Cox Regression Help: Finding Data for Analysis

  • Thread starter AlmostFamous
  • Start date
  • Tags
    Regression
In summary, a person is looking for data to use in a coursework on cox regression. They have had trouble finding data with enough detail and are asking for suggestions on where to find it. Another person suggests a website with a sample data set, but the original person had already seen it and found it insufficient. They continue to search for suitable data.
  • #1
AlmostFamous
14
0
First of all, I'm not sure if this is the best place to ask this question so if it isn't...sorry.

I'm doing a piece of coursework on cox regression, but I'm having trouble finding any data to use. Most of the data I've seen just gives percentages of people in certain groups, which isn't much use. I need something which itemises characteristics of each person. I've attached a sample data set I was given in a word document, 'cause I've no doubt I didn't explain that well. I also have to do some work on time series analysis and I had no trouble finding some data for that.

The data doesn't have to be complex, just enough to do a reasonable analysis on. Does anyone know of any good websites to look on for this sort of data?

Thanks for any help
 

Attachments

  • cox reg.doc
    73.5 KB · Views: 162
Physics news on Phys.org
  • #2
Have you tried a Google search for "cox regression"? The first hit I got was http://www.statsdirect.com/help/regression_and_correlation/cox_regression.htm

which apparently has a sample data set and some statistics calculated from it.

BTW I know nothing about cox regression itself so apologies if this is irrelevant.
 
Last edited by a moderator:
  • #3
thanks, but i'd tried that. I had actually seen this one before, but the data isn't complex enough for the coursework.

the main problem i am finding is that there is plenty of data about cox regression, but very little about what data sets they used to do the analysis with in the first place.
 
  • #4
Don't know if anyone else was looking for this data, but after sifting through hundreds of web pages, I think I've got some, just waiting to see if the tutor okays it.

Thanks though to anyone who was helping.
 

1. What is Cox regression and how does it work?

Cox regression, also known as the Cox proportional hazards model, is a statistical method used to analyze survival data. It determines the relationship between a set of predictor variables and the time it takes for an event to occur. The model assumes that the hazard rate (the probability of the event occurring at a specific time) is proportional to the hazard rate of the baseline group.

2. What types of data are suitable for Cox regression analysis?

Cox regression is commonly used in medical and epidemiological studies to analyze time-to-event data, such as survival times of patients with a disease. It can also be used in other fields where time-to-event data is relevant, such as economics and engineering. The data should be continuous and have a non-negative distribution.

3. How do I find data for Cox regression analysis?

There are various sources for finding data suitable for Cox regression analysis. These include publicly available datasets, such as those from government agencies or research institutions, and data collected from your own experiments or surveys. It is important to ensure that the data is appropriate for your research question and properly formatted for analysis.

4. What are the assumptions of Cox regression?

The Cox proportional hazards model assumes that the hazard rate is proportional to the hazard rate of the baseline group. It also assumes that the censoring of data is non-informative, meaning that the reason for censoring is not related to the outcome being studied. Additionally, the model assumes that there is no multicollinearity among the predictor variables.

5. How do I interpret the results of a Cox regression analysis?

The results of a Cox regression analysis will provide hazard ratios, which represent the relative risk of the event occurring for each predictor variable. A hazard ratio greater than 1 indicates an increased risk, while a hazard ratio less than 1 indicates a decreased risk. These results can also be visualized using a Kaplan-Meier curve, which shows the survival probabilities over time for different groups of individuals based on their predictor variable values.

Similar threads

  • Set Theory, Logic, Probability, Statistics
Replies
4
Views
1K
  • Set Theory, Logic, Probability, Statistics
Replies
23
Views
2K
  • Introductory Physics Homework Help
Replies
1
Views
840
  • STEM Educators and Teaching
Replies
11
Views
2K
  • Set Theory, Logic, Probability, Statistics
Replies
30
Views
2K
  • General Math
Replies
1
Views
799
  • Set Theory, Logic, Probability, Statistics
Replies
2
Views
466
  • Linear and Abstract Algebra
Replies
3
Views
1K
Replies
9
Views
1K
Back
Top