Find Jobs
Hire Freelancers

Calculating likelihood of event based on retrospective analysis

£20-250 GBP

Closed
Posted about 10 years ago

£20-250 GBP

Paid on delivery
I have a simple dataset consisting of the dates/times at which certain medications were taken by a patient. The amount of medication taken, and the different types, can be entirely variable. By looking retrospectively at previous medicine intake, I'd like to make a best guess estimate as to which medicine that same patient is most likely to be taking at any given date/time in the future. Essentially I'm looking to base my estimate on the following factors: * Time: medication is usually taken at fairly regulated intervals. If a certain medication is always taken at a specific time of day, and we're close to that time, increase the likelihood that that medication will be taken. * Day: similar to time, certain medications may only be taken on certain days of the week. This should help determine the probability of a given medication being taken. However, it's worth nothing that this should not strictly exclude certain medications (i.e: don't exclude a medication simply because it's never been taken on a given day before). My ultimate goal is to hopefully come up with a solution that can be solved computationally and integrated into a software application. I've been told that multinomial logistic regression would be a suitable approach, but am really looking for some clarification and assistance from an expert.
Project ID: 5312460

About the project

18 proposals
Remote project
Active 10 yrs ago

Looking to make some money?

Benefits of bidding on Freelancer

Set your budget and timeframe
Get paid for your work
Outline your proposal
It's free to sign up and bid on jobs
18 freelancers are bidding on average £212 GBP for this job
User Avatar
Expert in statistics and M.Sc. in mathematics is here to complete the project for you. I am one of the top ranking statistics freelancer in freelancer.com. If you award me the project you have to pay 150 pound now and 150 pound after completion. If you ready to release 150 pound now only then you may contact.
£300 GBP in 10 days
4.9 (227 reviews)
6.8
6.8
User Avatar
Hi ndgiacomelli I am hands down the best statistician on this website. Let's chat about your project a bit more. I have a few other project to complete, but we can definitely bounce a few emails before we officially onboard and get started. If you are interested in high quality and are not cost concious then my service is unmatched here. Think of me as the big fish in a small pond :) Please view my profile, read a few reviews (some of them really made me blush), then shoot me an email and I can ask you a few questions about the data source and the long term objective you discuss. Cheers, SstatsC
£500 GBP in 7 days
5.0 (43 reviews)
6.6
6.6
User Avatar
Hi. I think I can do this project for you, here are some examples of my previous similar in data analys work: http://www.freelancer.com/projects/4429429.html http://www.freelancer.com/projects/Figuring-out-algorithim-Matlab.html Regards, Vova
£200 GBP in 7 days
4.9 (150 reviews)
6.6
6.6
User Avatar
Hi, I have earned a master's degree in statistics. I might help. Waiting for your response. Thanks
£233 GBP in 7 days
5.0 (42 reviews)
6.1
6.1
User Avatar
Hi, I am interested to the job you recently posted. I have been a professional statistical analyst for over six years. I am an expert user of SPSS, STATA, Eviews, gretl, Minitab and MS Excel. Please see my public profile for my education, related work experiences, previous work feedback and portfolio items. As your requirements, I am able to run multinomial logistic regression or other possible alternatives such as non parametric test with cross tabulations, hypothesis testing etc based on your research objectives and variable characteristics. I am excited to assist you in event based on retrospective analysis - please feel free to contact me directly to discuss this position further. Thanking you.
£200 GBP in 5 days
4.6 (76 reviews)
6.2
6.2
User Avatar
Experienced math worker here. U can definitely rely on me regarding ur project. Please see my reviews to be assured about my expertise. Regards.
£277 GBP in 3 days
5.0 (49 reviews)
5.4
5.4
User Avatar
A proposal has not yet been provided
£122 GBP in 5 days
5.0 (49 reviews)
5.5
5.5
User Avatar
Hi! I am a doctor as well as an expert statistician. Highly experienced in SPSS as well! lets start the work? Thanks!
£160 GBP in 3 days
4.9 (7 reviews)
4.4
4.4
User Avatar
I'm not going to fully commit to this project, but I had a couple of thoughts that might be helpful. Try using a Bayesian model. Here is my suggestion: For each medication m, let p(m,d) be the probability of m being taken on day d. Put a beta prior over these and update (simply by adding occurrence count to the parameters). Assume a medication is taken k times on the days that it is taken. You can model the time by using k normal distributions with fixed (known) variance (say an hour for standard deviation). This means that the medication is taken at k specific average time with a known variance. You can put a normal prior on the mean of these distributions and the posterior is updated again with a simple update rule. Once you have these models updated with some observation data, you can estimate the probability of taking a medication by multiplying these two posteriors.
£23 GBP in 3 days
4.9 (5 reviews)
4.1
4.1
User Avatar
Experienced and accomplished academic writer at your service. Please contact for quality and result oriented services. Regards
£142 GBP in 3 days
4.8 (5 reviews)
3.6
3.6
User Avatar
Experienced statistician with lot of practical knowledge in field. Expert in all kind of hypothesis/statistical analysis using tools like SPSS, R, Stata, SAS and AMOS
£277 GBP in 10 days
3.5 (6 reviews)
4.0
4.0
User Avatar
Hello, I have degrees in math, computational physics, chemistry, along with a CS minor. I hav been coding with various languages for over 5 yars now. I have devloped databaases from scratch and written programs to solve optimizaton problems. I look forward to hearing from you to discuss this project further.
£222 GBP in 7 days
5.0 (1 review)
1.5
1.5
User Avatar
Have a good experience in analyzing the data. Have good academic background/knowledge about statistics.
£300 GBP in 10 days
0.0 (0 reviews)
0.0
0.0
User Avatar
A proposal has not yet been provided
£33 GBP in 3 days
0.0 (0 reviews)
0.0
0.0
User Avatar
A proposal has not yet been provided
£250 GBP in 10 days
0.0 (0 reviews)
0.0
0.0
User Avatar
With more than 3 years of experience, I have skillset and capabilities best suited for the profile. I have worked with different industries and built predictive models. Hand-on experience when it comes to linear regression model. Used different forecasting techniques when building a forecasting algorithm. Know all about segmentation and factor analysis. Have used major tools and programming languages like SAS,SPSS and R. I can easily work for 30-40 hours/week. Lets discuss further over a skype call. Regards, Sahil Khan
£222 GBP in 5 days
0.0 (0 reviews)
0.0
0.0
User Avatar
Working as Senior financial analyst in one of the world's leading automotive company Worked on logistic regression (using Sigmoid function) to estimate the investment of the project MBA finance - Nottingham University Business School Partner has experience in computer programming and applications. Both of us will be able to provide the project deliverables
£150 GBP in 3 days
0.0 (0 reviews)
0.0
0.0
User Avatar
Hi, I am interested in the project. As you know it can be done using multinomial logistic regression. Method works as follows. We have a patient (an observed data point, it can be many) and there are many dates/times when medicine was taken (termed as explanatory variables). Now using this information, we can find probability (between 0 to 1) of medicine being taken at different times in future (termed as categorical outcome, can be many). Softmax algorithm can be used to write a code for your requirement. I would suggest python as programming language, but we can take others like C, C++, Fortran,matlab etc. depending upon your comfort level. If you are interested to discuss it further, I am available. Regards Sourabh
£200 GBP in 3 days
0.0 (0 reviews)
0.0
0.0

About the client

Flag of UNITED KINGDOM
United Kingdom
0.0
0
Member since Jan 12, 2014

Client Verification

Thanks! We’ve emailed you a link to claim your free credit.
Something went wrong while sending your email. Please try again.
Registered Users Total Jobs Posted
Freelancer ® is a registered Trademark of Freelancer Technology Pty Limited (ACN 142 189 759)
Copyright © 2024 Freelancer Technology Pty Limited (ACN 142 189 759)
Loading preview
Permission granted for Geolocation.
Your login session has expired and you have been logged out. Please log in again.