paired vs two sample t-test
$begingroup$
It's been awhile since taking Prob. & Stats in college. My question is regarding which test to use in the following situation. I have two data sets that contain values regarding some testing/quality control procedure in a manufacturing process.
The first data set is when this particular testing/quality control procedure was being carried out by a human, while the second data set is when this same testing/quality control procedure was being done by a robot.
I would like to find out whether or not there is a significant relationship between these two data sets, using the t-test. A coworker had recommended the paired t-test, but as I am refreshing my knowledge on prob & stats, it seems like the 2-sample (independent) t-test would be more appropriate in this situation.
My question is basically: Which one should I use? The paired or the 2-sample t-test?
probability statistics hypothesis-testing
asked Dec 5 '18 at 4:10
davlovskydavlovsky
11
$endgroup$
|
show 3 more comments
$begingroup$
It's been awhile since taking Prob. & Stats in college. My question is regarding which test to use in the following situation. I have two data sets that contain values regarding some testing/quality control procedure in a manufacturing process.
The first data set is when this particular testing/quality control procedure was being carried out by a human, while the second data set is when this same testing/quality control procedure was being done by a robot.
I would like to find out whether or not there is a significant relationship between these two data sets, using the t-test. A coworker had recommended the paired t-test, but as I am refreshing my knowledge on prob & stats, it seems like the 2-sample (independent) t-test would be more appropriate in this situation.
My question is basically: Which one should I use? The paired or the 2-sample t-test?
probability statistics hypothesis-testing
asked Dec 5 '18 at 4:10
davlovskydavlovsky
11
$endgroup$
$begingroup$
So what is the variable being measured and are you comparing one test versus another on the same sample subjects?
$endgroup$
– Phil H
Dec 5 '18 at 7:03
$begingroup$
Good questions. There are several variables being measured, but each one will have their own t-test. One variable, for example, would be the percentage of alcohol found within some solution. The second question I am not too sure about. Lets say that in case (1) the exact same solutions were being measured (same product, unit/serial number) and in case (2) same product but different unit/serial number.
$endgroup$
– davlovsky
Dec 5 '18 at 13:04
$begingroup$
The paired t-test is appropriate to use when comparing measurements taken on the same subject often before and after a treatment involving many different subjects. In your particular case, this would be appropriate if the two methods of measurement were applied to identical samples. But if "all" the samples are identical (I assume there are many test samples) there is nothing to gain from it. From what you say, I'm not sure what your situation is. The reason for this is because we want to measure the difference in measurement methods and not the differences between samples.
$endgroup$
– Phil H
Dec 5 '18 at 19:25
$begingroup$
Thanks for the reply. There are 19 unique tests. For these 19 unique tests, 30 samples are being tested. One data set contains the 19x30 matrix where these tests were performed by a robot. A second data set contains another 19x30 matrix of values where these tests were performed by a human. So, yes, we're testing to see whether or not there is a statistical difference between the measurement methods. Ultimately I would like to combine all the p-values for all 19 tests and do a "meta-analysis" of sorts.
$endgroup$
– davlovsky
Dec 5 '18 at 20:00
$begingroup$
(And the samples being tested are the same.)
$endgroup$
– davlovsky
Dec 5 '18 at 20:08
|
show 3 more comments
$begingroup$
It's been awhile since taking Prob. & Stats in college. My question is regarding which test to use in the following situation. I have two data sets that contain values regarding some testing/quality control procedure in a manufacturing process.
The first data set is when this particular testing/quality control procedure was being carried out by a human, while the second data set is when this same testing/quality control procedure was being done by a robot.
I would like to find out whether or not there is a significant relationship between these two data sets, using the t-test. A coworker had recommended the paired t-test, but as I am refreshing my knowledge on prob & stats, it seems like the 2-sample (independent) t-test would be more appropriate in this situation.
My question is basically: Which one should I use? The paired or the 2-sample t-test?
probability statistics hypothesis-testing
asked Dec 5 '18 at 4:10
davlovskydavlovsky
11
$endgroup$
It's been awhile since taking Prob. & Stats in college. My question is regarding which test to use in the following situation. I have two data sets that contain values regarding some testing/quality control procedure in a manufacturing process.
The first data set is when this particular testing/quality control procedure was being carried out by a human, while the second data set is when this same testing/quality control procedure was being done by a robot.
I would like to find out whether or not there is a significant relationship between these two data sets, using the t-test. A coworker had recommended the paired t-test, but as I am refreshing my knowledge on prob & stats, it seems like the 2-sample (independent) t-test would be more appropriate in this situation.
My question is basically: Which one should I use? The paired or the 2-sample t-test?
probability statistics hypothesis-testing
probability statistics hypothesis-testing
asked Dec 5 '18 at 4:10
davlovskydavlovsky
11
asked Dec 5 '18 at 4:10
davlovskydavlovsky
11
asked Dec 5 '18 at 4:10
davlovskydavlovsky
11
asked Dec 5 '18 at 4:10
davlovskydavlovsky
11
asked Dec 5 '18 at 4:10
davlovskydavlovsky
11
11
$begingroup$
So what is the variable being measured and are you comparing one test versus another on the same sample subjects?
$endgroup$
– Phil H
Dec 5 '18 at 7:03
$begingroup$
Good questions. There are several variables being measured, but each one will have their own t-test. One variable, for example, would be the percentage of alcohol found within some solution. The second question I am not too sure about. Lets say that in case (1) the exact same solutions were being measured (same product, unit/serial number) and in case (2) same product but different unit/serial number.
$endgroup$
– davlovsky
Dec 5 '18 at 13:04
$begingroup$
The paired t-test is appropriate to use when comparing measurements taken on the same subject often before and after a treatment involving many different subjects. In your particular case, this would be appropriate if the two methods of measurement were applied to identical samples. But if "all" the samples are identical (I assume there are many test samples) there is nothing to gain from it. From what you say, I'm not sure what your situation is. The reason for this is because we want to measure the difference in measurement methods and not the differences between samples.
$endgroup$
– Phil H
Dec 5 '18 at 19:25
$begingroup$
Thanks for the reply. There are 19 unique tests. For these 19 unique tests, 30 samples are being tested. One data set contains the 19x30 matrix where these tests were performed by a robot. A second data set contains another 19x30 matrix of values where these tests were performed by a human. So, yes, we're testing to see whether or not there is a statistical difference between the measurement methods. Ultimately I would like to combine all the p-values for all 19 tests and do a "meta-analysis" of sorts.
$endgroup$
– davlovsky
Dec 5 '18 at 20:00
$begingroup$
(And the samples being tested are the same.)
$endgroup$
– davlovsky
Dec 5 '18 at 20:08
|
show 3 more comments
$begingroup$
So what is the variable being measured and are you comparing one test versus another on the same sample subjects?
$endgroup$
– Phil H
Dec 5 '18 at 7:03
$begingroup$
Good questions. There are several variables being measured, but each one will have their own t-test. One variable, for example, would be the percentage of alcohol found within some solution. The second question I am not too sure about. Lets say that in case (1) the exact same solutions were being measured (same product, unit/serial number) and in case (2) same product but different unit/serial number.
$endgroup$
– davlovsky
Dec 5 '18 at 13:04
$begingroup$
The paired t-test is appropriate to use when comparing measurements taken on the same subject often before and after a treatment involving many different subjects. In your particular case, this would be appropriate if the two methods of measurement were applied to identical samples. But if "all" the samples are identical (I assume there are many test samples) there is nothing to gain from it. From what you say, I'm not sure what your situation is. The reason for this is because we want to measure the difference in measurement methods and not the differences between samples.
$endgroup$
– Phil H
Dec 5 '18 at 19:25
$begingroup$
Thanks for the reply. There are 19 unique tests. For these 19 unique tests, 30 samples are being tested. One data set contains the 19x30 matrix where these tests were performed by a robot. A second data set contains another 19x30 matrix of values where these tests were performed by a human. So, yes, we're testing to see whether or not there is a statistical difference between the measurement methods. Ultimately I would like to combine all the p-values for all 19 tests and do a "meta-analysis" of sorts.
$endgroup$
– davlovsky
Dec 5 '18 at 20:00
$begingroup$
(And the samples being tested are the same.)
$endgroup$
– davlovsky
Dec 5 '18 at 20:08
$begingroup$
So what is the variable being measured and are you comparing one test versus another on the same sample subjects?
$endgroup$
– Phil H
Dec 5 '18 at 7:03
$begingroup$
So what is the variable being measured and are you comparing one test versus another on the same sample subjects?
$endgroup$
– Phil H
Dec 5 '18 at 7:03
$begingroup$
Good questions. There are several variables being measured, but each one will have their own t-test. One variable, for example, would be the percentage of alcohol found within some solution. The second question I am not too sure about. Lets say that in case (1) the exact same solutions were being measured (same product, unit/serial number) and in case (2) same product but different unit/serial number.
$endgroup$
– davlovsky
Dec 5 '18 at 13:04
$begingroup$
Good questions. There are several variables being measured, but each one will have their own t-test. One variable, for example, would be the percentage of alcohol found within some solution. The second question I am not too sure about. Lets say that in case (1) the exact same solutions were being measured (same product, unit/serial number) and in case (2) same product but different unit/serial number.
$endgroup$
– davlovsky
Dec 5 '18 at 13:04
$begingroup$
The paired t-test is appropriate to use when comparing measurements taken on the same subject often before and after a treatment involving many different subjects. In your particular case, this would be appropriate if the two methods of measurement were applied to identical samples. But if "all" the samples are identical (I assume there are many test samples) there is nothing to gain from it. From what you say, I'm not sure what your situation is. The reason for this is because we want to measure the difference in measurement methods and not the differences between samples.
$endgroup$
– Phil H
Dec 5 '18 at 19:25
$begingroup$
The paired t-test is appropriate to use when comparing measurements taken on the same subject often before and after a treatment involving many different subjects. In your particular case, this would be appropriate if the two methods of measurement were applied to identical samples. But if "all" the samples are identical (I assume there are many test samples) there is nothing to gain from it. From what you say, I'm not sure what your situation is. The reason for this is because we want to measure the difference in measurement methods and not the differences between samples.
$endgroup$
– Phil H
Dec 5 '18 at 19:25
$begingroup$
Thanks for the reply. There are 19 unique tests. For these 19 unique tests, 30 samples are being tested. One data set contains the 19x30 matrix where these tests were performed by a robot. A second data set contains another 19x30 matrix of values where these tests were performed by a human. So, yes, we're testing to see whether or not there is a statistical difference between the measurement methods. Ultimately I would like to combine all the p-values for all 19 tests and do a "meta-analysis" of sorts.
$endgroup$
– davlovsky
Dec 5 '18 at 20:00
$begingroup$
Thanks for the reply. There are 19 unique tests. For these 19 unique tests, 30 samples are being tested. One data set contains the 19x30 matrix where these tests were performed by a robot. A second data set contains another 19x30 matrix of values where these tests were performed by a human. So, yes, we're testing to see whether or not there is a statistical difference between the measurement methods. Ultimately I would like to combine all the p-values for all 19 tests and do a "meta-analysis" of sorts.
$endgroup$
– davlovsky
Dec 5 '18 at 20:00
$begingroup$
(And the samples being tested are the same.)
$endgroup$
– davlovsky
Dec 5 '18 at 20:08
$begingroup$
(And the samples being tested are the same.)
$endgroup$
– davlovsky
Dec 5 '18 at 20:08
|
show 3 more comments
0
active
oldest
votes
Your Answer
StackExchange.ifUsing("editor", function () {
return StackExchange.using("mathjaxEditing", function () {
StackExchange.MarkdownEditor.creationCallbacks.add(function (editor, postfix) {
StackExchange.mathjaxEditing.prepareWmdForMathJax(editor, postfix, [["$", "$"], ["\\(","\\)"]]);
});
});
}, "mathjax-editing");
StackExchange.ready(function() {
var channelOptions = {
tags: "".split(" "),
id: "69"
};
initTagRenderer("".split(" "), "".split(" "), channelOptions);
StackExchange.using("externalEditor", function() {
// Have to fire editor after snippets, if snippets enabled
if (StackExchange.settings.snippets.snippetsEnabled) {
StackExchange.using("snippets", function() {
createEditor();
});
}
else {
createEditor();
}
});
function createEditor() {
StackExchange.prepareEditor({
heartbeatType: 'answer',
autoActivateHeartbeat: false,
convertImagesToLinks: true,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: 10,
bindNavPrevention: true,
postfix: "",
imageUploader: {
brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
allowUrls: true
},
noCode: true, onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
});
}
});
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fmath.stackexchange.com%2fquestions%2f3026609%2fpaired-vs-two-sample-t-test%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
0
active
oldest
votes
0
active
oldest
votes
active
oldest
votes
active
oldest
votes
Thanks for contributing an answer to Mathematics Stack Exchange!
- Please be sure to answer the question. Provide details and share your research!
But avoid …
- Asking for help, clarification, or responding to other answers.
- Making statements based on opinion; back them up with references or personal experience.
Use MathJax to format equations. MathJax reference.
To learn more, see our tips on writing great answers.
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fmath.stackexchange.com%2fquestions%2f3026609%2fpaired-vs-two-sample-t-test%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
$begingroup$
So what is the variable being measured and are you comparing one test versus another on the same sample subjects?
$endgroup$
– Phil H
Dec 5 '18 at 7:03
$begingroup$
Good questions. There are several variables being measured, but each one will have their own t-test. One variable, for example, would be the percentage of alcohol found within some solution. The second question I am not too sure about. Lets say that in case (1) the exact same solutions were being measured (same product, unit/serial number) and in case (2) same product but different unit/serial number.
$endgroup$
– davlovsky
Dec 5 '18 at 13:04
$begingroup$
The paired t-test is appropriate to use when comparing measurements taken on the same subject often before and after a treatment involving many different subjects. In your particular case, this would be appropriate if the two methods of measurement were applied to identical samples. But if "all" the samples are identical (I assume there are many test samples) there is nothing to gain from it. From what you say, I'm not sure what your situation is. The reason for this is because we want to measure the difference in measurement methods and not the differences between samples.
$endgroup$
– Phil H
Dec 5 '18 at 19:25
$begingroup$
Thanks for the reply. There are 19 unique tests. For these 19 unique tests, 30 samples are being tested. One data set contains the 19x30 matrix where these tests were performed by a robot. A second data set contains another 19x30 matrix of values where these tests were performed by a human. So, yes, we're testing to see whether or not there is a statistical difference between the measurement methods. Ultimately I would like to combine all the p-values for all 19 tests and do a "meta-analysis" of sorts.
$endgroup$
– davlovsky
Dec 5 '18 at 20:00
$begingroup$
(And the samples being tested are the same.)
$endgroup$
– davlovsky
Dec 5 '18 at 20:08