Reference Class Forecasting in Python code.
- or -
Post a project like this£280(approx. $351)
- Posted:
- Proposals: 12
- Remote
- #3442269
- Expired
Artificial Intelligence| machine Learning |Deep Learning |Computer Vision |Medical Imaging | NLP
Kimhae
Data analyst | Writer & Researcher | Statistician | Wikipedia editor & Publisher
Bay Minette
Quick Graphic Designer + Animator + Video Editor + Photo Editor + Logo Designer + Autocad Designer
Sydney
66498419624052306654277578037108865038705516811152704885618553625512463847676476906
Description
Experience Level: Intermediate
I am looking for someone to build me a piece of Python code that will allow me to undertake some Reference Class Forecasting on data.
I want to update the code for where the categories/reference classes will be ie in columns C, D and say Z and performance to be plot is in column AB
But, next time it may only be 1 category in column F and output performance in column L.
So code needs to be dynamic and easy to be updated
Data will be in excel and the Python code will need to produce and provide a number of statistical analyses and outputs such as graphs from the data from a number of categories. I am interested in a distribution histogram, P-value outputs from P1-P100 and other statistical tests as recommended by the incumbent winner.
Reference Class Forecasting takes the outside-view approach to challenge forecasts, looking at the performance of past projects or programmes overall and encouraging risks to be managed at a portfolio level.
This is achieved using an approach called Kernel Density Estimation and ratio ie baseline divide by forecast/actual = ratio ie 100/120 =1.2
I want the code to provide recommended classes to look at based on statistical recommendations
"Reference Classes should be based on the conclusions for your statistical testing – I appreciate the test for sample size, but how about testing differences between project categories and regions? And then creating reference classes based on the results"
Have you tried log transforming the x-axes?"
I can provide dummy data and information to winning bidder.
I want to update the code for where the categories/reference classes will be ie in columns C, D and say Z and performance to be plot is in column AB
But, next time it may only be 1 category in column F and output performance in column L.
So code needs to be dynamic and easy to be updated
Data will be in excel and the Python code will need to produce and provide a number of statistical analyses and outputs such as graphs from the data from a number of categories. I am interested in a distribution histogram, P-value outputs from P1-P100 and other statistical tests as recommended by the incumbent winner.
Reference Class Forecasting takes the outside-view approach to challenge forecasts, looking at the performance of past projects or programmes overall and encouraging risks to be managed at a portfolio level.
This is achieved using an approach called Kernel Density Estimation and ratio ie baseline divide by forecast/actual = ratio ie 100/120 =1.2
I want the code to provide recommended classes to look at based on statistical recommendations
"Reference Classes should be based on the conclusions for your statistical testing – I appreciate the test for sample size, but how about testing differences between project categories and regions? And then creating reference classes based on the results"
Have you tried log transforming the x-axes?"
I can provide dummy data and information to winning bidder.
Aleister H.
0% (0)Projects Completed
-
Freelancers worked with
-
Projects awarded
0%
Last project
8 May 2024
United Kingdom
New Proposal
Login to your account and send a proposal now to get this project.
Log inClarification Board Ask a Question
-
There are no clarification messages.
We collect cookies to enable the proper functioning and security of our website, and to enhance your experience. By clicking on 'Accept All Cookies', you consent to the use of these cookies. You can change your 'Cookies Settings' at any time. For more information, please read ourCookie Policy
Cookie Settings
Accept All Cookies