07-21-2021
Minhtrang
Obsidian | Level 7
Member since
07-28-2015
- 39 Posts
- 20 Likes Given
- 0 Solutions
- 0 Likes Received
-
Latest posts by Minhtrang
Subject Views Posted 747 07-19-2021 05:15 AM 1268 09-23-2020 11:08 PM 1271 09-23-2020 11:01 PM 1366 09-22-2020 11:49 PM 1411 09-22-2020 07:25 PM 5853 05-23-2018 08:30 AM 5867 05-23-2018 12:26 AM 5927 05-10-2018 01:16 AM 6011 05-08-2018 03:16 AM 1702 11-21-2017 03:09 AM -
Activity Feed for Minhtrang
- Posted Calculate Sample size for non-inferiority clinical trial (with given Hazard ratio margin) on Statistical Procedures. 07-19-2021 05:15 AM
- Liked Re: Correlation coefficient boundaries/ Correlation matrix _ Generalized Equation Estimation for Ksharp. 09-27-2020 05:29 PM
- Posted Re: Correlation coefficient boundaries/ Correlation matrix _ Generalized Equation Estimation on Statistical Procedures. 09-23-2020 11:08 PM
- Liked Re: Correlation coefficient boundaries/ Correlation matrix _ Generalized Equation Estimation for MichaelL_SAS. 09-23-2020 11:02 PM
- Posted Re: Correlation coefficient boundaries/ Correlation matrix _ Generalized Equation Estimation on Statistical Procedures. 09-23-2020 11:01 PM
- Posted Re: Correlation coefficient boundaries/ Correlation matrix _ Generalized Equation Estimation on Statistical Procedures. 09-22-2020 11:49 PM
- Posted Correlation coefficient boundaries/ Correlation matrix _ Generalized Equation Estimation on Statistical Procedures. 09-22-2020 07:25 PM
- Liked Re: How to compare Odds Ratios from models with different outcomes, same predictors for JacobSimonsen. 05-23-2018 10:28 AM
- Posted Re: How to compare Odds Ratios from models with different outcomes, same predictors on Statistical Procedures. 05-23-2018 08:30 AM
- Liked Re: How to compare Odds Ratios from models with different outcomes, same predictors for JacobSimonsen. 05-23-2018 08:30 AM
- Posted Re: How to compare Odds Ratios from models with different outcomes, same predictors on Statistical Procedures. 05-23-2018 12:26 AM
- Posted Re: How to compare Odds Ratios from models with different outcomes, same predictors on Statistical Procedures. 05-10-2018 01:16 AM
- Posted How to compare Odds Ratios from models with different outcomes, same predictors on Statistical Procedures. 05-08-2018 03:16 AM
- Posted Why opposing results occured with categorical and continuous predictor ? on SAS Health and Life Sciences. 11-21-2017 03:09 AM
- Liked Re: How to set cut-off P-value for interaction term in linear regression model? for Reeza. 07-04-2017 10:22 PM
- Liked Re: PROC GLIMMIX: How to choose the distribution for response variable with limited range of value? for Ksharp. 06-27-2017 10:17 PM
- Liked Re: PROC GLIMMIX: How to choose the distribution for response variable with limited range of value? for sld. 06-27-2017 10:16 PM
- Posted Re: PROC GLIMMIX: How to choose the distribution for response variable with limited range of value? on Statistical Procedures. 06-27-2017 08:07 PM
- Posted Re: PROC GLIMMIX: How to choose the distribution for response variable with limited range of value? on Statistical Procedures. 06-27-2017 09:29 AM
- Posted Re: PROC GLIMMIX: How to choose the distribution for response variable with limited range of value? on Statistical Procedures. 06-27-2017 09:27 AM
-
Posts I Liked
Subject Likes Author Latest Post 1 1 1 4 1
07-19-2021
05:15 AM
Hi,
Could anyone show me how to calculate sample size for a non-inferiority clinical trial with given information as following?
"The primary hypothesis aims to show non-inferiority on 3P-MACE for empagliflozin versus placebo based on a non-inferiority margin of < 1.3 (upper limit of the adjusted 95% confidence interval (CI)) for the hazard ratio. The upper limit of the adjusted 95% CI for the HR of <1.3 was based on FDA guidance for CV trials evaluating new anti-hyperglycemic therapies for T2DM [9]. Patients who receive either 10 mg or 25 mg of empagliflozin will be pooled into a common treatment group for the purposes of the primary analysis. A 4-step hierarchical testing strategy will be followed: 1) non-inferiority test of the primary outcome (3P-MACE), 2) non-inferiority test of the key secondary outcome (4P-MACE), 3) superiority test of the primary outcome (3P-MACE) and 4) superiority test of the key secondary outcome (4P-MACE). A minimum of 691 confirmed primary outcome events are required to provide 90% power with a one-sided α level of 0.025, assuming equal risk between the placebo and empagliflozin groups. With a minimum of 691 events, the trial will also have at least 80% power to detect a hazard ratio of 0.785 (corresponding to a 21.5% risk reduction in CV outcome events) for the primary outcome."
So actually how to get the number of 691 as stated in the article?
Thanks a lot for your kinda help.
Trang
... View more
09-23-2020
11:08 PM
Thank you very much for your great help!
I'm still not clear about the so-called "correlation coefficient boundaries".
I did not hear about or see this term in books or documents on the topic of repeated measure analysis.
Is it similar to correlation matrix?
I was asked by a reviewer. I'm not sure if he asks the right question.
... View more
05-23-2018
09:02 AM
1 Like
Yes, you can include the value of one response as predictor for the other response. Though, it is my gut feeling that something will go wrong if you do that both ways, because the predictor then will depend on the outcome.
If you want to use AAC as a predictor for CAC, and in same model you also want to test if age has same effect on the two outcomes, you can add one more variable, that are constant when the outcome takes the value AAC, but when the response is CAC it takes its value should depend on AAC. As below (which is an extension of the program I gave you before) the "type_" variable will estimate the log(oddsratio) of the AAC on CAC.
data mydata2;
set mydata;
type=1; type_=1; respons=AAC; output;
type=2; type_=2*10+AAC; respons=CAC; output;
run;
*now test interaction (the type 3 test in this model): ;
proc logistic data=mydata2;
class type type_ /param=glm;
model respons(event="1")=type type_ age type*age;
run;
... View more
11-21-2017
08:33 AM
@Minhtrang wrote:
Hi all,
I am running a Cox model with outcome as mortality, and predictor as Magnesium (Mg).
When I treat Mg as quintiles, p-value for this predictor is significant. However, when Mg was entered into the model as continuous, p-value is >0.05.
I can not find an explanation for this difference. What are next steps to be considered?
I would love to hear from your experience about this problem.
Thank you.
There's no reason to think that a model based upon quintiles (in which you are throwing away data) will produce the same result as a model based upon the continuous variable (where you are not throwing away data). In fact, if you have the continuous variable values, I can't really think of a reason why you'd even want to use quintiles in place of the continuous data ... I doubt you could justify this to a reviewer or professor.
... View more
06-27-2017
08:07 PM
Hi sld, Thank you so much for your reference with one-zero inflated beta regression! I know something about beta regression, but never thought of one- zero inflated one. This is exactly I want. The illustration of SAS used similar type of response variable (a score from 0 to 100) like mine. They also divided it by 100 and gave detailed guidance of the Macro for this analysis. Best,
... View more
06-25-2017
01:24 PM
1 Like
That method of analysis is also known as 'p-value' hacking to some degree these days and you should be very careful with this, especially if you're trying to publish your results.
https://en.wikipedia.org/wiki/Data_dredging
... View more
05-28-2017
09:44 PM
Dear mkeintz,
You understood my problem so well.
Categorical variable is my desired outcome.
Thank you so much for your explanation in depth as well as the given optimal solution.
Best,
Trang
... View more
05-02-2016
08:54 AM
1 Like
Look at the documentation for PROC PANEL and PROC MODEL for possible examples.
Steve Denham
... View more
04-19-2016
06:40 PM
Dear Astouding,
Thanks a lot for your help.
It's so simple!
Best,
Trang
... View more
04-15-2016
09:31 AM
1 Like
Trang, I'm pretty rusty on time-dependent covariates, so I can just refer you to, say, Paul Allison's BBU on survival analysis. I can comment on treating sodium as continous versus quantiles. If a predictor is reasonalby linear in the hazard space, it will be a better predictor than quantiles for a couple of reasons. For one, with more granularity in the measure, you can get better estimates. The second is that you are not really looking at quantiles as a test; you are looking at a 4-level categorial data and that dilutes the effect. I'm not sure how you can test for monotonicity. You could test for linear or quadratic effects, but that takes additional assumptions on the quantiles that may not be supported by the data.
... View more
04-05-2016
05:38 AM
Dear Xia,
I'm really surprised by your code! It's so short and it creates the same results which I expected.
I've more experience now.
Thank you very much.
Best,
... View more