The Odds, Continually Updated

TheOdds, Continually Updated

TheOdds, Continually Updated

NewYork Times published the article, TheOdds, Continually Updatedby Faye Flam on September 29, 2014, which sought to distinguishbetween Bayesian and frequentist statistics. It covers the origin ofboth Bayesian and frequentists statistics by including severalstatistical applications from Bayesian theory. The article definesBayesian statistics as a &quotset of mathematical rules for usingnew data to continuously update beliefs or existing knowledge&quot(Flam,2014).Thomas Bayes invented this method in the 18thcentury. Today, Bayesian statistics have gained usefulness given themodern computing power.

Thistheory has proved useful in solving complex mysteries. For example, acoast guard applied it in 2013 to locate a missing angler (Flam,2014).Bayesian statistics are present in virtually all scientific fieldstoday. This is because they are giving light into problems thatseemed impossible two decades ago. However, there has been a ragingdebate concerning the reliability of results obtained from Bayesianstatistics.

Themodern statistical controversies revolve around the conversion ofdata into knowledge, evidence, and forecasts by scientists. Somescientific fields have been cited as being dormant in inferringpredictions using statistical tools. Despite opposing points of viewabout Bayesian theory, some scientists believe that it can be used togenerate credible conclusions on scientific phenomena if they arecrosschecked with the classical approach (frequentist statistics)(Flam,2014).

Thearticle accentuates the distinctions between Bayesian approach andfrequentist approach. First, frequentist approach applies probabilityto data while Bayesian technique heads straight to the probability ofthe hypothesis by taking into account the data and other relevantfacts. According to the article, frequentist statistics gainedpopularity in the 20thcentury and a careful consideration of previous studies that applieda similar technique cast doubts on the validity of results accordingto Professor Andrew Gelman (Flam,2014).

Theprofessor re-evaluated a study on voting preferences among single,ovulating women in the U.S 2012 election and the statisticalsignificance of the study ceased to hold (Flam,2014).According to him, Bayesian approach can be used to replacefrequentist techniques and to flag false results. Today, Bayesianthought combined with advanced computing capabilities haverevolutionized a range of fields such as astronomy and cancerresearch. However, the use of Bayesian techniques requires priorinformation, which is not always the case.

Despitethe contribution of Bayesian statistics in scientific research today,some people feel that the ideal way to solve the problem ofmisleading findings is replacing flawed frequentist techniques withgood ones. Uri Simonsohn supported this argument when he published apaper addressing statistical mischief in his field of specialty(psychology (Flam,2014).He concluded that misunderstanding or misuse of a single system inBayesian statistics would nullify the findings of research.Nonetheless, Bayesian technique has been able to prove its power withthe modern computing speed because it can be used to infer theseemingly impossible conclusions.

Inlight of modern computing capabilities and statistical applications,financial analysis jobs entail the evaluation of a business entityfrom a range of perspectives to comprehend its financial capacity anddetermine the best way to strengthen its operations. A financialanalyst explores many aspects of the business such as stability,profitability, liquidity, and solvency. Financial analysts usespreadsheets and statistical software packages to analyze financialdata to indicate and predict forecasts. They can use a range ofBayesian techniques in conjunction with statistical software packagesto conduct their analysis, prepare reports and recommend the rightactions relating to a company`s finances.


Flam,F. (2014). . Retrieved October 02, 2016,from