David Dunaetz Hello sir, I am having airborne dust concentrations data for >1 micron size, >3 micron, 5 micron and >10 micron size. (> means greater than) These data was taken before and during dust producing work in field study. N=5 How can i compare these before and during operations data ? It seems that there is relative percent variation in dust concentrations in atmosphere between before and during operation data. (Taking >1) micron as 100 %) Before operation: The relative percent variation of concentration with different particle size is as below. For example Concentration of >1 micron size particle is 100%. >3 micron: 80% >5 micron : 60% >10 micron: 40%. During operation: Concentration of >1 micron size particle is 100%. >3 micron: 90% >5 micron : 80% >10 micron: 70%. It seems that >10 micron particle share is increased due to that machine operation...? Which test is suitable for analysing these type similar data for discussion ? How to use statistics? Any comparison among these concentrations of different particle sizes ? thank u.
I have calculated a correlation between two variables, emotional intelligence and learning styles among students, and my hypothesis is 1. Boys and girls will not differ significantly in their emotional intelligence. 2. Boys and girls will not differ significantly in their learning style. 3. There will be a positive relationship between emotional intelligence and learning styles of adolescent students. Which t-test should I use here?
Hi Ritka, The first two hypotheses could be explored using a two-sample t-test as explained in the video. For the first one, for example, you could compare the average emotional intelligence of boys to the average emotional intelligence of girls. However, hypothesis testing like this can't be used to test for a lack of difference. It can only test for differences, not similarities. If the null hypothesis is retained, it means that either the null hypothesis is true or the main (alternate) hypothesis is true: We can't tell which is true. We can never "accept" the null hypothesis as true, which is what you want to do in your first two hypotheses. In the third hypothesis, you want to test the significance of the correlation between emotional intelligence and learning style. You won't use a t-test; rather, you'll calculate the r and test to see if the r is significant. You will use a one-tailed test since your hypothesis is directional. There are other videos which show how to test the significance of r.
Hi David, I want to measure the similarity between A and B over 5 minutes using T test. A refers to statistical Mean for 3 minutes and B refers to statistical Mean for 5 minutes for the same person. So, what are the parameters for the T test? two tails or one tail. tails? and Type? if the P>0.05 does that mean A is similar to B? Best regards Ram
Hi Ram, To use a two sample t-test like I've shown in the video, you need to have all the data (not just the mean) for the three minute period and for the 5 minute period. You would enter the data into columns as shown on the video for each period. If you don't have all the data, you at least need to have the standard deviation for both periods. However, you'd have to use formulas for this calculation which are not covered in this video. Since you're getting your data from a single person, a more powerful test would be a repeated measures ANOVA. However, this is much more complicated than a 2 sample t-test. If the 2 sample t-test works, you can leave "good enough" alone. Also, a t-test can't measure similarity. It can only tell you if two things are significantly different (i.e., that the difference between two means is unlikely to be due to chance). To understand how different the means are, you need to calculate the effect size d. I have a short video which introduces effect size which might interest you. "Introduction to effect size": ruclips.net/video/2AKTNvVN3Dk/видео.html
It might be easier to use an online Cronbach alpha reliability calculator: www.google.com/search?q=online+cronbach+alpha+calculator If you google around, you can find an Excel spreadsheet with a reliability calculator and download it. Search for Cronbach's alpha rather than reliability.
In general, use the equal variance t-test unless you have a reason to assume the samples have unequal variance. This assumption would be rare; our null hypothesis is generally that the two samples come from the same population.
Thank you Sir your explanation was very helpful..but you mentioned the t value at the last as two tailed but I feel it should be one tailed ..right? Am I wrong Sir?
It's definitely a one-tailed test. At the end of the video, I say that it's a "two sample" t-test, which is very different than a "two-tailed test." If I said "two-tailed test" somewhere, please let me know at what point so that I can make a correction.
Excellent Video Thank you so much for the explanation. Please Mr. David Dunaetz, I have one question, with an independent sample, can I compare the theoretical (using calculator) vs. experimental (measured - real values measured) results with a t-test - independent sample?
Hi Victor. If you have a theoretical value that's already known, it would be better to do a single sample (one sample) t-test, using the theoretical value as the population value. Here's a video: ruclips.net/video/DgDUxaQhcDw/видео.html
Hi, Thanks. I am wondering why you picked up the equal variances? The descriptive statistics showed you both A and B have different variances. Please give me the reason!
+Hehradad Rabiei If you have reason to believe that the populations (and not just the samples) have different variances, you should use "unequal variances." There are very detailed discussions of this questions in many places on the web, e.g., stats.stackexchange.com/questions/305/when-conducting-a-t-test-why-would-one-prefer-to-assume-or-test-for-equal-vari
Thanks, i want to ask a think that, when I used more than 3 parameters for all subcategories in my study, and subjects are more than 100, with five subcategories, like; 20,20,20,20,20........,then which type of test or statistics I should have to apply?,,,,,
When reporting your results, you generally want to report the mean and the standard deviation for both samples. Excel doesn't provide the standard deviation directly when doing a t-test with with the Analysis TookPak.
When the probability is low, the null hypothesis (that these results are due to chance) is rejected. So when the null hypothesis is rejected, our main hypothesis is supported. That is, Division A is more stressed than Division B. It kind of goes back and forth like a ping-pong game.
@@DavidDunaetz thank you so much! I wanted to ask since I didn’t see a chi square one…do you have a video for that? Also how do you get the expected value when there isn’t one given?
@@rebeccabacchus3272 Sorry, I don't have a chi-square video. These videos are focused on organizational psychology, and we use chi-square very rarely. As for the expected difference in a t-test, it's almost 0. You'd have to be doing something much more advanced than what is covered in these videos for it to be something other than 0.
Sir, if the data from a stress survey given to the same 8 people in Division A and in Division B, in this case one tailed or two tailed test?? And kindly tell me how to know if to select if two samples are having equal or unequal variances. kindly it me know, would mean a lot. Thank you.
First, the 8 people in Division A are different from the 8 people in Division B. That's why we can say that it's a "two sample" test. Second, whether it is one-tailed or two-tailed depends on the hypothesis that you're trying to test. If your hypothesis is that Division A's stress is higher than Division B's stress, it's one tailed (you predicted which one would be higher). If your hypothesis is that the stress level in A will be different than the stress level in B, it's a two-tailed test (you didn't predict which one would be higher). Third, you can safely assume equal variances unless you have a specific reason to believe that the variances are not equal.
The p-value is the probability that we could have gotten a difference in group means this extreme if the two populations from which we got our samples had the same mean. If the probability is low enough (less than 5%), we say that the populations most likely don't have the same means, that is to say, the difference is significant.
+shery qures The difference between the two samples is significant if the p-value is less than .05, that is, there is less than a 5% chance of getting that big of a difference in means of two samples if, in fact, the two samples come from the same source (the same population). You choose the one-tail or two-tail p-value based on the hypothesis that you're testing.
@@DavidDunaetz I have both alternate and null hypothesis. I'm testing for the differences between finger ridge density in male and female. (this is where it gets complicated), I also want to compare the radial, ulnar and proximal ridge density areas of the fingers,between male and female. Pleaseeeee help me im in my last 3 months of uni
@@sq9779 Hi Shery. It sounds like you actually have 4 hypotheses (that is, 4 alternate hypotheses), all two-tails, that you want to test: 1. MaleFingerRD is different than FemaleFingerRD. 2. MaleRadialRD is different than FemaleRadialRD. 3. MaleUlnarRD is different than FemaleUlnarRD. 4. MaleProximalRD is different than FemaleProximalRD You need to do 4 different two-sample t-tests on the appropriate data. Be careful setting up your data on Excel. Everything needs to be grouped carefully. There are also some more complicated things you can do to prevent "alpha inflation" (i.e., avoiding false-positives), but I would guess that this would be beyond the scope of this project.
Hi Sam Kab, This is a good question. Note that we're hypothesizing, not assuming. If our hypothesis is the mean in Division B is greater than the mean in Division A, as soon as we calculate the means for the two divisions, we can tell that the hypothesis is not supported (since the mean for Div A is greater than the mean for Div B, the opposite of what we hypothesized). We don't even need to do a t-test. We have absolutely no evidence to support the hypothesis that Div B > Div A.
@@samkab677 There's no need to do a test. You just look at the data and say that it obviously doesn't support the hypothesis. You only need do a t-test to test a one-tailed hypothesis if the data seems to support the data but you want to find out if the difference in means of the sample is greater than what you would expect by chance if the two means were equal in the population. It's for this reason you should do a two-tailed test rather than a one-tailed test unless you're relatively certain that you know which one will be higher.
+aruna kumar You need to have a good reason to use the un-equal variance version of the t-test (for example, if the standard deviation of one sample was 4 times the size of the standard deviation of the other sample). But if you use the un-equal variance version of the test, you lose a lot of power. In general you should avoid it if you can. However, if you want to be very conservative and are willing to pay the price to avoid Typel 1 (alpha) error, you can always use the un-equal variance version. As a rule of thumb, most people always assume equal variances.
We have the data from a stress survey given to 8 people in Division A and the data from the same stress survey given to 8 people in Division B. The t-test allows us to use this data and make a conclusion whether the average stress level of the entire Division A is different the average stress level of the entire Division B. Stress is typically measured with instruments such as the "Perceived Stress Scale" or "Maslach Burnout Inventory." Much information on these scales can be found online.
David, thank you for you previous reply and let me ask one question. I am doing t-test for the research. I formulated the hypothesis (like A greater than B, one-tail) but means of t-test showed that B greater than A and moreover the difference was not statistically significant (p>0,1). What's the conclusion should I write ? Does it mean that the hypothesis should be rejected? Also does it mean that the bigger T-value, the more solid the result?
Hi +an166ful, In the situations you described, you made a directional (one tailed) hypothesis (A > B). However, your results came out indicating a trend in the opposite direction. So your conclusion should be that your hypothesis is not supported by this data. You need to retain the null hypothesis that there is no difference between A and B or even that B is greater than A. This means that your hypothesis still might be true, but that the data you collected provides absolutely no evidence for it being true.
Will it still works if you respondents for each variable is not the same for example variable a only has 18 respondents where data is gathered while variable b has 22
Hi Noraz. The mean difference would be the sum of all the differences divided by number pairs A and B that you have. The t-test compares the difference of the means of two different groups (Mean of A - Mean of B).
@@DavidDunaetz OK sir tqvm. I have this situation, where the result rmse is ok.lowest value of RMSE (Minimization). but the p-value is quite high. how can i interpret the result sir? Welch Two Sample t-test data: test_set$Close and mfopsoY t = -0.4243, df = 274, p-value = 0.6717 alternative hypothesis: true difference in means is not equal to 0 95 percent confidence interval: -0.002905947 0.001875425 sample estimates: mean of x mean of y 1.110894 1.111409 Appreciate your advise sir.tq
The sign of the t-value doesn't matter. You use its absolute value in the calculation of its p-value. However, if you made a one-tailed test and the difference is not in the direction you predicted, then the p-value doesn't matter, regardless of how small it is. In a two-tailed test, the sign doesn't matter, but you should always report which mean was higher.
Hi Mama.Cindas. The E-05 in the p value means "10 to the -5th power." So your p value is .0000596, which is very low. You should report this as p < .001. The difference between the sample means is significant.
It's because of our hypothesis: Division A is more stressed than Division B. This is a directional (or one-tailed) hypothesis because we're predicting which group will have a higher average score than the other. If we had hypothesized "The stress of Division A will be different than the stress of Division B," then that would have been a non-directional hypothesis and we would have used a two-tailed test.
It should work on Excel 2018 for Mac. However, you need to install the free statistics ToolPak. Here's a short video on how to do it: ruclips.net/video/1R_aJ_Fli2w/видео.html
![[TF2] The Russian Bear Trap](http://i.ytimg.com/vi/YFNSwz2_rOA/mqdefault.jpg)
why t(14) = 2.14?? it should be 2.11
+an166ful You're absolutely correct. The correct t value is 2.11 as calculated. It looks like I miscopied it when I was writing out the response.
David Dunaetz
Hello sir,
I am having airborne dust concentrations data for >1 micron size, >3 micron, 5 micron and >10 micron size.
(> means greater than)
These data was taken before and during dust producing work in field study.
N=5
How can i compare these before and during operations data ?
It seems that there is relative percent variation in dust concentrations in atmosphere between before and during operation data. (Taking >1) micron as 100 %)
Before operation:
The relative percent variation of concentration with different particle size is as below. For example
Concentration of >1 micron size particle is 100%.
>3 micron: 80%
>5 micron : 60%
>10 micron: 40%.
During operation:
Concentration of >1 micron size particle is 100%.
>3 micron: 90%
>5 micron : 80%
>10 micron: 70%.
It seems that >10 micron particle share is increased due to that machine operation...?
Which test is suitable for analysing these type similar data for discussion ?
How to use statistics?
Any comparison among these concentrations of different particle sizes ?
thank u.
David, you deserve the salary of my Professor. Thank you very much for this education. Now I am able to use excel to calculate t-test.
Finally I find someone explain clearly, thank u so much Sir.
I'm glad you found it useful!
Lovely demonstration of using Microsoft Excel to conduct the T-Test.I giggled lots when you made that cheeky mistake, hahah you sure are funny!!
Your video is the perfect guide for performing t-test for my Psychology dissertation data analysis. Thank You.
Sir, thank you so much for this. It saved me time from analyzing and interpreting my data.
Awesome demonstration of the descriptive statistic for calculating Std.Dev using two samples♥
Thank you so much. Your video is a lifesaver.
Glad it helped!
Thank you so much for this tutorial video.
I'm glad you found it useful!
Thank you so much for this valuable information.🙏🙏
this video really helped me out, thanks
thank you so much for this useful video
You're a life saver! Thank you!
Your video saved my life for a final! Thank you so much for your help!
Thank you so much Mr. David.
Thank you so much David, it helps me a lot for my data analysis : )
Glad it helped!
Data Analysis Toolpak OMG!!!
Thank you
I have calculated a correlation between two variables, emotional intelligence and learning styles among students, and my hypothesis is
1. Boys and girls will not differ significantly in their emotional intelligence.
2. Boys and girls will not differ significantly in their learning style.
3. There will be a positive relationship between emotional intelligence and learning styles of adolescent students.
Which t-test should I use here?
Hi Ritka,
The first two hypotheses could be explored using a two-sample t-test as explained in the video. For the first one, for example, you could compare the average emotional intelligence of boys to the average emotional intelligence of girls. However, hypothesis testing like this can't be used to test for a lack of difference. It can only test for differences, not similarities. If the null hypothesis is retained, it means that either the null hypothesis is true or the main (alternate) hypothesis is true: We can't tell which is true. We can never "accept" the null hypothesis as true, which is what you want to do in your first two hypotheses.
In the third hypothesis, you want to test the significance of the correlation between emotional intelligence and learning style. You won't use a t-test; rather, you'll calculate the r and test to see if the r is significant. You will use a one-tailed test since your hypothesis is directional. There are other videos which show how to test the significance of r.
Hi David,
I want to measure the similarity between A and B over 5 minutes using T test.
A refers to statistical Mean for 3 minutes and B refers to statistical Mean for 5 minutes for the same person.
So, what are the parameters for the T test?
two tails or one tail. tails? and Type?
if the P>0.05 does that mean A is similar to B?
Best regards
Ram
Hi Ram,
To use a two sample t-test like I've shown in the video, you need to have all the data (not just the mean) for the three minute period and for the 5 minute period. You would enter the data into columns as shown on the video for each period.
If you don't have all the data, you at least need to have the standard deviation for both periods. However, you'd have to use formulas for this calculation which are not covered in this video.
Since you're getting your data from a single person, a more powerful test would be a repeated measures ANOVA. However, this is much more complicated than a 2 sample t-test. If the 2 sample t-test works, you can leave "good enough" alone.
Also, a t-test can't measure similarity. It can only tell you if two things are significantly different (i.e., that the difference between two means is unlikely to be due to chance). To understand how different the means are, you need to calculate the effect size d. I have a short video which introduces effect size which might interest you. "Introduction to effect size": ruclips.net/video/2AKTNvVN3Dk/видео.html
Thanks A lot Professor
Thank you thank you thank you
You are very welcome.
Thanks sir.
Thank you for the video. I need a video to measure the validity for each question. Could you please make this video
It might be easier to use an online Cronbach alpha reliability calculator: www.google.com/search?q=online+cronbach+alpha+calculator
If you google around, you can find an Excel spreadsheet with a reliability calculator and download it. Search for Cronbach's alpha rather than reliability.
How do we decide whether to use the equal variance t-test or the unequal variance t-test?
In general, use the equal variance t-test unless you have a reason to assume the samples have unequal variance. This assumption would be rare; our null hypothesis is generally that the two samples come from the same population.
Hi David, thank you for the video! May I know what does the t stat show? And how do I use it to prove my hypothesis is right or wrong?
Here's a playlist explaining t-tests: ruclips.net/p/PLx-uqKoW1C5my0ofaBcC_O_7aRAirkIkI
Thank you!
Thank you Sir your explanation was very helpful..but you mentioned the t value at the last as two tailed but I feel it should be one tailed ..right? Am I wrong Sir?
It's definitely a one-tailed test. At the end of the video, I say that it's a "two sample" t-test, which is very different than a "two-tailed test." If I said "two-tailed test" somewhere, please let me know at what point so that I can make a correction.
Sir, how to identify equal variance and un-equal variance that is homogeneity of variance test
Excellent Video Thank you so much for the explanation. Please Mr. David Dunaetz, I have one question, with an independent sample, can I compare the theoretical (using calculator) vs. experimental (measured - real values measured) results with a t-test - independent sample?
Hi Victor. If you have a theoretical value that's already known, it would be better to do a single sample (one sample) t-test, using the theoretical value as the population value. Here's a video: ruclips.net/video/DgDUxaQhcDw/видео.html
Hi, Thanks. I am wondering why you picked up the equal variances? The descriptive statistics showed you both A and B have different variances. Please give me the reason!
+Hehradad Rabiei If you have reason to believe that the populations (and not just the samples) have different variances, you should use "unequal variances." There are very detailed discussions of this questions in many places on the web, e.g., stats.stackexchange.com/questions/305/when-conducting-a-t-test-why-would-one-prefer-to-assume-or-test-for-equal-vari
Hello again, when you wrote t(14)=2.14, did you mean 2.11 instead of 2.14 since that is what I see highlighted ….the 2.11?
Yes. See the note in text below the video.
Thanks, i want to ask a think that, when I used more than 3 parameters for all subcategories in my study, and subjects are more than 100, with five subcategories, like; 20,20,20,20,20........,then which type of test or statistics I should have to apply?,,,,,
If you're comparing the means of three or more samples, then a one-way ANOVA sounds like it be the appropriate test.
@@DavidDunaetz thanks sir.
Your understandable
And should the descriptive statistics be done all the time before the t-test?
When reporting your results, you generally want to report the mean and the standard deviation for both samples. Excel doesn't provide the standard deviation directly when doing a t-test with with the Analysis TookPak.
hey
but p value(0.03) is less than the significance level of 0.05, so the hypothesis is rejected right? so div A is not more stressed than div A?
When the probability is low, the null hypothesis (that these results are due to chance) is rejected. So when the null hypothesis is rejected, our main hypothesis is supported. That is, Division A is more stressed than Division B.
It kind of goes back and forth like a ping-pong game.
Why did you need to do the descriptive statistics before doing the one tailed computation?
To get the standard deviation for both samples, which is generally reported when doing t-tests. The Analysis ToolPak doesn't provide it automatically.
@@DavidDunaetz thank you so much!
I wanted to ask since I didn’t see a chi square one…do you have a video for that?
Also how do you get the expected value when there isn’t one given?
@@rebeccabacchus3272 Sorry, I don't have a chi-square video. These videos are focused on organizational psychology, and we use chi-square very rarely. As for the expected difference in a t-test, it's almost 0. You'd have to be doing something much more advanced than what is covered in these videos for it to be something other than 0.
Sir, if the data from a stress survey given to the same 8 people in Division A and in Division B, in this case one tailed or two tailed test?? And kindly tell me how to know if to select if two samples are having equal or unequal variances.
kindly it me know, would mean a lot. Thank you.
First, the 8 people in Division A are different from the 8 people in Division B. That's why we can say that it's a "two sample" test.
Second, whether it is one-tailed or two-tailed depends on the hypothesis that you're trying to test. If your hypothesis is that Division A's stress is higher than Division B's stress, it's one tailed (you predicted which one would be higher). If your hypothesis is that the stress level in A will be different than the stress level in B, it's a two-tailed test (you didn't predict which one would be higher).
Third, you can safely assume equal variances unless you have a specific reason to believe that the variances are not equal.
Hi just want to ask, how does the p-value becomes evidence that the difference was significant?
The p-value is the probability that we could have gotten a difference in group means this extreme if the two populations from which we got our samples had the same mean. If the probability is low enough (less than 5%), we say that the populations most likely don't have the same means, that is to say, the difference is significant.
How do we know if it is significant?
+shery qures The difference between the two samples is significant if the p-value is less than .05, that is, there is less than a 5% chance of getting that big of a difference in means of two samples if, in fact, the two samples come from the same source (the same population). You choose the one-tail or two-tail p-value based on the hypothesis that you're testing.
@@DavidDunaetz I have both alternate and null hypothesis. I'm testing for the differences between finger ridge density in male and female. (this is where it gets complicated), I also want to compare the radial, ulnar and proximal ridge density areas of the fingers,between male and female. Pleaseeeee help me im in my last 3 months of uni
@@sq9779 Hi Shery. It sounds like you actually have 4 hypotheses (that is, 4 alternate hypotheses), all two-tails, that you want to test:
1. MaleFingerRD is different than FemaleFingerRD.
2. MaleRadialRD is different than FemaleRadialRD.
3. MaleUlnarRD is different than FemaleUlnarRD.
4. MaleProximalRD is different than FemaleProximalRD
You need to do 4 different two-sample t-tests on the appropriate data. Be careful setting up your data on Excel. Everything needs to be grouped carefully.
There are also some more complicated things you can do to prevent "alpha inflation" (i.e., avoiding false-positives), but I would guess that this would be beyond the scope of this project.
If we assume that B > A as hypothesis at start.
Will we get the same results?
If yes , so which hypothesis is to be selected ??
Hi Sam Kab,
This is a good question. Note that we're hypothesizing, not assuming.
If our hypothesis is the mean in Division B is greater than the mean in Division A, as soon as we calculate the means for the two divisions, we can tell that the hypothesis is not supported (since the mean for Div A is greater than the mean for Div B, the opposite of what we hypothesized). We don't even need to do a t-test. We have absolutely no evidence to support the hypothesis that Div B > Div A.
@@DavidDunaetz what test to do then in order to see which division is bigger than the other??
@@samkab677 There's no need to do a test. You just look at the data and say that it obviously doesn't support the hypothesis. You only need do a t-test to test a one-tailed hypothesis if the data seems to support the data but you want to find out if the difference in means of the sample is greater than what you would expect by chance if the two means were equal in the population. It's for this reason you should do a two-tailed test rather than a one-tailed test unless you're relatively certain that you know which one will be higher.
When to perform for equal variance and when for un-equal variance.
+aruna kumar You need to have a good reason to use the un-equal variance version of the t-test (for example, if the standard deviation of one sample was 4 times the size of the standard deviation of the other sample). But if you use the un-equal variance version of the test, you lose a lot of power. In general you should avoid it if you can. However, if you want to be very conservative and are willing to pay the price to avoid Typel 1 (alpha) error, you can always use the un-equal variance version. As a rule of thumb, most people always assume equal variances.
OKK
how do I know if A is more stressed out than B ? looking from what ? thanks in advance
We have the data from a stress survey given to 8 people in Division A and the data from the same stress survey given to 8 people in Division B. The t-test allows us to use this data and make a conclusion whether the average stress level of the entire Division A is different the average stress level of the entire Division B. Stress is typically measured with instruments such as the "Perceived Stress Scale" or "Maslach Burnout Inventory." Much information on these scales can be found online.
David, thank you for you previous reply and let me ask one question. I am doing
t-test for the research. I formulated the hypothesis (like A greater
than B, one-tail) but means of t-test showed that B greater than A and
moreover the difference was not statistically significant (p>0,1).
What's the conclusion should I write ? Does it mean that the hypothesis
should be rejected? Also does it mean that the bigger T-value, the more solid the result?
Hi +an166ful,
In the situations you described, you made a directional (one tailed) hypothesis (A > B). However, your results came out indicating a trend in the opposite direction. So your conclusion should be that your hypothesis is not supported by this data. You need to retain the null hypothesis that there is no difference between A and B or even that B is greater than A. This means that your hypothesis still might be true, but that the data you collected provides absolutely no evidence for it being true.
Will it still works if you respondents for each variable is not the same for example variable a only has 18 respondents where data is gathered while variable b has 22
Yes, it's fine that the two groups are not equal.
@@DavidDunaetz thank you so much I was panicking because I thought if you have 20 scores for variable a then you must also have 20 for variable b
Sir, How to do we say the mean difference? (is it by substracting the mean of B-A)?
Hi Noraz. The mean difference would be the sum of all the differences divided by number pairs A and B that you have. The t-test compares the difference of the means of two different groups (Mean of A - Mean of B).
@@DavidDunaetz OK sir tqvm. I have this situation, where the result rmse is ok.lowest value of RMSE (Minimization). but the p-value is quite high. how can i interpret the result sir?
Welch Two Sample t-test
data: test_set$Close and mfopsoY
t = -0.4243, df = 274, p-value = 0.6717
alternative hypothesis: true difference in means is not equal to 0
95 percent confidence interval:
-0.002905947 0.001875425
sample estimates:
mean of x mean of y
1.110894 1.111409
Appreciate your advise sir.tq
sir how about if the t-value has a negative result is it still significant? to the df and p value?
The sign of the t-value doesn't matter. You use its absolute value in the calculation of its p-value. However, if you made a one-tailed test and the difference is not in the direction you predicted, then the p-value doesn't matter, regardless of how small it is. In a two-tailed test, the sign doesn't matter, but you should always report which mean was higher.
@@DavidDunaetz thankyou sir😇
Hi David, I love your video! Can you please explain to me why my p-value is this .. P(T
Hi Mama.Cindas. The E-05 in the p value means "10 to the -5th power." So your p value is .0000596, which is very low. You should report this as p < .001. The difference between the sample means is significant.
@@DavidDunaetz thank you!!!😎
Thank you :)
Can someone tell me why is one-tail but not two-tail?
It's because of our hypothesis: Division A is more stressed than Division B. This is a directional (or one-tailed) hypothesis because we're predicting which group will have a higher average score than the other. If we had hypothesized "The stress of Division A will be different than the stress of Division B," then that would have been a non-directional hypothesis and we would have used a two-tailed test.
Does this also work, if both samples have a different count?
Yes, unequal sample sizes work fine.
@@DavidDunaetz thank you!😊
damn it, i got excel 2018 and that option ain´t there :´v
It should work on Excel 2018 for Mac. However, you need to install the free statistics ToolPak. Here's a short video on how to do it: ruclips.net/video/1R_aJ_Fli2w/видео.html
Thank you
Thank you