Researchers at Columbia University, Princeton and Harvard University have developed a new approach for analyzing big data that can drastically improve the ability to make accurate predictions about medicine, complex diseases, social science phenomena, and other issues.
In a study published in the December 13 issue of Proceedings of the National Academy of Sciences (PNAS), the authors introduce the Influence score, or “I-score,” as a statistic correlated with how much variables inherently can predict, or “predictivity”, which can consequently be used to identify highly predictive variables.
“In our last paper, we showed that significant variables may not necessarily be predictive, and that good predictors may not appear statistically significant,” said principal investigator Shaw-Hwa Lo, a professor of statistics at Columbia University. “This left us with an important question: how can we find highly predictive variables then, if not through a guideline of statistical significance? In this article, we provide a theoretical framework from which to design good measures of prediction in general. Importantly, we introduce a variable set’s predictivity as a new parameter of interest to estimate, and provide the I-score as a candidate statistic to estimate variable set predictivity.”
Current approaches to prediction generally include using a significance-based criterion for evaluating variables to use in models and evaluating variables and models simultaneously for prediction using cross-validation or independent test data.
“Using the I-score prediction framework allows us to define a novel measure of predictivity based on observed data, which in turn enables assessing variable sets for, preferably high, predictivity,” Lo said, adding that, while intuitively obvious, not enough attention has been paid to the consideration of predictivity as a parameter of interest to estimate. Motivated by the needs of current genome-wide association studies (GWAS), the study authors provide such a discussion.
In the paper, the authors describe the predictivity for a variable set and show that a simple sample estimation of predictivity directly does not provide usable information for the prediction-oriented researcher. They go on to demonstrate that the I-score can be used to compute a measure that asymptotically approaches predictivity. The I-score can effectively differentiate between noisy and predictive variables, Lo explained, making it helpful in variable selection. A further benefit is that while usual approaches require heavy use of cross-validation data or testing data to evaluate the predictors, the I-score approach does not rely as much on this as much.
“We offer simulations and an application of the I-score on real data to demonstrate the statistic’s predictive performance on sample data,” he said. “These show that the I-score can capture highly predictive variable sets, estimates a lower bound for the theoretical correct prediction rate, and correlates well with the out of sample correct rate. We suggest that using the I-score method can aid in finding variable sets with promising prediction rates, however, further research in the avenue of sample-based measures of predictivity is needed.”
The authors conclude that there are many applications for which using the I-score would be useful, for example in formulating predictions about diseases with high dimensional data, such as gene datasets, in the social sciences for text prediction or financial markets predictions; in terrorism, civil war, elections and financial markets.
“We’re hoping to impress upon the scientific community the notion that for those of us who might be interested in predicting an outcome of interest, possibly with rather complex or high dimensional data, we might gain by reconsidering the question as one of how to search for highly predictive variables (or variable sets) and using statistics that measure predictivity to help us identify those variables to then predict well,” Lo said. “For statisticians in particular, we’re hoping this opens up a new field of work that would focus on designing new statistics that measure predictivity.”
Learn more: Researchers develop new approach for better big data prediction
[osd_subscribe categories=’prediction-tool’ placeholder=’Email Address’ button_text=’Subscribe Now for any new posts on the topic “PREDICTION TOOL”‘]
Receive an email update when we add a new PREDICTION TOOL article.
The Latest on: Accurate predictions
[google_news title=”” keyword=”accurate predictions” num_posts=”10″ blurb_length=”0″ show_thumb=”left”]
via Google News
The Latest on: Accurate predictions
- International SWOT mission can improve flood predictionon May 8, 2024 at 10:29 am
Rivers, lakes, and reservoirs are like our planet's arteries, carrying life-sustaining water in interconnected networks. When Earth's water cycle runs too fast, flooding can result, threatening lives ...
- EA FC 24 Ligue 1 TOTS: release date, predictions and latest Ultimate Team leakson May 8, 2024 at 10:00 am
The next EA FC 24 Team of the Season squad to be released in Ultimate Team is the Ligue 1 TOTS, with Kylian Mbappe expected to headline the squad.
- Google DeepMind Unveils AlphaFold 3, Achieves 50% Better Prediction Accuracyon May 8, 2024 at 9:20 am
It has also launched AlphaFold Server, a free platform that scientists globally can use for non-commercial research, enabling them to model structures composed of proteins, DNA, RNA, and other ...
- Who is Allan Lichtman and how does he predict the presidential race with such accuracy?on May 8, 2024 at 8:36 am
Known as the presidential prognosticator, this American University professor has a strong record of predicting who might win the White House.
- Pacers vs. Knicks Game 2: NBA prediction, picks, odds and Bet365 bonus code for Wednesdayon May 8, 2024 at 6:45 am
The New York Knicks will take on the Indiana Pacers in an NBA matchup on Wednesday. This prediction is based on 10,000 simulations of the game.
- When Will I Die? Life2vec Death Calculator – 79% Accurate, But Beware of Scamon May 6, 2024 at 4:26 am
The Life2vec life expectancy calculator achieves 78.8% accuracy, but creators warn against copycat versions that hijack sensitive information.
- Breakthrough Algorithm Enhances Climate Models, Promising More Accurate Predictions of Future Climate Changeon May 4, 2024 at 6:53 pm
Earth System Models – complex computer models which describe Earth processes and how they interact – are critical for predicting future climate change. By simulating the response of our land, oceans, ...
- New computer algorithm supercharges climate models and could lead to better predictions of future climate changeon May 4, 2024 at 11:08 am
A study describes a new computer algorithm which can be applied to Earth System Models to drastically reduce the time needed to prepare these in order to make accurate predictions of future climate ...
- Wolves vs. Nuggets Game 1 prediction: NBA odds, picks, props and Bet365 bonus code for Sundayon May 4, 2024 at 3:15 am
The Minnesota Timberwolves will square off with the Denver Nuggets in an NBA matchup on Saturday. This prediction features our best bet of the game.
via Bing News