(This article was first published on

Should statistical teachers continue to teach z-tests?**OutLie..R**, and kindly contributed to R-bloggers)vote:

**, or**

*save z-test*

*stop z-test*Looking at textbooks, articles and general research I cannot remember the last time I saw someone use a z-test in a study. I have seen many a t-test, ANOVA, chi^2, and others, but rarely a z-test.

The z-test has the burden of needing the population mean and population standard deviation. In the world of statistics getting a true population is like finding the holy grail, the stuff legends are made of, like the perfect dataset.

I have some arguments for and against teaching z-test, please add your comments and arguments for or against, or vote to

**, or**

*save z-test*

*stop z-test*

**Save the Z-Test**This is how it has been done for decades, why change a good thing

When there is a dataset with a population, a z-test is the best tool

Get to look up cool numbers in an appendix of your favorite stats book (ah memories)

Z-tests are a stepping stone to t-tests and hypothesis testing, foundational to the rest of statistics

Great problems for textbooks

**Stop the Z-Test**This is how it has been done for decades, it is due for a change

How often does a researcher ever really get a true population?

Computer should be able to do all of the looking up

Z-test can be skipped moving straight to t-tests

When was the last time you actually did a z-test with a real dataset?

Please add additional arguments or just vote to

**, or**

*save z-test***it. A tally will be added up and presented next week.**

*stop z-test*To

**leave a comment**for the author, please follow the link and comment on his blog:**OutLie..R**.R-bloggers.com offers

**daily e-mail updates**about R news and tutorials on topics such as: visualization (ggplot2, Boxplots, maps, animation), programming (RStudio, Sweave, LaTeX, SQL, Eclipse, git, hadoop, Web Scraping) statistics (regression, PCA, time series, trading) and more...