Igor Shuryak

21 Questions 90 Answers 0 Followers

Questions related from Igor Shuryak

How to generate causal effect estimates from causal forest in the grf R package for continuous treatments?

I am using the grf R package (https://grf-labs.github.io/grf/reference/causal_forest.html) to obtain causal effect estimates for a continuous treatment variable. The package description says:...

16 January 2024 1,961 0 View

How to quantitatively compare partial dependence plots for the same variables from different machine learning models (e.g. random forest, xgboost)?

For example, suppose the data set is analyzed by random forest, and I make the partial dependence plot for predictor variable x. The same data set was also analyzed by a different model, and the...

13 May 2021 5,580 9 View

Does anyone have experience using causal random forests (e.g. causal_forest from grf R package)? Can they be reliably used in observational studies?

I am considering using causal random forests to detect/quantify potential causal effects of a variable of interest (e.g. radiation dose) on an outcome variable (e.g. some type of radiation-induced...

28 April 2021 8,725 2 View

Possible optimization algorithms for fitting a nonlinear model with no analytic solution (contains integrals that can only be solved numerically)?

I would be grateful for suggestions to solve the following problem. The task is to fit a mechanistically-motivated nonlinear mathematical model (4-6 parameters, depending on version of assumptions...

15 April 2020 2,252 12 View

What are the advantages/disadvantages of mixed-effects COX models (coxme R package) vs random forests (randomForestSRC) for survival data analysis?

Specifically, the data set consists of a heterogeneous group of individuals which can be divided into many sub-groups. The random effects (e.g. intercepts and/or slopes) in a mixed COX model could...

27 April 2016 2,247 1 View

How do I eliminate noise variables when using ensemble prediction methods like randomGLM in R?

The task involves predicting a binary outcome in a small data set (sample sizes of 20-70) using many (>100) variables as potential predictors. The main problem is that the number of predictors...

02 November 2015 4,545 10 View

Is logistic regression appropriate for the following ecological data set?

Soil samples were taken from two locations which differ by the values of several variables (x1, x2, etc). There were N1 samples from location 1 and N2 samples from location 2. The total number of...

08 May 2015 5,938 11 View

How to statistically analyze experimental data which turned out to violate the assumptions used for initial power/sample size estimation?

For example, suppose a certain method was chosen for power/sample size calculation for a future experiment, with the intent to use the same method to analyze the experimental data. But the...

06 January 2014 2,413 18 View

What are the most efficient methods for power/sample size estimation for mouse studies with longitudinal data (e.g. tumor volumes measured over time)?

Among the many available methods, which are the most efficient (i.e. require the smallest sample size for defined alpha and beta) and relatively straightforward to implement?

20 December 2013 832 9 View

What are some useful techniques to statistically compare exponentially distributed data?

Suppose there are several treatment groups. Within each group there are exponentially distributed data, i.e. the number of counts is proportional to exp[-A*x^B], where A and B are parameters. What...

01 October 2013 4,871 55 View

How to assess goodness of fit for a non-linear model?

Suppose a non-linear smooth function is fitted to some data (e.g. means and standard errors for cell survival after various radiation doses). What are some useful ways to assess goodness of fit...

06 September 2013 9,572 45 View

How to attach Ustilago maydis cells to a mylar film at the bottom of a culture dish?

The issue is how to induce U. maydis cells to attach to the bottom of a culture dish, which is composed of a mylar film. Thanks in advance!

27 August 2013 4,876 0 View

How useful (or not) is partial rank correlation coefficient (PRCC) for estimating the sensitivity of non-linear models to parameter values?

I used PRCC in one paper (A model of interactions between radiation-induced oxidative stress, protein and DNA damage in Deinococcus radiodurans, available on my page) because reviewers requested...

22 August 2013 910 4 View

Which normality test is preferable for small data sets (<10 observations)?

There are several commonly used normality tests. I wonder what do you suggest is optimal for small data sets?

15 July 2013 301 63 View

What is the best way to perform and report parameter sensitivity analysis when fitting nonlinear models?

For example, suppose a nonlinear model is fitted to a data set. It is possible to map out a region in the parameter space around the best-fit point, within which the residual sum of squares...

11 July 2013 2,017 35 View

Can alpha/beta ratios for the same tumor type differ for stereotactic vs standard radiotherapy?

In other words, can alpha/beta ratios for the same cancer type depend on dose per fraction?

02 July 2013 9,149 5 View

What is known about growth-stimulatory or inhibitory intercellular signaling in C. neoformans?

For example, do C. neoformans cells secrete signals which stimulate other C. neoformans cells to proliferate or not to priliferate?

02 July 2013 3,509 0 View

Is radiation dose (or BED) to the tumor isocenter, or to the tumor periphery, more important for tumor killing by radiotherapy?

For different radiotherapy techniques, the ratio of isocenter/peripheral doses differs substantially. Is anything known about which region - center or periphery - is most relevant for tumor killing?

27 June 2013 5,793 19 View

Is there any research about cell cycle redistribution of cancer cells subjected to hypofractionated radiotherapy compared with standard radiotherapy?

For example, comparing stereotactic techniques with large doses per fraction to standard fractionation?

24 June 2013 8,132 7 View

Is there any evidence for reduced effectiveness of split-dose recovery of mammalian cell survival as the dose per fraction increases?

For example, assuming a sufficiently long inter-fraction repair period, does increasing the dose per fraction reduce the relative gain in survival?

20 June 2013 4,497 1 View

Is there any recent research on the effects of densely ionizing radiation (e.g. alpha particles) on filamentous fungi?

For example, what about effects of alpha-emitting radionuclides?

12 June 2013 2,657 4 View