Short note on the Empirical research -Econometrics and Experimental economics

In applied economics, input-output models employing linear programming methods are quite common. Large amounts of data are run through computer programs to analyse the impact of certain policies; IMPLAN is one well-known example. Experimental economics has promoted the use of scientifically controlled experiments. This has reduced the long-noted distinction of economics from natural sciences because it allows direct tests of what were previously taken as axioms. In some cases these have found that the axioms are not entirely correct; for example, the ultimatum game has revealed that people reject unequal offers.

Jul 4, 2022 - 15:54
 0

Economic theories are frequently tested empirically, largely through the use of econometrics using economic data.

The controlled experiments common to the physical sciences are difficult and uncommon in economics, and instead, broad data is observationally studied; this type of testing is typically regarded as less rigorous than controlled experimentation, and the conclusions are typically more tentative.

However, the field of experimental economics is growing, and increasing use is being made of natural experiments. Statistical methods such as regression analysis are common. Practitioners use such methods to estimate the size, economic significance, and statistical significance ("signal strength") of the hypothesized relation(s) and to adjust for noise from other variables.

By such means, a hypothesis may gain acceptance, although in a probabilistic, rather than certain, sense. Acceptance is dependent upon the falsifiable hypothesis surviving tests.

The use of commonly accepted methods need not produce a final conclusion or even a consensus on a particular question, given different tests, data sets, and prior beliefs.

Criticisms based on professional standards and non-replicability of results serve as further checks against bias, errors, and over-generalization, although much economic research has been accused of being non-replicable, and prestigious journals have been accused of not facilitating replication through the provision of the code and data.

Like theories, uses of test statistics are themselves open to critical analysis, although critical commentary on papers in economics in prestigious journals such as the American Economic Review has declined precipitously in the past 40 years. This has been attributed to journals' incentives to maximize citations in order to rank higher on the Social Science Citation Index (SSCI).

In applied economics, input-output models employing linear programming methods are quite common. Large amounts of data are run through computer programs to analyse the impact of certain policies; IMPLAN is one well-known example. Experimental economics has promoted the use of scientifically controlled experiments.

This has reduced the long-noted distinction of economics from natural sciences because it allows direct tests of what were previously taken as axioms. In some cases these have found that the axioms are not entirely correct; for example, the ultimatum game has revealed that people reject unequal offers.

In behavioural economics, psychologist Daniel Kahneman won the Nobel Prize in economics in 2002 for his and Amos Tversky's empirical discovery of several cognitive biases and heuristics.

Similar empirical testing occurs in neuroeconomics. Another example is the assumption of narrowly selfish preferences versus a model that tests for selfish, altruistic, and cooperative preferences. These techniques have led some to argue that economics is a "genuine science".

What's Your Reaction?

like

dislike

love

funny

angry

sad

wow