Question 1 of 35
Explain to me the 80/20 rule.
Data split for training and testing.
The Pareto principle (also known as the 80–20 rule, for many events, roughly 80% of the effects come from 20% of the causes. "80% of your sales come from 20% of your clients." 20% of the peapods in his garden contained 80% of the peas.
Question 2 of 35
What was the largest data set that you processed? How did you process it?
My PhD project was based on a cohort, which contained more than 6k participants.
A dataset with more than 2000 patients and more than 50 variables. I formatted and labeled it with SAS.
The biggest data set I processed is 6000*874, which need to be classified.
The CDC dataset on the National Health and Nutrition Examination Survey of 10,000 subjects.
10000000 million observations. Processed it using SAS
I have processed Census data in a research project, I processed it by performing several analysis on the data. Such as, the well know mean, mode and median of different variables. I havve also performed the frequencies of diferent variables. From there, I had to perform variaty of testings to see if the data is following a normal distribution curve. If not, I had to remove all the outliers in order to make the data normal. Using quality control meansures.
Repeated measures data using mixed models.
Nhanes data and seer madicare data and United health data.
Question 3 of 35
Would you say you are creative? When have you shown creativity?
Yes, I am creative, and I have shown my creativity thinking in data analysis.
Yes I am very creative. I have a lot of skills with spreadhseet, and data management. Creating graphs, tables, pie charts etc is something that I excel in. I have recently had to create charts and graphs for a project that I am working on and I got to show my creativity with the design and details.
Yes I am very creative. I have a lot of skills with spreadsheet, and data management. Creating graphs, tables, pie charts etc. Is something that I excel in. I have recently had to create charts and graphs for a project that I am working on and I got to show my creativity with the design and details.
Thesis idea from limited dataset.
Yes,. I've created a HIV resistance score against drug based on mathem.
I think I am creative, but I used my creative in different situations. When I work on data collection, data analysis, this needs to follow the rule and to be careful, but not the creative. But when I am working on a proposal to solve a health problem, which needs some creative ideas, and thinking some research topics that others haven't done.
Yes. Working as a biostatistician, I alway face the problem that the real case is much more complicated than expected, such as missing values, complex study design, clustered or correlated covariates and some ethical issues. Thus we cannot simply apply a statistical model to solve the problem. I showed my creativity when making choices from applicable methods.
By drawing statistical conclusion.
I really don't know where to show my creativity when working as a biostatistician.
Before the problem be
Yes. I find the best way to truly be creative is to be collaborative. When working with people from multiple backgrounds and view points, you can truly take parts of several ideas and come up with a solution that is both creative and appropriate. like developing visual tools to motivate people while increasing accountability.
Question 4 of 35
What studies have you worked on in the past?
Enviornmental air quality studies.
In the past, I have worked on studies involving groups in the Adopt-A-Highway program. I have studied multiple financial data groups and anazlyzed the information to make sure everything is correct.
I have done a study on Forecasting electricity demand for Windhoek residence, for my Honours research.
Except dose/response Phase I (only one), I have worked on preclincal animal's model (cardiology, neurology ...) study pilot, Phase II and III : from placebo controlled to therapeutic stregaies, including.
I have worked on the project of China Air pollution project, which is related to.
I am trying to apply statistics in the relations between countries in the new global climate.
A project to build a model to determine the optimal drug combination with least toxicity; A clinical research project to compare the treatment effects of 2 different cardiovascular drugs; A survey analysis project.
Repeated measures anova in animal experiments.
Question 5 of 35
Why do you feel statistics are important?
Statistics are important because they are the data collected in order for the policies makes and all relevant stakeholders interested in obtaining the statistics in order for them to make informative decision that will influence the reaction of the statistics at hand.
Using statistics we solve any difficulties such as related to market, business forcasting, quality control and so on.
Because it help us to decide. In all situation we need to decide with respect to information that we have, and it is statistics that help us to convert data to information.
Statistics is imp bcoz it is used in every field and it helps one to attain its objective in their respective field.
Provides meaningful insights of a study.
Statistics are important because it allows the public to be aware of the issues that are going on around them. If there werent people such as statisticians working to analyze and interpret large sets of data, there would be no collection of running statistics pertaining to a certain cause. It allows people to easily view and obtain informtaion on important topics.
Statistics is important because it help in policy and decision making.
They are very important because they are used in most of humans fields.
It gives us insight based on solid data, which we cannot get from other methods.
First, by exploratory analysis, you can get a basic understanding of the data, the characteristics of the sample you are analyzing. Second, by model fitting or hypothesis testing, you may find hidden pattern or associations.
They are imprtant because they are resposible with concerting data into information and let the right users be aware of the happenings. They also inform strategical planners.
Question 6 of 35
Do you have experience working with SQL?
Question 7 of 35
How do you like to present your data findings to your coworkers?
In graphical presentation form.
I like to present my data findings in a few ways. Sometimes the data I have collected is shown better in a simple excel chart. Other data findings are more easily understood in a graph or chart. How I present my data findings all depends on the type of data being researched and the best way to get that data a crossed to another person so they can easily understand it.
It depends of findings and coworkers. It could be outlayer which came from mistake. Statistic limitation, or un scientific concil if hypothesis are not different (glorious p value), but combiin.
By ussing the statistical programs and In a computer screen.
Using graphs and tables. As straightforward as possible.
Question 8 of 35
How would you explain a p-value to a novice?
Probability of having the same result of a more extreme one assuming that H0 is true.
In frequentist statistics, the p-value is a function of the observed sample results (a test statistic) relative to a statistical model, which measures how extreme the observation is. The p-value is the probability that the observed result has nothing to do with what one is actually testing for. Specifically, the p-value is defined as the probability of obtaining a result equal to or "more extreme" than what was actually observed, assuming that the model is true. There are different definitions of "extreme"; see definition below.
Its a propability value that can be used after decisions of the statistical tests.
The probability of obtaining a result equal to or "more extreme" than what was actually observed.
Question 9 of 35
Why is mean square error a bad measure of model performance?
When it is under predicted or over predicting.
The answers to questions like this usually boil down to how the model is being used.
Suppose you are a store owner using a model to predict how many widgets to stock. If you under-predict, you lose the profit on the widgets you could have sold. If you over-predict, you have to deal with the extra widgets on your shelves. Perhaps the widgets are spoiling. The costs of overpredicting may be different from the costs of underpredicting, and these costs are in dollars, so there is no reason to be squaring things. This is an example where squared error may not make sense.
In statistics, the mean squared error (MSE) or mean squared deviation (MSD) of an estimator measures the average of the squares of the errors or deviations, that is, the difference between the estimator and what is estimated. MSE is a risk function, corresponding to the expected value of the squared error loss or quadratic loss. The difference occurs because of randomness or because the estimator doesn't account for information that could produce a more accurate estimate.
One case where MSE will be a bad measure is those cases where linear regression’s assumption are violated.
Also, the mean squared error can only be compared between models whose errors are measured in the same units.
Question 10 of 35
How would you rate your education? What things would you like to improve upon?
Excellent. Advances in medicinal field.
My education level is up to standard. I would like to continue with my study to again an advanced level.
I think my Master program education in biostatistics can be rated as 9. On one side, I am enrolled in one of the top universities in the world. The professors taught me are leading thinkers in biostatistics. On the other side, I am a straight A student and excel at most every class. I would like to improve upon the application in practice of what I have learnt.
I would rate my education as a proficient in statistical background, I would love to improve on my existing skills on some of the statistical packages, for more kknowledge attainment.
Question 11 of 35
Why did you enter a career in statistics?
With statistics we can take any decision in any condition. It gives us future requirement so we know advance requirement for future.
My education at university which was statistics give me prominency to choose this kind of career.
Because I had a liking for maths and moreover its application.. So I opted for statistics as my career.
Via foundation degree in maths.
Question 12 of 35
What do you know about our company?
Question 13 of 35
What is your dream data set, if you could have access to anything?
Question 14 of 35
What is model fitting?
Question 15 of 35
Tell me about a data project you have done that was successful. What made it successful?
Question 16 of 35
What are your salary expectations?
Question 17 of 35
Rate your communication skills from 1-10 with proper examples backing your given rating.
Question 18 of 35
What are your career aspirations beyond this job?
Question 19 of 35
What leadership qualities do you possess?
Question 20 of 35
What makes you a great problem solver?
Question 21 of 35
What excites you?
Question 22 of 35
Tell me about yourself.
Question 23 of 35
How do you like to be recognized for your accomplishments?
Question 24 of 35
Tell me about a contribution you made to the last team you worked on.
Question 25 of 35
What is your biggest strength when it comes to mathematics?
Question 26 of 35
Tell me about your post-secondary education.
Question 27 of 35
Why are you looking for a new position?
Question 28 of 35
What do you enjoy most about your career as a Statistician?
Question 29 of 35
What do you dislike the most about being a Statistician?
Question 30 of 35
Do you have experience with database design?
Question 31 of 35
What was the last thing that you did for fun?
Question 32 of 35
What is your favorite algorithm? Can you explain it to me?
Question 33 of 35
Tell me the last time you had completely unexpected results. What did you do after?
Question 34 of 35
What do you think our company can offer that you are not receiving in your current role?
Question 35 of 35
Tell me about a time you led a difficult project.