Don’t rely on fancy statistics - Deepstash

deepstash

Beta

Get an account to save ideas & make your own & organize them how you wish.

deepstash

Beta

How to Think Like a Scientist

Don’t rely on fancy statistics

Don’t rely on fancy statistics

They can obscure the structure of evidence.

Remain skeptical of all statistical and mathematical modeling procedures that pre-process evidence while leaving little trace of its original structure.  

Start out close to the data by scrutinizing frequency distributions, means, standard deviations, how variables are actually measured, degree of measurement error, zero-order correlations, and sample composition.

50 SAVES


This is a professional note extracted from an online article.

Read more efficiently

Save what inspires you

Remember anything

IDEA EXTRACTED FROM:

How to Think Like a Scientist

How to Think Like a Scientist

https://www.psychologytoday.com/us/blog/finding-the-next-einstein/201307/how-think-scientist

psychologytoday.com

5

Key Ideas

Pursue what appears to be a paradox

It will force you to reexamine the full body of evidence with new eyes.

Seeking relevant knowledge in unfamiliar disciplines increases the odds of serendipitous insights and allows novel empirical patterns to emerge.

Spot contradictions and novel patterns

Go on cross-disciplinary research expeditions.

By reading and translating the literature in fields outside your own, the full body of evidence surrounding a problem become apparent. 

Focus on data and methods

Ignore the author’s conclusions.

When you are doing cross-disciplinary research what really matters is the structure of the full body of evidence rather than any authors’ particular interpretation of their data in one paper, which is often biased. 

Don’t rely on fancy statistics

They can obscure the structure of evidence.

Remain skeptical of all statistical and mathematical modeling procedures that pre-process evidence while leaving little trace of its original structure.  

Start out close to the data by scrutinizing frequency distributions, means, standard deviations, how variables are actually measured, degree of measurement error, zero-order correlations, and sample composition.

There is no single formula

Be open to have your basic presumptions shattered.

Strategies for solving scientific mysteries:  

  • pin down why perspectives on them differ and what each has to offer
  • try to locate the essential core of available evidence
  • not put much stock in any single study or piece of evidence
  • watch for recurring patterns in the most reliable data
  • think through likely counterarguments
  • and look hard for holes in my evidence and logic.  

SIMILAR ARTICLES & IDEAS:

Statistics Inaccuracies

Most studies that involve statistical research remain largely inaccurate, and a large number of hypotheses use data samples which are inadequate.

Beliefs and Statistics
  • Researchers extract a lot of false certainty from data which is used to study a particular hypothesis, due to their myopic thinking, confirmation bias, and other cognitive assumptions that they aren't even aware of.
  • Many researchers believe in small samples of data as if they stand for the whole of the population, and this can lead to unpredictable consequences.
The Eye Poster Experiment

It points out our irrational bias and behavior towards our surroundings. How people succumb to irrational beliefs was demonstrated in an experiment at a University Kitchen.

It found out that if there was a poster with eyes put up near the kitchen counter, then people were more likely to pay for the food, subconsciously taking those eyes in the poster as someone looking at them.

one more idea

We’re swayed by anecdotes
We’re swayed by anecdotes
Most of us are influenced more powerfully by personal testimony from a single person than by impersonal ratings or outcomes averaged across many people. This is the power of anecdote to dull our criti...
We’re overconfident

We overestimate our comprehension of the science. 

Part of the problem seems to be that we infer our understanding of scientific text based on how well we have comprehended the language used. This “fluency bias” can also apply to science lectures when it is delivered by an engaging speaker.

We’re seduced by graphs
It doesn’t take a lot to dazzle the average newspaper or magazine reader using the superficial props of science, be that formulas, graphics or jargon. 

One study found that participants were far more likely to support new evidence when it had a graphic visualisation of the correlational evidence than if they had read the same evidence without a graphic.

one more idea

The Way Therapy Works
There is growing research on how therapy actually works. Psychological communication, dialogue, and intervention can work even better than pills.
This seems eve...
Therapy Techniques
  • Some therapists are just there to listen and provide a backdrop.
  • Even the silence that they exhibit seems to kindle the patients into divulging more of their most uncomfortable truths.
  • Others keep the sequence of assignments and tests lined up, never pausing.
  • Therapists play varied roles to get some valuable information out of the patient and make him better.
Therapy That Works

No particular form of therapy is proven to be better or more effective than others.

Different people prefer or respond to different forms of therapy.

5 more ideas

Traffic jams 

Most traffic jams are unnecessary. Local transport engineers manage to achieve local improvements, but after a while the flows rearrange, and the same traffic jams appear elsewhere.

Ma...

Math approaches to traffic

  • All drivers need to be on the same navigation system. Cars can only be efficiently rerouted if instructions come from the same hub. 
  • Many urban roads are too narrow. Traffic-flow models can indicate where parking spots should be turned into lanes.
  • Green lanes incentive. For cities that want to increase electric car use, special lanes should be created for electric cars.
  • Digital twins. Digital modeling can create an entire “twin” of existing roadways to assist transport engineers.

Thinking is not IQ

We often make the mistake of thinking that people with high IQs think better. But it's not true. That's not the type of knowledge or brainpower that makes you better at life, happier, or more succe...

Principles for seeking wisdom
  • Go to bed smarter than when you woke up.
  • "I’m not smart enough to figure everything out myself, so I want to master the best of what other people have already figured out."
If you want to think better...
  • Become better at probing other people’s thinking. Ask questions. Simple ones are better. “Why” is the best.
  • Slow down. Make sure you give yourself time to think.
  • Probe yourself. Try and understand if you’re talking about something you really know something about or if you’re just regurgitating something you heard.

2 more ideas

Creating quantitative models
Creating quantitative models

Most of the psychological theories are verbal, but words can be imprecise. If "cooperation is intuitive", it needs to state when. And what does "intuitive" mean?

In order to solve this, compu...

The Sims computer simulation

These models represent collections of individual people described by computer algorithms that capture a specific set of traits, such as a tendency to cooperate or not.

  • You can give them new personalities to see how they would behave.
  • You can observe social processes in action.
  • You can observe time scales, from seconds to generations.
  • You can watch the spread of certain behaviors throughout a population and you can see how certain behaviors influence other behaviors.

The patterns that emerge can tell you things about large-scale social interaction that lab experiments and real people never could.

The human instinct to cooperate

There seems to be evolutionary logic to the human ability to cooperate but adjust if necessary. To trust, but verify. 

We generally collaborate with other people because it benefits us. Our rational minds let us work out when we might occasionally gain by acting selfishly instead.

4 more ideas

Systematic approach
Most people jump straight from finding a problem to attempting to solve it.

Having a systematic approach to how you deal with problems, as opposed to just going by gut and feelings, ca...

Study the problem first

Detectives and investigators use the process. They ask both obvious and unthinkable questions.

Get close and collect information about how the problem is manifesting.  Understand where the problem does and doesn’t happen, when the problem started, and how often the problem occurs to generate critical insight for the problem-solving effort.

Question for great answers
  • Don’t look for solutions immediately; Keep redefining the problem until you arrive at the root cause.
  • Don’t try to guess the solution; try to understand how the obstacles, or challenges manifest first.
  • Gather data to analyze all potential root causes.
  • Consider all options, regardless of how irrelevant they currently appear.
  • Find a way to connect the dots. Make better analogies. One good analogy is worth three hours of discussion.

6 more ideas

Early History

The connection between genius and possible insanity was first documented in 1891 in the Italian physicians’ book The Man Of Genius.

In 1869, this was taken up by the cousin of Charles Darwi...

Genius and Heredity

In a 1904 study by English physician Havelock Ellis, a list was made of 1030 individuals through extensive research, examining thoroughly the intellectual distinction people had by the various factors like heredity, general health, and social class.


These works established that genius minds are often hereditary.

Genetic Studies Of Genius

A body of work of Stanford psychologist Lewis M. Terman, was an in-depth multi-decade study of gifted individuals, and an attempt to improve the measurement of genius and its association with the degradation of mental stability. This also included an enhanced version of the French IQ (Intelligence Quotient) test.

10 more ideas

Think like Sherlock Holmes

“What Sherlock Holmes offers isn’t just a way of solving a crime. It is an entire way of thinking."

"Holmes provides... an education in improving our faculty of mindful thought...

Engagement
As children, we are remarkably aware to the world around us. This attention wanes over time as we allow more pressing responsibilities to attend to and demands on our minds to address. And as the demands on our attention increase so, too, does our actual attention decrease.

 As it does so, we become less and less able to know or notice our own thought habits and more and more allow our minds to dictate our judgments and decisions, instead of the other way around.

Pitfalls of the Untrained Brain

Daniel Kahneman believes there are two systems for organizing and filtering knowledge: 

  • System one is real-time. This system makes judgments and decisions before our mental apparatus can consciously catch up. 
  • System two, on the other hand, is a slow process of thinking based on critical examination of evidence. Konnikova refers to these as System Watson and System Holmes.

To move from a System Watson- to a System Holmes-governed thinking takes mindfulness plus motivation.

6 more ideas