more than $50 are recorded as $50 donations. This counters the skewing effect of outlier donations.

Data Analysis[edit]

This section analyzes and interprets the results of the tests.

Data Consistency and Cleaning[edit]

The plots below display the counts of the data sources over the testing period as verification of the consistency of the donation pipeline data used in testing. It should be noted that a certain amount of natural variance is expected in donation counts and is no cause for alarm. The bottom two figures depict the total views and donations with those coming from each banner. This illustrates when the campaign becomes active and is also a useful tool for determining where anomalous behaviour may be visible in the data. It is of note that there are a couple of intervals where the impressions dipped down to zero, however these were sparse enough not to effect the quality of the data significantly. It should be noted that the data is analyzed over a period at least as large as the full testing period and that the testing period was chosen based on the period of time where significant hits and donations were observed.

It should be noted that for the two line plots showing view and donation totals an additional banner was running along with the two being compared and so the totals in those plots may show an overestimate of the impressions generated from the banners being tested.

Impressions broken out in two minute intervals over the test period.


Donations broken out in two minute intervals over the test period.


Donations/Impression broken out in two minute intervals over the test period.


Amount50/Impression broken out in two minute intervals over the test period.


The views corresponding to each banner and the total views over the campaign for two minute intervals.


The donations corresponding to each banner and the total donations over the campaign for two minute intervals.

Analyzing the above plots the donation and impression data appear to be quite regular over the interval 2010-12-13 15:05:00 UTC - 2010-12-13 16:53:00 UTC. Therefore, two minute intervals will be used for sampling over this period as a source for the paired t-test to assess confidence in the winner.

Modelling and Hypothesis Testing[edit]

"Jimmy" won in each case for donations/impression and amount50/impression with increases of 65.69% and 58.77% respectively. The student's t-test was used to assess confidence over each metric and the confidence in the winner for donations/impression and amount50/impression is at least 99.0% and 97.5% respectively. This is a significant win for the "Jimmy" banner.

Mean and standard deviation over test intervals over Donations / Impression.


Mean and standard deviation over test intervals over Amount50 / Impression

NOTE: These banners were not served to readers in equal amounts.  The values in brackets show estimates of the counts if the banners were served at equal amounts.

TOTAL SHARE OF IMPRESSIONS "Jimmy": 67.9%
TOTAL SHARE OF IMPRESSIONS "Sue": 32.1%

TOTAL DONATIONS "Jimmy": 261 (192.19)
TOTAL DONATIONS "Sue": 72 (112.15)

TOTAL AMOUNT50* RAISED "Jimmy": $6863.33 ($5053.99)
TOTAL AMOUNT50* RAISED "Sue": $1945.00 ($3029.56)

* AMOUNT50 indicates the total amount raised where all donations greater than $50 are taken to be a donation of $50.


DONATIONS PER IMPRESSION:

Between 99.0% and 99.5% confident about the winner.

Sue VS Jimmy -- 2010-12-13 15:05:00 - 2010-12-13 16:53:00

item 1  = Sue
item 2  = Jimmy

The winner Jimmy had a 65.69% increase.

interval	mean1		mean2		stddev1		stddev2

0		0.00008		0.00009		0.00003		0.00000
1		0.00004		0.00010		0.00002		0.00002
2		0.00006		0.00010		0.00010		0.00002


Overall Parameters:

mean1		mean2		stddev1		stddev2
0.00006		0.00010		0.00006		0.00002


AMOUNT50 PER IMPRESSION:

Between 97.5% and 99.0% confident about the winner.

Sue VS Jimmy -- 2010-12-13 15:05:00 - 2010-12-13 16:53:00

item 1  = Sue
item 2  = Jimmy

The winner Jimmy had a 58.77% increase.

interval	mean1		mean2		stddev1		stddev2

0		0.00216		0.00275		0.00007		0.00052
1		0.00128		0.00250		0.00045		0.00036
2		0.00145		0.00251		0.00286		0.00025


Overall Parameters:

mean1		mean2		stddev1		stddev2
0.00163		0.00259		0.00167		0.00039

Endnotes[edit]

  1. Campaign = "20101213JA009"
  2. "Jimmy" utm_source = "20101213_JA012A_US"
  3. "Sue" utm_source = "20101210_SA004A_US"