На главнуюОбразованиеПохожее видеоЕще от: Statistics Learning Centre

Choosing which statistical test to use - statistics help

Оценок: 3614 | Просмотров: 615264
Seven different statistical tests and a process by which you can decide which to use. The tests are: Test for a mean, test for a proportion, difference of proportions, difference of two means - independent samples, difference of two means - paired, chi-squared test for independence and regression. This video draws together videos about Helen, her brother, Luke and the choconutties.
Категория: Образование
Html code for embedding videos on your blog
Текстовые комментарии (282)
Aditi Sarkar (2 дня назад)
The video is quite helpful, but is too fast and at times incomprehensible..
Urvi Kikani (4 дня назад)
If only two samples , can we use ANOVA??
Statistics Learning Centre (3 дня назад)
Yes ANOVA for two groups will give the same p-value as difference of two means t test.
Zin Ya Khaing (15 дней назад)
Thank you so much from Myanmar You save my Midterm !!!
Malek Azaz (16 дней назад)
Perfect Video for New Researcher
Rubi Bojorquez (23 дня назад)
Well explained and fun. Thanks
Haleema Begum (26 дней назад)
What about testing variances ??
Statistics Learning Centre (26 дней назад)
Thanks for asking. Testing variances is not a common statistical test. The ones listed are the seven people are most likely to use. Can you give me a scenario for when someone would want to test a variance?
MamtaBk Bk (1 месяц назад)
Good explanation.v useful. Thanks
Zeng Yu (1 месяц назад)
very helpful explanation, thx for sharing
orhan tokur (2 месяца назад)
I don't understand the "example 6". Why it is "regression analysis" instead of "difference of two means (paired) ? Isn't it correct to use second one?
orhan tokur (1 месяц назад)
Thank you for your kind answer, i believe i got it !
Statistics Learning Centre (1 месяц назад)
The two measures are the temperature and the sales of choconutties. It does not make any sense to compare the mean temperature in degrees and the mean sales in packets of choconutties over the days. We are looking at a relationship, so we use regression. Please explain your reasoning if you are still confused.
bumble2able (2 месяца назад)
Trying to relate this to sociolinguistics 😱😂☺️ wish me luck for my exam on Monday 😱😱😱 Kiora by the way 🤙🏻
Ligaw na Kuting (2 месяца назад)
I'm studying for my comprehensive exam..and found this very useful..thanks. I don't mind the accent at all...
BatistaR0X (2 месяца назад)
Gorgeous accent XD Aussie or kiwi?
BatistaR0X (2 месяца назад)
My apologies if I sounded rude but the content of the video was really helpful! Also, New Zealander's accent is one of my favourite kind of accent! :D Flight of the Conchords ze best!
Statistics Learning Centre (2 месяца назад)
You are very kind. I am a New Zealander - my accent is fairly close to RP, which means it is not much different from Aussie RP. Sometimes people think I am South African.
suke (2 месяца назад)
Why is the answer to Q#3 "paired" and not "independent" .... I got that wrong :( Otherwise u saved my statistical life .. excellent vid
suke (2 месяца назад)
Ohhhh ok I see the logic behind the decision. "Paired" makes perfect sense now. Thanks for the prompt response :)
Statistics Learning Centre (2 месяца назад)
You could do it as independent samples, but you would be wasting information.Because for each person we have two pieces of information - the time taken to eat the choconutty and the time taken to eat the nuttabar we can control better for variation between people. There is only one sample - the 36 people.
Deniz Gunes (2 месяца назад)
what should i use if im trying to identify if gentrification causes crime? i have a gentrified and a non gentrified area and have crime statistics for both area from 2015-18 URGENT thanks!
Statistics Learning Centre (2 месяца назад)
You cannot tell if gentrification causes crime - you can only tell if there is a correlation between gentrification and crime. See the video Important statistical concepts, that explains about causation and relationship. https://youtu.be/FG7xnWmZlPE It your have just two areas and two time series, you are probably best to use a time series analysis. We have videos about time series in our statistics course.
Rishiik srivastava (2 месяца назад)
great video
Sugar Hits (3 месяца назад)
I've not finished the video yet, but it's been really helpful so far! Breaking it down into those questions has helped me figure out what I'm looking for.
Statistics Learning Centre (3 месяца назад)
So glad to hear it! Most text books etc use a flow diagram method, but I made up this way of displaying it as it shows the relationships between the methods as well.
artikuno2 (3 месяца назад)
Thanks for the help, but the way you implemented the insulting comments such as "Pause the video if you have any kind of self esteem" end up being, to some extent, directed towards those who actually paused the video and thus had the time to read them...
Statistics Learning Centre (3 месяца назад)
Interesting. It is a rather complicated form of humour. Pausing is good! Some people find it really funny.
Care Air (3 месяца назад)
Isn’t the test ultimately dependent on the underlying characteristic of the r.v.?
Statistics Learning Centre (3 месяца назад)
And the purpose of the investigation.
Rob Huntington (3 месяца назад)
Hi there- is there a playlist that contains videos detailing all of the different tests. I've seen it twice now and don't remember seeing links embedded in the video after describing each test. Maybe I am missing something? But I'd like to learn more in-depth about each type of test
Statistics Learning Centre (3 месяца назад)
Hi again. I just made a playlist, Choosing the test. Sadly we only have test for a mean (which is in "Understanding the p-value", difference of two means, independent samples, and regression. I'm hoping to get some time to make more one day.
Statistics Learning Centre (3 месяца назад)
Hi Rob We meant to have videos for all the tests, but ran out of money. I will put links on the ones we do have. We are looking for sponsors to help us make more videos, so if you know anyone...
dr.sadaf alam (4 месяца назад)
i think this channel is great for biostatistics,,,,hence i have recommended ur videos to medical students in my medical lecture review for medical students...as i think its simple and had great quality !!https://www.youtube.com/watch?v=OoFknuzmcsw&t=12s
XRC (4 месяца назад)
Very helpful video, thank you!
Sylvia v (5 месяцев назад)
Could you explain in spanish, please? Say yes! thank you
Statistics Learning Centre (5 месяцев назад)
Sadly I am not able to speak spanish.
Martin Federico (5 месяцев назад)
excellent series, thank you very much, this is priceless.Just a question though, what are pickets? just kidding
Statistics Learning Centre (5 месяцев назад)
Yeah yeah. I know you're jist kudding. People from outside NZ have trouble discerning our highly evolved short vowel sounds. We have a heap more videos too.
roger roger (6 месяцев назад)
I will never get this bullshit😓
Statistics Learning Centre (6 месяцев назад)
I think the problem lies with the person teaching you. Statistics does not need to be difficult, but many teachers make it so. Take a look at my blog - you might find some help there. https://learnandteachstatistics.wordpress.com/2013/09/09/study-stats-1/
roger roger (6 месяцев назад)
Statistics Learning Centre and i have to study it even when i have no interest in it for an exam😓
roger roger (6 месяцев назад)
Statistics Learning Centre its not u..its me..its too complicated for me
Statistics Learning Centre (6 месяцев назад)
I'm sorry to hear that. Tell me more what the problem is.
abiyot lema (7 месяцев назад)
I found it really help full, I am attending my MPH but can really Understand my instructor in the class but after getting this video wow, I understand it thank you so much.
ulysse-pacome koudou (8 месяцев назад)
Very constructive video, it's a must watch
Statistics Learning Centre (8 месяцев назад)
Thank you. It took a lot of thinking to come up with that structure, as all the other textbooks used tree and decision frameworks. I like that it teaches about structure and relationships as well as being a process.
Gaudeamus (8 месяцев назад)
ACCENT!!! :'(
hamza 123 (8 месяцев назад)
Am I the only one that got the deathnote reference with that picture of melo and chocolates at 4:34 lolllll
Statistics Learning Centre (8 месяцев назад)
Hmmm
kalatog pinggan (9 месяцев назад)
Thank you very much for this video. I really need this for the upcoming licensure examination for Psychometricians this 29 and 30 and I could say that I’m having issues with Statistical tools :)
Adrian Gomez (9 месяцев назад)
is that brienne from game of thrones?
Nayre (10 месяцев назад)
Good day, I would just like to ask what type of Statistical test would be most appropriate for comparing 3 different independent variables. Im doing a MFC research, comparing the voltage and amperage over time of the three microbes (independent V.) to determine which has the highest power generation among the three. Thank you
Statistics Learning Centre (10 месяцев назад)
Hi Nayre I'm afraid you would need to give me more info than this. MFC? If you have three groups - the three microbes, as the independent vble, and power generation is interval/ratio, then it looks as if you are looking at ANOVA.
Kimi Møller (10 месяцев назад)
Great and very helpful video. Thanks for sharing!
Catburglar (10 месяцев назад)
I am so happy I found this video - you have saved me! When teachers break things down so anyone can understand you are catering for everyone to learn. Thanks Dr Nic  :).
Statistics Learning Centre (10 месяцев назад)
That is great to hear.
DayGloBetty (11 месяцев назад)
This is a great video and super helpful, thank you, I've subscribed. I'm still confused about what test I need to use though, could you help me? I'll write the problem out in terms of Helen and the chocco nutties: Helen wants to know if the number of times someone has eaten a chocco nutty changes their opinion of chocco nutties. She has one group of 12 people and gives each person 22 chocco nutties. After each bar a person eats she asks them if they liked or disliked the bar, and wants to compare if there's a difference between the percentage of the group who enjoyed their first chocco nutty bar vs. their second, their third, their fourth and so on. I get that the liking or disliking of the bar is nominal, but does the fact that it's been changed to the percentage of people who said they liked it change that? Also, what kind of data would the number of chocco nutties the subjects have eaten thus far be catagorised as? I'm definitely going to watch your other videos to see if they can help me find the answer but if you, or someone lovely in the comments, knows what test I should do I would super appreciate that! xoxo
DayGloBetty (11 месяцев назад)
Hey, that's really helpful, thank you so much. I have got it plotted out as a graph already but it's good to know that they are both interval data - I'll do some searching around and see if I can figure out what sort of test I should do. Thanks again.
Statistics Learning Centre (11 месяцев назад)
I'm not sure of a test, but I think a graph would be a good start. The percentage that like the bar at each stage is interval data. The number of choconutties eaten (which is really also a stage) would also be interval data. However you only have one observation at each stage, so there are only 12 data points.
oompaloompa23 (11 месяцев назад)
Good but the choco nutties is annoying as.
oompaloompa23 (11 месяцев назад)
As in from the original Willy Wonka film?! Oh dear!I think you could be the only person ever to think that. #stick to the maths
Statistics Learning Centre (11 месяцев назад)
That's a bit ironic coming from an oompaloompa.
Don Burgundy (11 месяцев назад)
whats with the obsession with damn chocobutties
Aafi (11 месяцев назад)
I hope someone can help me with this. I cant understand what my lecturer had been teaching and I really need help. 30 women hv anemia in pregnancy & 15 of them hv history of malaria. 90 hv normal hb lvl pregnancy & 20 of them hv history of malaria. what is the research hypothesis and null hypothesis? suggest a statistical test for testing the null hypothesis. is this considered as two sample or one sample?
Statistics Learning Centre (11 месяцев назад)
You can use a chi-sq test to do a difference of two proportions, and it gives the same result.
Aafi (11 месяцев назад)
the answer given was chi square test, so i thought it was asking if anemia in pregnancy and malaria are independent.
Statistics Learning Centre (11 месяцев назад)
Two samples, difference of two proportions.
Helina Jean Dupa (1 год назад)
thank you so much!
Fi Ly (1 год назад)
If you have continuous grouped data, what tests can you use?
Helina Jean Dupa (1 год назад)
i find this video very interesting that's why im downloading it...thank you very much!!!
Helina Jean Dupa (1 год назад)
Okay. Thank you for the reminder.
Statistics Learning Centre (1 год назад)
Hi - I'm glad you find it interesting. However please do not download it, as this violates your agreement with YouTube.
Madjid Bati (1 год назад)
What statistics can be use if i want to measure relation between integrity and performance of local parliament members, thank you
Statistics Learning Centre (1 год назад)
You need to read up about developing indices. There is a whole area of work behind this. Or you can use each measure individually, but it depends on how they are measured. I suspect your measures are ordinal data. In some fields it is acceptable to combine ordinal data to create an index of, for instance, accountability. The task you are talking about is not a small one. Correlation measures the linear relationship between two measures. You use rank correlation if your measures do not behave in such a way that Pearson correlation is valid.
Madjid Bati (1 год назад)
thank you for your kind respond. For instance integrity has four elements, one of the element is accountability, and accountability has six indicators, namely: 1. Transparency 2. Access to information 3. Consistency 4. Social responsibility 5. Clear record keeping 6. Openness to stakeholders Based on these indicator, how can I develop indices? and why I would use the correlation - probably Spearman rank correlation rather than Pearson. thank you for your wise respond...
Statistics Learning Centre (1 год назад)
It depends on what your measures are. First you may need to develop indices to measure integrity and performance. This looks like a difficult project. If you already have measures, then you may be able to use correlation - probably Spearman rank correlation rather than Pearson.
Ballwiz 23 (1 год назад)
Equally as confused as before...
Ballwiz 23 (1 год назад)
It's ok.. You helped a lot of other people. I'm in the middle of a Stats 2 class and just looking for things to help me make since of all this
Statistics Learning Centre (1 год назад)
Sorry to hear it. This is meant to function as a way to pull all the techniques together. You still need to learn about each one individually.
Tetracarbon (Phillip Wong) (1 год назад)
I love love love your Venn diagram approach!!! Thank you so much. I have read quite a few econometric textbooks and they still don't make it anywhere quite as clear as this. Thank you!
Not a phony (1 год назад)
wtf accent is this... "peckits of chukanuties"
Statistics Learning Centre (1 год назад)
NZ
shamee noori (1 год назад)
Thank you so much I hope u do more videos
Surekha Adki (1 год назад)
Excellent Job. It really helped me a lot. Thank you for the most informative video.
Sheila Beaudoin (1 год назад)
Thank you very much! I wish I had seen your video during my class and could have shared it with my classmates. Brilliant.
Aaron Woody (1 год назад)
Thank you so much. This would have helped me not be so far behind in my introduction to Statistics course. I am going to pass this video to my former professor.
ammar waadallah (1 год назад)
Hi, i have five tables (time X temp.) each table has different time (the first one from 0 to 15 min, the second from one to 25 min the third one from 0 to 18 min and so on). Each table starts with the same temp. Value (25°C) and end at the same new temp value (100°C). My question is, how can I calculate the Standard deviations and how can get a real average (time vs. temp) data and graph.
Laurens Sipahelut (1 год назад)
What statistical methodology do groups like 'The Political Compass' and 'Vote Compass' use to weight questionnaire answers and determine where you fall in x-y space?
Ramesh Maddali (1 год назад)
Truly awesome vedio. If i have a teacher like you i am blessed. But still i feel now as i found you. Teaching is a great art. You have proven. I am curious to know about you.
Elizabeth Marrero (1 год назад)
Super! I drew it all out and it makes total sense. Thank you so much!
Statistics Learning Centre (1 год назад)
That is great to hear, Elizabeth. It took quite a bit of thinking to work out this format rather than the usual flow chart that textbooks use. I like that it shows commonalities.
navymcz (1 год назад)
Great summary :)
Amin Nabil (1 год назад)
Hi there, 1. My data is interval/ratio (growth rate) 2. I have 3 samples (3 different methods) 3. Comparing 3 statistics May i know which statistical test should i use Thank you.
Amin Nabil (1 год назад)
Statistics Learning Centre thank you so much.
Statistics Learning Centre (1 год назад)
From what you have told me it sounds like ANOVA. Good place to start anyway.
Irum S (1 год назад)
Hi! I would request insights from the group regarding my results that involves Andrew Hayes mediation (model 4) and moderation (model1). X predictor (marital disaffection), Y outcome (Facebook intrusion) and M as a mediator (commitment). I have found that path a (Effect of X on M) is significant, Path B (effect of M on Y is significant), and Path C (original effect of X on Y is significant). However, the 4th requirement of the Mediation that C' is also Significant (effect of X on Y, SHOULD have be reduced or eliminated when M is introduced ). Can I report it as partial mediation ? Also with the same variables I have found the moderating (interaction) effect of commitment at all three levels (low medium and high commitment levels). Should I use another model that takes into account the mediation and moderation of the same variable? or just individually report both models in the results ? Thank you for your time and advice.
Piu N (1 год назад)
Hi... thanks a million for making the basics so clear.. choosing a test also has got to do with which kind of data is our dependent variable. & the number of variables.. It would really very helpful if you could share info on that. for eg, I havent understood when would we use path analysis & when logistic regression.. it would be of immense help if you could suggest in similar lines
Sir Zorg (1 год назад)
Helen looks and acts like melo from death note.
Piu N (1 год назад)
This is the 2nd time I am watching this .. this is such a useful video... testing ourselves against the examples was an eye-opener... could you please also share when do we use path analysis vs regression.. thank you so very much...
Susan Haas (1 год назад)
This is not only EXTREMELY helpful but hilarious! So fun to watch!
Bupe Kabamba (1 год назад)
Hehehehe the notes she was leaving to make sure you pause the video are just hilarious.
KSA MSA (1 год назад)
What A great explanation!, May I got the ppt file?
Statistics Learning Centre (1 год назад)
I'm glad you like it. There is no ppt file - this was developed on Premier Pro.
Michael Cruz (1 год назад)
What statistical test to use when the researcher likes to know whether note taking has effect on students academic performance based on the quantity of their achievements (whether they became honor students etc.)? The basis for achievements are: How many times did they achieve High Honor, Honor, Principals Lister, Top Student in class.
Piu N (1 год назад)
if i go through the above video, i would say regression, cause interval/ ratio data, 1sample 2measures & we are trying to find a relationship. would love to have inputs from stats learning centre on this
Gayane Harutyunyan (1 год назад)
thanks for video ! I would like to know how many should be my sample (at least) for each test ?
Kiran Mehr (1 год назад)
THANK YOU, MY GOD you saved me! Love Helen and her attitude haha! Thank you again :).
Tauseef Omer (1 год назад)
lols i love this video :-P
Kezia Jiao (1 год назад)
very well explained =)
Thingolness (1 год назад)
I'm curious. Where is this accent from?
Thingolness (1 год назад)
Ah I guessed somewhere around Australia but wasn't sure. Your videos are most helpful! Thank you kindly.
Statistics Learning Centre (1 год назад)
Thingolness I am from New Zealand.
Harpreet Singh (1 год назад)
We used to learn through animations. Excellent summarized presentation. Helen bringing statistical queries as an example.
Kamal Karkonasasi (1 год назад)
Helen is always angry when she asks people to answer her questions. She should change her attitude otherwise she can not find the real answers from the respondents and therefore, the results are not valid.
Exzequel Lim (4 месяца назад)
HAHAHAHAHAHHAHAHA
XRC (4 месяца назад)
You wouldn't think she has an attidute if she was a man. Anything to bash a woman entrepreneur even if she's a cartoon. For a man, this behaviour would go un-noticed and, mostly, un-commented..
Kamal Karkonasasi (1 год назад)
Thanks a lot. very good explanation :)
Diệu Trần (1 год назад)
You save my life, save my time. Loads of kisses to you :* :* :*
SHANEDABIRDMAN2 (1 год назад)
Diệu Trần hhhh
qerxxx (1 год назад)
Hee, Khee, not Chee, not Ki
Statistics Learning Centre (1 год назад)
I guess mathematical Greek is different from modern Greek! Thanks for letting me know.
qerxxx (1 год назад)
Strange, it's pronounced Khee in Greek
Statistics Learning Centre (1 год назад)
Hi - thanks for your comment. If the letter really were chi, you would be correct. However it is a Greek letter, and looks a bit like an X and is pronounced kai. https://en.wikipedia.org/wiki/Chi_(letter)
addis11100 (1 год назад)
language
Mansooreh Jami (1 год назад)
great explanation.I was wondering why Helen is always angry :)
Statistics Learning Centre (1 год назад)
She has an attitude problem. My editor is like that.
Merav Asaf (1 год назад)
thank you - I sent it to my students with Hebrew subtitles
CALDEH (1 год назад)
I want some choconutties!!!!
Statistics Learning Centre (1 год назад)
Me too.
Puneet M (2 года назад)
Your accent is totally non comprehensible. pickets? choco latte? tist?
whoeverwhateverany1 (5 месяцев назад)
I beg to differ. it is comprehensible, it's just probably an accent you are not used to. oh and it's choco nutties by the way. There are many different accents so it wouldn't harm to learn to get used to some new one once in a while. Wouldn't it be boring if everyone spoke in the exact same way?
Beauty Solutions (6 месяцев назад)
New Zealand accent.
Veggiepants! (7 месяцев назад)
^ spoken like a true aussie
vladimirhovno (2 года назад)
Great, simple and funny.
doczak69 (2 года назад)
excellent video ..thank you would you mind putting the word format also for us to read in description box.
KSA MSA (1 год назад)
please Helen
ronald laporte (2 года назад)
Excellent presentation on Youtube we would like to link to this. Also It would be wonderful if you could tell me about other youtube presentation you have on line, and other really good youtube presentation you know.. I am professor emeritus at the University of pittsburgh and former director of a WHO Collaborating Centre. I am writing you as I am collaborating with the Library of Alexandria in Egypt to build research capacity in Arabic and African countries to attack the deadly problem of "stataphobia" (my word). This is the fear of statistics and not having expert advice. Africa only publishes 3% of the world's literature, a primary reason for this the lack of statistical skills (stataphobia). We have created the research methods library of alexandria to boost research capacity. This is the largest virtual research methods library. Also we are collecting statistics books from 100 of the world's leading statistics experts. I am writing you for a simple reason. When I taught statistics there always was ~15% of the students who just did not get it. I thought it would be wonderful to have you come in to teach these kids from your perspective, or a professor from our statistics program. This obviously is not possible, but with youtube it is. I am looking to find the best lectures on the web so that if a student cannot understand "histogram", they can learn from you. I am writing to people have the best lectures on the web to link with them, and to get their advice about other grand lectures like yours to include. http://ssc.bibalex.org/helpdesk/introduction.jsf THank you very much for an outstanding lecture, and we hope to collaborate with you to improve research productivity in Arabic and African countries. Please write to me at ronaldlaporte@gmail.com Sincerely Ronald E. LaPorte, Ph.D. Professor Emeritus Ismail Serageldin, Ph.D. Director of the Library of alexandria
Miirrinda (2 года назад)
very helpful, thank you!
SonkleyFiz (2 года назад)
you accent is horrible, it was difficult to understand what the hell you were even talking about.
Statistics Learning Centre (2 года назад)
+SonkleyFiz That is why there are subtitles for people who have problem with the way other cultures speak.
Sai Yan (2 года назад)
my bio stat teacher just read thro the power point in mono tone voice and didn't give introduction on any new hypothesis test we learned. i was struggling when reading text book (i am not good at learning from reading text book). ur video is very helpful and concise. it really helped me to understand the purpose of each test a lot better and make statistic more enjoyable. Thank you very much Dr Nic.
Cl Choi (2 года назад)
Easy to understand and precise.  Thanks!
TheLadiesman217137 (2 года назад)
Lol, didnt even pause... haha.. *confused
Alberto Martinico (2 года назад)
Hello, thank you for this video, I found it very helpful. I have one question: in which category does the T-Test fit?
Statistics Learning Centre (2 года назад)
+Alberto Martinico Hi. It depends what the t-test is doing. You can use a t statistic to test the value of a mean, and you can also use a t statistic to test for the difference of two means, paired and independent samples. And you also use a t statistics for individual slope values in a regression. This is why I don't call any of them a t-test! If your instructor or textbook use that terminology, they probably mean testing the value of a mean.
figsandcoffee (2 года назад)
very helpful, but I also wish you said what tests to use.
Statistics Learning Centre (2 года назад)
I guess I could put annotations.
Statistics Learning Centre (2 года назад)
Maybe next time. ANOVA is used for more than two groups so isn't covered here. The difference of two proportions is done several different ways. I'm trying to avoid too much of a cookbook approach so that students know what they are testing, not just the statistic they use. Thanks for your input.
figsandcoffee (2 года назад)
exactly that - the t-test or z-test or ANOVA arent mentioned in the video.  It would be helpful to know upfront where they fit in, since for most students thats what they are looking at and don't understand.  thanks for the extra description.
Statistics Learning Centre (2 года назад)
+figsandcoffee I don't really understand what you mean. A test for a mean is usually a t-test for the value of a mean. A difference of two means is usually a t-test for the difference of two means. You can see more about those on my other videos. A regression is a regression! You do t-tests and an F-test as part of a regression. Can you be more specific about which test you want to know about.
sciencegalxx (2 года назад)
Hi. My topic is on A Study of Budget Slack and the Influence of Budget Participation on Budget Slack. My research objectives are to study the relationship between budget participation, procedural fairness, distributive fairness, trust, goal commitment and manager's propensity to create slack, to investigate the relationship between budget participation on budget slack, to study the impacts of budgetary slack to companies' managerial performance and to determine the effectiveness of budget participation on managerial performance. I am using questionnaire of 7-point Likert Scale from 1- Strongly disagree to 7- Strongly agree for data collection. For budget participation, my questionnaire has 6 questions of Likert Scale type. Should I use mean or median to combine the 6 questions of budget participation into one item of one value for budget participation in SPSS? Budget participation is the independent variable. The mediating variables are procedural fairness, distributive fairness, trust, goal commitment. The dependent variable is budget slack. I would like to test the reliability of the data using Cronbach alpha. I would like to use Pearson correlation to study the relationship of budget participation, procedural fairness, distributive fairness, trust, goal commitment towards budget slack. I would like to use multiple regression for hypothesis testing. And I would like to use factor analysis to test the 6 factors which are budget participation, procedural fairness, distributive fairness, trust, goal commitment and manager's propensity to create slack. My sample size is 154 respondents. The target population is on managers from small and medium companies (SMEs). Am I on the right track for my statistical tests? Any suitable recommendations of statistical tests for my research? Thanks. T
natalia (2 года назад)
All is great and helpful, thanks! But for us, international students - I wish you described the conditions of the problems a bit slower... But when you eliminate different tests' possibilities, the speed is perfect, easy to follow.
danielxxv (2 года назад)
+natalia kureneva On the video, you can change the playback speed to a slower speed using the settings button
Statistics Learning Centre (2 года назад)
+natalia kureneva I'm glad you find them helpful. One of the great things about YouTube is you can always pause and go back over a bit you didn't get. - Or read the captions.
Yassine oulad el majdoub (2 года назад)
can you lead me to some websites where i can find some raw spreadsheets about biological surveys in order to pratice some of these statistic tests using spss software thanks.
Ellie Gunner (2 года назад)
what is the difference between two samples i.e. men and women and one sample, two measures i.e. men and women's opinions on chocolate?
Statistics Learning Centre (2 года назад)
+Ellie Gunner Hi. The second example you give isn't feasible. Each observation is one person who is either male or female. One sample two measures means that both the measures are taken on the same person or entity. You could have, for example, a married couple is the entity, and the two measures are the woman's opinion and the man's opinion. But those are paired and thus different from taking independent samples of men and women. Two samples can be different sizes, whereas for one sample, two measures the columns must be equal length.
Ahmad Kaako (2 года назад)
Great Illustration! You nailed it. Would be great to have official names of the tests as listed in the text books.
Ahmad Kaako (2 года назад)
Thanks a bunch Ajay! That's helpful.
Ajay Saini (2 года назад)
+Ahmad Kaako You can find more about these tests here http://stattrek.com/hypothesis-test/proportion.aspx?Tutorial=AP
Ahmad Kaako (2 года назад)
I agree. Thanks a lot for you great effort!
Statistics Learning Centre (2 года назад)
+Ahmad Kaako That is an interesting idea - but the problem is that text books use different names for tests.
Ranjit Palsingh (2 года назад)
Agree Dr Michael Moroney. I am a student who has just started learning statistics and I found this video helpful to begin with. Can I request you any books related to this topic.
OSIC ARIO (2 года назад)
Hi pls i need help! I'm working on a research that focuses on the views of male and female employees concerning salary and fringe benefits and i dont know how i should analyse the data i have collected. Although i have been using the rank order to i just dont know how to continue. Please help am also to find the difference in opinion of both parties as my hypothesis...
OSIC ARIO (2 года назад)
is there anywhere i could get a tutorial on that?
Statistics Learning Centre (2 года назад)
+SEUN IYADI It sounds as if you need a Wilcoxon Rank sum test, which is like difference of two means, independent samples, but uses ranks rather than values.
h (3 года назад)
Hi, I've to compare three colors in an image. I want to see how different are the components of Red, Green and Blue in the image?
Darwin PC (3 года назад)
Very confused explanation
chrohnix (3 года назад)
i like my one better http://i.imgur.com/T1HSwpu.png
Darshan Patel (3 года назад)
Thank You!
Reem Sulaiman (3 года назад)
Hello there, thanks for your endless effort. I'm having trouble differentiating between the Sign test and Willcoxon test. When do i use each??
Reem Sulaiman (3 года назад)
Hello there, thanks for your endless effort. I'm having trouble differentiating between the Sign test and Willcoxon test. When do i use each??
samser nahid (3 года назад)
Hi, I have two operations for each for different group of people. each group has 90 patient. which statistical test should I use to see level significance (for time taken for operation). Thanks.
Statistics Learning Centre (3 года назад)
+samser nahid It sounds to me as if you have two groups, each with 90 patients in it. If the groups are randomly assigned you will be able to make some causation claims. I presume the time for the operation is a measurement variable - probably time in minutes. So if you look at the video from 7:04 you will see the process applied to a problem like yours.

Хотите оставить комментарий?

Присоединитесь к YouTube, или войдите, если вы уже зарегистрированы.