Posts Tagged ‘statistics article’

20% error rate found in study of published genetics research papers

September 13, 2016

In a recent study 20% of genetics research papers using Microsoft Excel have been found to have data errors due to improper data entry.  It turns out that gene names such as SEPT2 and MARCH1 (these are actual gene name abbreviations used by scientists) get converted to dates by Excel and then result in rejected data.  The problem is resolvable if the scientists would make sure the data cells were formatted as “Text,” prior to entering the data.

For the full article in the Washington Post click on the link below.

https://www.washingtonpost.com/news/wonk/wp/2016/08/26/an-alarming-number-of-scientific-papers-contain-excel-errors/

Advertisements

Deficit v. Debt – knowing the diference

July 21, 2016
In simple terms, a budget deficit is the difference between what the federal government spends (called outlays) and what it takes in (called revenue or receipts). The national debt, also known as the public debt, is the result of the federal government borrowing money to cover years and years of budget deficits.

What’s the difference between the U.S. deficit and the national debt …

money.howstuffworks.com/difference-between-u-s-deficitnationaldebt-.htm

Early Bedtime May Fight Fat

July 19, 2016

Scientists studying sleep time of preschoolers and obesity in teenages have observed some interesting correlations, but they are not conclusively cause and effect.  As reported in the New York Times, July 19, 2016.

Early Bedtime May Fight Fat NYT 7_19_16

‘Residual Seasonality,’ Fixing the Data or Fixing the Results?

July 3, 2016

Adjusting the data? How much adjustment is good?  How do you know when the adjustments introduce distortions?   When are you fixing the data? And when are you fixing the results?  To know the answers to those question take a lot of experience and objectivity.

In an article in The Wall Street Journal ( July 1, 2016), by Jo Craven McGinty, titled, “Seasonal Fluctuations Vex Statisticians in Quest to Capture Economy’s Growth, Stripping out normal variation challenges government as it seeks to give accurate GDP figure,” Ms. McGinty addresses a current example of how data is handled.

” “We expect a certain amount of randomness in any economic data,” said Brent Moulton, who oversees GDP and other national economic statistics for the Bureau of Economic Analysis.”

“When adjusted numbers continue to exhibit the influences of seasonal effects, statisticians refer to it as residual seasonality.” That is something new.

” “Small patterns of seasonality at the individual granular level, which don’t appear to be that significant, can add up over time, over quarter and over various components to substantial residual seasonality,” said Mr. Rudebusch, who found that adjusting the GDP a second time seems to erase the effect.”

As I said, are we fixing the data, or are we fixing the results?

How Changing the Expectations Changes the Outcome

June 19, 2016

Self fulfilling prophesies can make someone his own worst enemy.  Expecting to fail can become the formula for failure.  The question is how to get students who have low expectations of themselves, and who doubt their ability to succeed, to reset their mind-set.  Some new research sheds some valuable light on this question.

A Small Fix in Mind-Set Can Keep Students in School – WSJ

The Truth Behind the ‘Summer Rally’

June 6, 2016

Statistics students should read The Wall Street Journal article about the myth of the summer stock market rally (WSJ, June 6, 2016).  By examining the data the author shows that the summer historically had less rallies than other times of the year, and yet the name, the concept and the belief persists.  The author suggests that the name might go back to the Depression when in the summer of 1932 the Dow Jones Industrial Average gained 76.5% from the low close of June to the high close of August.

Sometimes we see what we expect to see, and no one is immune from the perception bias, but being aware of the tendency makes you better prepared to deal with it in an intelligent manner.

For the full article, click here: The Market’s Summer-Rally Myth – WSJ

MBAs Need Data Comprehension and Communication With Geeks

May 5, 2016

The Wharton School has come to realize that in a data filled world, understanding how data can drive good decision making is key to tomorrow’s (and today’s) executives.  Case studies, which have long dominated MBA education, is no match for a deep understanding of analytics.  Being able to communicate with the data handlers and being knowledgeable about what one can expect from them in now a key skill.  The Wharton School of the University of Pennsylvania, in now pushing analytics in their MBA programs.  See the attached article.

Wharton M.B.A

Using Big Data to Predict Worker Illness and Pregnancies

February 29, 2016

Not a typographical error!  Companies who hire outside consultants are able to get data about their workforce that borders on a serious intrusion of privacy.  Click below for the whole WSJ article, but just a few quotes might give the sense of what I am talking about.

Bosses Tap Outside Firms to Predict Which Workers Might Get Sick – WSJ

“Trying to stem rising health-care costs, some companies, including retailer Wal-Mart Stores Inc., are paying firms like Castlight Healthcare Inc. to collect and crunch employee data to identify, for example, which workers are at risk for diabetes, and target them with personalized messages nudging them toward a doctor or services such as weight-loss programs.”

“To determine which employees might soon get pregnant, Castlight recently launched a new product that scans insurance claims to find women who have stopped filling birth-control prescriptions, as well as women who have made fertility-related searches on Castlight’s health app.”

“Privacy advocates have raised concerns about such practices. Employees generally have a choice in whether to participate in the programs. The services are new enough that relatively few workers are aware of them.”

“Federal health-privacy laws generally bar employers from viewing workers’ personal health information, though self-insured employers have more leeway, says Careen Martin, a health-care and cybersecurity lawyer at Nilan Johnson Lewis PA. Instead, employers contract with wellness firms who have access to workers’ health data.”

The “proxy,” an easier way to count.

February 10, 2015

The number of new car registrations can be used as a proxy for new car sales in cases where the new car sales numbers are not available, or the new car registration statistics are easier or cheaper to get.

In an article about the European car sales, the Wall Street Journal reports, “Last year, new passenger car registrations, a proxy for new car sales, rose 5.7% to 12.6 million, according to figures released by the European Automobile Manufacturers’ Association, or ACEA.”

Why is the number of new car registrations a good proxy for new car sales numbers? It is based on the assumption that people who buy new cars will register them and use them right away, so it is reasonable to assume a one to one relationship, with a very high degree of accuracy.

Another example of a proxy would be using the sales of various commodities as a measure of the strength of an economy, i.e., the sale of certain luxury goods. Some proxies are better at mimicking the underlying statistic than others.

“At the current rate…” and other assumptions

February 6, 2015

In order to make any predictions in any area of study, one must make assumptions about the data, and what is likely to affect it going forward. That is why statistical studies often make use of such statements as:

“At the current rate…”

“If things continue as in the past…”

“Based on what we know now…”

“It is reasonable to assume…”

“If history is a guide…”

“If things don’t change…”

But things do change, and that is what makes predicting the future so difficult, and so vulnerable to known and unknown biases. While these caveats are unavoidable, and need to be stated, they require the consumer of the statistics to have a reasonable amount skepticism and a large amount knowledge.

A quote in The Great Race by Levi Tillemann states that “The available supply of gasoline, as is well know, is quite limited and it behooves the farseeing men of the motor car industry to look for likely substitutes.” This quote is attributed to Thomas J. Fay, in 1905, in a magazine call Horseless Age.