Good video sir, I have a question, if P value lack of fit less than 0.05 but r square more than 90, So I can use this model to predict or not
@instituteofqualityandrelia7902Күн бұрын
Good question! If p-value of LOF is low, the model is not fitting well. You can try transformations such as box cox. If you still get a similar p-value, you will need to decide whether some more factors need to be added, or change levels or use the model with caution.
@jeejin2686Күн бұрын
@@instituteofqualityandrelia7902 thank you very much sir
@BharathReddy-p7j8 күн бұрын
Dear Sir, I have one doubt... Actually Cpk is calculated by using the standard deviation (within) but you have shown in the video calculating by using standard deviation (overall). Could you please clarify.. Thanks in advance
@instituteofqualityandrelia79026 күн бұрын
Hello Bharat, you are right. This video is intended to explain the basic concepts. The within and overall sd is applicable when we use control charts. Maybe in one of the videos, I will talk about these. Thank you for your keen interest.
@BharathReddy-p7jКүн бұрын
Sir, thanks for the reply, it will be grateful if you provide the video, it will be really helpful for the career growth. I will be waiting for the video.
@joseantoniovargasbazan505811 күн бұрын
Thanks for the excellent overview of the topic.
@instituteofqualityandrelia79029 күн бұрын
Welcome! Appreciate your feedback!
@madhuriswami937613 күн бұрын
Thanks sir im using this DOE I'm completed my research in M.pharm thank you sir
@instituteofqualityandrelia79029 күн бұрын
Most welcome! All the best!
@coobi378413 күн бұрын
How can I get Minitab?
@instituteofqualityandrelia79029 күн бұрын
You can download the 30-day trial version from www minitab.com
@haqiasekarmaharani255014 күн бұрын
Sir, is the method match to analyze the risk of production process of food industry?
@instituteofqualityandrelia79029 күн бұрын
You can use it for any system.
@rahulprajapati463815 күн бұрын
Hello sir, kind request to upload lectures about MS Power BI or Tableau 🙏🙏🙏
@instituteofqualityandrelia79029 күн бұрын
Thank you. However, that is not my expertise. Apologize.
@sugambhardwaj21321 күн бұрын
Wow. Such good information with easy examples. Great Job Sir
@uhemant121 күн бұрын
Thank you!🙏
@instituteofqualityandrelia790216 күн бұрын
So nice of you
@leezhisen170426 күн бұрын
Hi sir, regarding the application exercise question, what would be the MTBF since it has 0 failure, which T/F would actually give infinity?
@instituteofqualityandrelia79029 күн бұрын
You can estimate the lower bound of MTBF in case of zero failure in case of time terminated test. See formula and tempate. Download template from our website www.world-class-quality.com
@leezhisen17047 күн бұрын
@@instituteofqualityandrelia7902 I see, so for zero failure we can only estimate the lower bound value. Thanks!
@BNT0527 күн бұрын
Thank you Sir for sharing your knowledge and experience for free. Be blessed. 👋 Are your datafiles have the solutions in place?
@instituteofqualityandrelia79029 күн бұрын
Please clarify your question. I didn't understand it. The data files do not have solutions.
@BNT059 күн бұрын
@instituteofqualityandrelia7902 Thanks for coming back to me. I meant to say that if you have an example(s) of each subject on a dataset. For example, you can have a few datasets on Run Chart, but at least you have shown your audience how to go about...in one of them
@rambrandtvanrijnАй бұрын
In this example, we are sure about all the raw data are operation time of failure, right? Another question: Isn't a smaller Anderson-Darling value indicative of a better goodness-of-fit? Why is the Weibull distribution considered the most appropriate when the exponential distribution has the smallest value?
@instituteofqualityandrelia790228 күн бұрын
Hello friend, that is a very good question! Yes, the lower value of AD shows better fit. Choosing Weibull is still safe as Exponential is only a special case of Weibull with a shape parameter of 1.
@donnymac575Ай бұрын
Can minitab plot multiple accelerating factors at the same time, like temperature and humidity?
@uhemant1Ай бұрын
Thank you for asking an excellent question! Yes, Minitab can analyse data of an accelerated life test with two variables.
@donnymac575Ай бұрын
@@uhemant1 thank you for the response 😊
@Qpac524Ай бұрын
Greetings Professor! Thank you for your highly invaluable videos, I found them to be extremely useful. I just have one question: are you familiar with the software 'Cornerstone' for DoE? Can you recommend any links where I can find tutorials for Cornerstone?
@instituteofqualityandrelia790228 күн бұрын
Thank you! I am glad to know you are finding the videos useful! I am not aware of the software mentioned by you. Apologize.
@seshansesha7645Ай бұрын
Thank you
@instituteofqualityandrelia7902Ай бұрын
My pleasure!
@hamidbouaricha9714Ай бұрын
How to represent a standby pump in RBD
@instituteofqualityandrelia7902Ай бұрын
A standby pump would be in parallel with the primary pump with a switch. The reliability of the switch also needs to be considered.
@harryzhang4239Ай бұрын
Hi Sir, what if we're studying a system, for example, computer? There're so many components in it. Do we need separate the data by diff. failure modes or just combine them together? Thanks!
@instituteofqualityandrelia7902Ай бұрын
You need to separate the failure modes for taking improvement actions. For growth calculations, all failure modes should be considered.
@harryzhang4239Ай бұрын
@@instituteofqualityandrelia7902 Thank you so much for the quick answer. I'm studying the warranty. So I need consider all failure modes. Rght?
@kamyarghods2429Ай бұрын
good initial insight about the accelerating methods
I am not sure why Minitab does this often. However, Exponential is only a special case of Weibull Distribution with a shape parameter of 1. So if you select Weibull, Exponential will get included, if it fits.
@ranjithkumar-qb9xyАй бұрын
thank you. video was informative
@instituteofqualityandrelia7902Ай бұрын
Glad it was helpful!
@FernandoFerrariFernandesАй бұрын
Why in some cases there is a time in the column even when genset did not fail?
@instituteofqualityandrelia7902Ай бұрын
Hello Fernando, Thanks for your interest. There are two gensets. So the time is time column shows data when any of the genset fails. Hope this is clear.
@FernandoFerrariFernandesАй бұрын
Yes I got it. When performing this analysis using Minitab the results are different. Also, how this Eta and Beta relates to shape and scale parameters informed when using Minitab?
@thinuraramsithАй бұрын
very good explanation
@instituteofqualityandrelia7902Ай бұрын
Glad you think so! Keep watching!🎉
@vatsalparikh3574Ай бұрын
Awesome Concise
@instituteofqualityandrelia7902Ай бұрын
Thank you!🙏
@karthikeyanvenkatesan1009Ай бұрын
Hello sir, Thank you for this wonderful video. Is it possible to share the excel sheet used in the video ? it would be of great help. Thanks again for the explanation. it is very clear.
@instituteofqualityandrelia7902Ай бұрын
Appreciate your feedback! I suggest that you create the xl worksheet for better learning and understanding!
@GioPalencia2 ай бұрын
Very clear and direct to the point. Thank you so much!!!
@instituteofqualityandrelia7902Ай бұрын
Thank you!🙏
@STIBLOPP20232 ай бұрын
Sir...Thanks a lot for the DFMEA video.....Very well explained
@instituteofqualityandrelia79022 ай бұрын
Most welcome!
@shanmugavelayutham13942 ай бұрын
hi, @11:02 63% failure u mentioned but actually it is 66.9% failure right??
@instituteofqualityandrelia79022 ай бұрын
No. 63% is correct. For Weibull distribution, by time equal to scale parameter, 63.2% parts are expected to fail. You may like to watch my video on Weibull distribution. Here is the link: kzfaq.info/get/bejne/mt6nn7yLkp7Dd4E.html
@eamonnquinn95852 ай бұрын
good and clear tutorial on this topic - Thank you
@instituteofqualityandrelia79022 ай бұрын
Glad to hear that it was helpful! Appreciate your feedback!
@kuldeepjayaswal99332 ай бұрын
Name of software
@instituteofqualityandrelia79022 ай бұрын
I have used Minitab software. There are other software such as Weibull++.
@sudhansugrahacharya70942 ай бұрын
<5 failure or >=6 failures out of how many samples? what should be the sample size sir??
@instituteofqualityandrelia79022 ай бұрын
It is basically for test time in multiples of lower test mtbf.
@azizvohra8712 ай бұрын
How the simulated values are derived?
@instituteofqualityandrelia79022 ай бұрын
These are calculated based on probabilities as per assumed distribution.
@harryzhang42392 ай бұрын
Hi Sir, why is the Hazard rate 1/i? just because of one failure among i?
@instituteofqualityandrelia79022 ай бұрын
Thank you for your interest. 1/i is delta hazard where i is the reverse rank. The reverse rank represents items at risk just prior to t. Thus proportion of items failing out of SURVIVING population during the interval is by definition delta of hazard rate. You may like to watch my video on hazard rate. Here is the link: kzfaq.info/get/bejne/ZsdddalhmJyomWg.html
@Doctor-Lean2 ай бұрын
Thank you so much for sharing the VDO so, I request training apply concern with heuristic model if possible to sharing concept.
@instituteofqualityandrelia79022 ай бұрын
Thank you for your suggestion. Kindly clarify your expectations.
@sudhansugrahacharya70942 ай бұрын
how to get the effectiveness factors of the corrective action??
@instituteofqualityandrelia79022 ай бұрын
It is explained in the video. You can also refer to the paper referenced.
@dhinakaranm48053 ай бұрын
The video is really useful
@instituteofqualityandrelia79022 ай бұрын
Glad you think so!
@sumitgharge12983 ай бұрын
Hello sir ... Can I run the botched runs I minitab?? And please tell if it is possible then they give very accurate results to consider for further analysis in DOE to find significant factors??
@instituteofqualityandrelia79022 ай бұрын
Thx. But I haven't understood your question.
@shubhampawar52943 ай бұрын
Great video
@instituteofqualityandrelia79022 ай бұрын
Glad you enjoyed it
@AhmadAli-rm3pi3 ай бұрын
very nice lecture i solute you thank you sir
@instituteofqualityandrelia79022 ай бұрын
So nice of you
@MEKalp3 ай бұрын
Great and clear explanation, thanks for sharing 😊
@instituteofqualityandrelia79022 ай бұрын
You’re welcome 😊
@sumitgharge12983 ай бұрын
Hello sir can you please tell me how we can find the values of shape parameter and scale parameter??
@instituteofqualityandrelia79023 ай бұрын
Thank you! Please watch my video on how to estimate beta and eta parameters using probability plotting. Here is the link: kzfaq.info/get/bejne/mtmlf7mEl9-1ZIk.htmlsi=i7saq3ej5S-wkYKk
@sumitgharge12983 ай бұрын
@@instituteofqualityandrelia7902 Thank you very much sir..
@sumitgharge12983 ай бұрын
Hello sir can you please tell me how we can find the values of shape parameter and scale parameter??
@instituteofqualityandrelia79023 ай бұрын
Watch my other video: kzfaq.info/get/bejne/mtmlf7mEl9-1ZIk.htmlsi=i7saq3ej5S-wkYKk
@sumitgharge12983 ай бұрын
@@instituteofqualityandrelia7902 Sir can you tell me how we can decide which plots are good and which one is to choose or very helpful for further analysis after conducting the ALT How to decide plots according to what??
@memsuniverse3 ай бұрын
great example and effective way to explain DEO , many thanks for the explanation
@instituteofqualityandrelia79023 ай бұрын
I am glad you liked it!🎉🙏
@MohammadBintangRizqiPratama3 ай бұрын
Thanks for the explanation, but still i have question. In a real case e.g determining the components reliability of a machine, what is the ß value? Because sometimes, when it broke, u just need to repair the components and it will run again (basically we use MTBF on this situation), and sometimes when it broke you need to change the components so it would start again (non repairable units, and this we use MTTF). What is the ß value then?
@instituteofqualityandrelia79022 ай бұрын
Beta value is estimated from the data of past failures.
@sumitgharge12983 ай бұрын
Hii sir, why i get the zero error, zero SE coefficient, zero P and T values in minitab when i run the two level two factor design for design of experiments can you please tell this..
@instituteofqualityandrelia79023 ай бұрын
This is possible when you do not have any degrees of freedom for the error term.
@sumitgharge12983 ай бұрын
@@instituteofqualityandrelia7902 because of this in minitab I didn't get the values of p test , f test and SE Coefficient So how I can resolve this??
@sumitgharge12983 ай бұрын
@@instituteofqualityandrelia7902 basically I'm facing this problem when I use the minitab software and I have created 2 level 2 factor full factorial design in this, when I checked for the significance then I didn't get any P values ...
@instituteofqualityandrelia79023 ай бұрын
Yes. This is called a saturated design. If you replicate the design, your problem will be solved as then you will get enough degrees of freedom for error. With two replicates, there will be 8 runs. Total degrees of freedom will be 7 and there will now be 3 degrees of freedom for error. Hope this helps.
thank you for sharing sir. could you share LDA of left cencored data using minitab too please ?
@instituteofqualityandrelia79023 ай бұрын
Thank you! The left censored data can be analysed using similar commands in arbitratily censored data.
@shanmugavelayutham13943 ай бұрын
Sir, I have 1 doubt, at 5.45 you said for alpha you mentioned shape parameter. but actually Beta is called as share parameter is it? but in excel we have to consider alpha as a shape parameter. is right?
@instituteofqualityandrelia79023 ай бұрын
This is only because in XL, the notation is different. In most literature, the shape parameter is denoted as beta. In XL, the shape parameter is denoted as alpha.
@shanmugavelayutham13943 ай бұрын
Good morning sir, How you saying 63% product will fail. where it is mentioned? can you pls explain..
@instituteofqualityandrelia79023 ай бұрын
Hello there! This is a property of Weibull Distribution. You may like to watch my videos on Weibull Distribution. Links shown below: Weibull Distribution Part-1 kzfaq.info/get/bejne/mt6nn7yLkp7Dd4E.html Weibull Distribution Part-2 kzfaq.info/get/bejne/jch3aL1ozti5pWg.html
@brianyeh26954 ай бұрын
Thank you very much. Clearest of all videos in this topic
@instituteofqualityandrelia79023 ай бұрын
You are welcome! I am really glad to know!
@4321blastof4 ай бұрын
Shouldn't Cpk be calculated using sigma estimator instead of standard deviation?
@instituteofqualityandrelia79024 ай бұрын
Standard Deviation can be for sample or population. In this particular case, standard deviation is calculated based on 250 data points and therefore can be practically considered as population standard deviation, If control charts are use and process is stable, the standard deviation can be calculated using the control chart, but then it is considered as 'within' subgroup variation and represents the random portion of the variation.