# variable selection

**URL:** https://discourse.datamethods.org/c/stat/select/11.md

[Latest](https://discourse.datamethods.org/latest.md) · [Categories](https://discourse.datamethods.org/categories.md) · [Tags](https://discourse.datamethods.org/tags.md)

---

## [About the variable selection category](https://discourse.datamethods.org/t/about-the-variable-selection-category/24)

<div class="topic-metadata">

**Author:** [@f2harrell](https://discourse.datamethods.org/u/f2harrell)\
**Replies:** 2\
**Last updated:** [October 31, 2024, 10:20am UTC](https://discourse.datamethods.org/t/about-the-variable-selection-category/24 "2024-10-31T10:20:51Z")

</div>

Selection of predictive features in multivariable modeling, one-at-a-time screening of variables, and the cost of feature selection compared to using fuller models, possibly with penalization (shrinkage; regularization). …

---

## [Choosing variables for mutivariable survival prediction](https://discourse.datamethods.org/t/choosing-variables-for-mutivariable-survival-prediction/5130)

<div class="topic-metadata">

**Author:** [@Indranil\_Mallick](https://discourse.datamethods.org/u/Indranil_Mallick)\
**Replies:** 21\
**Last updated:** [March 18, 2024, 8:33pm UTC](https://discourse.datamethods.org/t/choosing-variables-for-mutivariable-survival-prediction/5130 "2024-03-18T20:33:34Z")

</div>

I am an oncologist and I am trying to grasp the concepts of variable selection for prediction of survival. This is a wonderfully educative forum, and I thought I’d ask here. There is a dataset of approx 600 patients wit…

---

## [Appropriate to do lasso, then standard glm using variables with non-zero coef. from lasso?](https://discourse.datamethods.org/t/appropriate-to-do-lasso-then-standard-glm-using-variables-with-non-zero-coef-from-lasso/16932)

<div class="topic-metadata">

**Author:** [@Hanis\_Kadir](https://discourse.datamethods.org/u/Hanis_Kadir)\
**Replies:** 1\
**Last updated:** [July 2, 2024, 11:34am UTC](https://discourse.datamethods.org/t/appropriate-to-do-lasso-then-standard-glm-using-variables-with-non-zero-coef-from-lasso/16932 "2024-07-02T11:34:23Z")

</div>

My dataset comprises 1300 patient records, featuring 25 variables (expanded to 28 after accommodating categorical variables with multiple levels) carefully selected for their clinical relevance and significance. The outc…

---

## [BBR: Challenges of Analyzing High Dimensional Data](https://discourse.datamethods.org/t/bbr-challenges-of-analyzing-high-dimensional-data/7231)

<div class="topic-metadata">

**Author:** [@f2harrell](https://discourse.datamethods.org/u/f2harrell)\
**Replies:** 12\
**Last updated:** [November 28, 2023, 1:06pm UTC](https://discourse.datamethods.org/t/bbr-challenges-of-analyzing-high-dimensional-data/7231 "2023-11-28T13:06:25Z")

</div>

This topic is for Q&A and discussions around the BBR chapter on high dimensional data analysis.

---

## [Choosing penalty parameters for elastic net](https://discourse.datamethods.org/t/choosing-penalty-parameters-for-elastic-net/922)

<div class="topic-metadata">

**Author:** [@bobmcpop](https://discourse.datamethods.org/u/bobmcpop)\
**Replies:** 9\
**Last updated:** [September 6, 2022, 7:42pm UTC](https://discourse.datamethods.org/t/choosing-penalty-parameters-for-elastic-net/922 "2022-09-06T19:42:39Z")

</div>

I’m trying to develop a classification model with \>70 variables and training set of only 500 (case prevalence 10%). I’ve used cross-validation before to choose the penalty (lamba) for lasso, similar to what’s described h…

---

## [Question about symmetry in dichotimization cutpoints in Federov et al. 2009](https://discourse.datamethods.org/t/question-about-symmetry-in-dichotimization-cutpoints-in-federov-et-al-2009/4921)

<div class="topic-metadata">

**Author:** [@alanlhutchison](https://discourse.datamethods.org/u/alanlhutchison)\
**Replies:** 3\
**Last updated:** [October 1, 2021, 7:37pm UTC](https://discourse.datamethods.org/t/question-about-symmetry-in-dichotimization-cutpoints-in-federov-et-al-2009/4921 "2021-10-01T19:37:11Z")

</div>

I have been trying to read through Fedorov et al 2009 so that I can explain it to my clinical colleagues. I understand (and can explain) why dichotomizing a continuous variable leads to a reduction in power (or an increa…

---

## [How to test if IV and DV measuring different things](https://discourse.datamethods.org/t/how-to-test-if-iv-and-dv-measuring-different-things/3774)

<div class="topic-metadata">

**Author:** [@mohsen](https://discourse.datamethods.org/u/mohsen)\
**Replies:** 1\
**Last updated:** [September 23, 2020, 1:00pm UTC](https://discourse.datamethods.org/t/how-to-test-if-iv-and-dv-measuring-different-things/3774 "2020-09-23T13:00:02Z")

</div>

Hi, After working around a year on my research paper I recieved a critic from one of my colleagues that question my whole research designe. Since I’m not an expert, I wanted to ask if his critic is fair and is there a w…

---

## [Clarification on chance-corrected adequacy measure for a subset of predictors](https://discourse.datamethods.org/t/clarification-on-chance-corrected-adequacy-measure-for-a-subset-of-predictors/3132)

<div class="topic-metadata">

**Author:** [@COOLSerdash](https://discourse.datamethods.org/u/COOLSerdash)\
**Replies:** 1\
**Last updated:** [March 26, 2020, 3:05pm UTC](https://discourse.datamethods.org/t/clarification-on-chance-corrected-adequacy-measure-for-a-subset-of-predictors/3132 "2020-03-26T15:05:38Z")

</div>

Prof. Frank Harrell writes in his book Regression Modeling Strategies (2nd ed.) in section 9.8.4 (page 207): A chance-corrected adequacy measure could be derived by squaring the ratio of the R-index for the subset to t…

---

## [Model specification/variable selection for risk prediction model](https://discourse.datamethods.org/t/model-specification-variable-selection-for-risk-prediction-model/1783)

<div class="topic-metadata">

**Author:** [@rd4218](https://discourse.datamethods.org/u/rd4218)\
**Replies:** 3\
**Last updated:** [June 27, 2019, 6:35pm UTC](https://discourse.datamethods.org/t/model-specification-variable-selection-for-risk-prediction-model/1783 "2019-06-27T18:35:46Z")

</div>

Hi, I am new to this forum and looking for some advice on my analysis plans. I would like to identify clinical features/combinations of clinical features which can predict high risk of a colorectal cancer diagnosis. Cli…
