Estimating population segments
A method performed by one or more processing devices includes receiving a request to generate an estimate of a size of a population segment that accesses a resource; identifying, in demographic data, a number of counted users for the population segment; generating an estimate of a number of uncounted users in the population segment that access the resource; and generating, from the number of counted users and the number of uncounted users, the estimate of the size of the population segment.
1. A method performed by one or more processing devices, comprising:
receiving a request to generate an estimate of a size of a population segment that accesses a resource;
identifying, in demographic data, a number of counted users for the population segment;
generating an estimate of a number of uncounted users in the population segment that access the resource within a specified period of time, wherein the estimate of the number of uncounted users includes an estimate of a number of unidentified users in the population segment that have accessed the resource in the past for which no demographic data was available or otherwise stored in association with the access; and
generating, from the number of counted users and the number of uncounted users, the estimate of the size of the population segment.
2. The method of claim 1 , wherein the demographic data comprises first demographic data and second demographic data, and wherein the method further comprises:
receiving, from a first source, the first demographic data; and
receiving, from a second source, the second demographic data.
3. The method of claim 2 , further comprising:
identifying, in the first demographic data, one or more first items of data that are associated with the population segment; and
identifying, in the second demographic data, one or more second items of data that are associated with the population segment.
4. The method of claim 3 , further comprising:
identifying, in the one or more first items, one or more items of data that is included in the one or more second items;
wherein generating the estimate of the number of uncounted users is based on a number of the one or more items identified in the one or more first items that are included in the one or more second items.
5. The method of claim 3 , further comprising:
identifying, in the one or more first items, an item of data that is associated with a first type of demographic data;
identifying, in the one or more second items, that the item of data identified is associated with a second type of demographic data that differs from the first type of demographic data; and
removing the item of data identified from the one or more first items and from the one or more second items.
6. The method of claim 3 , wherein the one or more first items comprise a first sample, the one or more second items comprise a second sample, and wherein generating the estimate of the number of uncounted users comprises:
generating the estimate based on the first sample and the second sample.
7. The method of claim 1 , wherein the estimate of the size of the population segment is based on a probability distribution of
P
(
n
0
=
k
π
i
,
1
≤
i
≤
N
)
=
(
k
+
n
-
1
k
-
1
)
[
∏
S
⋐
N
(
∏
i
∈
S
π
i
n
S
)
(
∏
i
∈
S
(
1
-
π
i
)
nS
)
]
(
∏
i
<
N
(
1
-
π
i
)
k
)
.
;
wherein k is a random variable;
wherein π i is an unknown probability value;
wherein n 0 is the number of uncounted users;
wherein N is the number of counted users for the population segment;
wherein S is a subset of N;
wherein i is an integer value; and
wherein n is a number of samples in a union of samples.
8. One or more machine-readable media configured to store instructions that are executable by one or more processing devices to perform operations comprising:
receiving a request to generate an estimate of a size of a population segment that accesses a resource;
identifying, in demographic data, a number of counted users for the population segment;
generating an estimate of a number of uncounted users in the population segment that access the resource within a specified period of time, wherein the estimate of the number of uncounted users includes an estimate of a number of unidentified users in the population segment that have accessed the resource in the past for which no demographic data was available or otherwise stored in association with the access; and
generating, from the number of counted users and the number of uncounted users, the estimate of the size of the population segment.
9. The one or more machine-readable media of claim 8 , wherein the demographic data comprises first demographic data and second demographic data, wherein the operations further comprise:
receiving, from a first source, the first demographic data; and
receiving, from a second source, the second demographic data.
10. The one or more machine-readable media of claim 9 , wherein the operations further comprise:
identifying, in the first demographic data, one or more first items of data that are associated with the population segment; and
identifying, in the second demographic data, one or more second items of data that are associated with the population segment.
11. The one or more machine-readable media of claim 10 , wherein the operations further comprise:
identifying, in the one or more first items, one or more items of data that is included in the one or more second items;
wherein generating the estimate of the number of uncounted users is based on a number of the one or more items identified in the one or more first items that are included in the one or more second items.
12. The one or more machine-readable media of claim 10 , wherein the operations further comprise:
identifying, in the one or more first items, an item of data that is associated with a first type of demographic data;
identifying, in the one or more second items, that the item of data identified is associated with a second type of demographic data that differs from the first type of demographic data; and
removing the item of data identified from the one or more first items and from the one or more second items.
13. The one or more machine-readable media of claim 10 , wherein the one or more first items comprise a first sample, the one or more second items comprise a second sample, and wherein generating the estimate of the number of uncounted users comprises:
generating the estimate based on the first sample and the second sample.
14. The one or more machine-readable media of claim 8 , wherein the estimate of the size of the population segment is based on a probability distribution of
P
(
n
0
=
k
π
i
,
1
≤
i
≤
N
)
=
(
k
+
n
-
1
k
-
1
)
[
∏
S
⋐
N
(
∏
i
∈
S
π
i
n
S
)
(
∏
i
∉
S
(
1
-
π
i
)
nS
)
]
(
∏
i
<
N
(
1
-
π
i
)
k
)
.
;
wherein k is a random variable;
wherein π i is an unknown probability value;
wherein n 0 is the number of uncounted users;
wherein N is the number of counted users for the population segment;
wherein S is a subset of N;
wherein i is an integer value; and
wherein n is a number of samples in a union of samples.
15. An electronic system comprising:
one or more processing devices; and
one or more machine-readable media configured to store instructions that are executable by the one or more processing devices to perform operations comprising:
receiving a request to generate an estimate of a size of a population segment that accesses a resource;
identifying, in demographic data, a number of counted users for the population segment;
generating an estimate of a number of uncounted users in the population segment that access the resource within a specified period of time, wherein the estimate of the number of uncounted users includes an estimate of a number of unidentified users in the population segment that have accessed the resource in the past for which no demographic data was available or otherwise stored in association with the access; and
generating, from the number of counted users and the number of uncounted users, the estimate of the size of the population segment.
16. The electronic system of claim 15 , wherein the demographic data comprises first demographic data and second demographic data, wherein the operations further comprise:
receiving, from a first source, the first demographic data; and
receiving, from a second source, the second demographic data.
17. The electronic system of claim 16 , wherein the operations further comprise:
identifying, in the first demographic data, one or more first items of data that are associated with the population segment; and
identifying, in the second demographic data, one or more second items of data that are associated with the population segment.
18. The electronic system of claim 17 , wherein the operations further comprise:
identifying, in the one or more first items, one or more items of data that is included in the one or more second items;
wherein generating the estimate of the number of uncounted users is based on a number of the one or more items identified in the one or more first items that are included in the one or more second items.
19. The electronic system of claim 17 , wherein the operations further comprise:
identifying, in the one or more first items, an item of data that is associated with a first type of demographic data;
identifying, in the one or more second items, that the item of data identified is associated with a second type of demographic data that differs from the first type of demographic data; and
removing the item of data identified from the one or more first items and from the one or more second items.
20. The electronic system of claim 17 , wherein the one or more first items comprise a first sample, the one or more second items comprise a second sample, and wherein generating the estimate of the number of uncounted users comprises:
generating the estimate based on the first sample and the second sample.
21. The electronic system of claim 15 , wherein the estimate of the size of the population segment is based on a probability distribution of
P
(
n
0
=
k
π
i
,
1
≤
i
≤
N
)
=
(
k
+
n
-
1
k
-
1
)
[
∏
S
⋐
N
(
∏
i
∈
S
π
i
n
S
)
(
∏
i
∉
S
(
1
-
π
i
)
nS
)
]
(
∏
i
<
N
(
1
-
π
i
)
k
)
.
;
wherein k is a random variable;
wherein π i is an unknown probability value;
wherein n 0 is the number of uncounted users;
wherein N is the number of counted users for the population segment;
wherein S is a subset of N;
wherein i is an integer value; and
wherein n is a number of samples in a union of samples.