Andreas Bergh is associate professor in Economics at Lund university and fellow at the Research Institute of Industrial Economics in Stockholm.

His research concerns the welfare state, institutions, development, globalization, trust and social norms.

He has published in journals such as European Economic Review, World Development, European Sociological Review and Public Choice. He is the author of 'Sweden and the revival of the capitalist welfare state" (Edward Elgar, 2014).

Google Scholar
Ny hem
« Världsförbättrare, kommersialism och signalering | Main | Kvinnor och barn först? Sällan! »
tisdag
apr102012

Varför visualisera data?

Jag brukar säga åt uppsatsstudenter att visualisera data med scatterplots innan de börjar köra stata eller SPSS. Tack vare Richard Öhrvall har jag numera ett dunderargument för detta, hämtat från en klassisk artikel av Anscombe, vari presenteras 4*11 datapunkter med den intressanta egenskapen att medelvärde, standardavvikelse är identiska för samtliga fyra datamängdet – och en OLS-regression ger i samtliga fyra fall  sambandet y=3+0,5x (p = 0,03, R2 = 0,67).

Den som visualiserar data ser dock snabbt att regressionen inte ger riktigt hela bilden:

image

Tack Richard!

PrintView Printer Friendly Version

EmailEmail Article to Friend

References (2)

References allow you to track sources for this article, as well as articles that were written in response to this article.
  • Response
    I am writing a research paper and collecting information on this topic. Your post is one of the better that I have read. Thank you for putting this information into one location.
  • Response
    Response: sohairextensions
    I mean, they are great apps and I am sure that many of us will download at least a few of them, but it is not like they’re topping the charts or anything.

Reader Comments (1)

At one time, cipher would admission acclimatized the difference. Fortunately it is no best so.

PostPost a New Comment

Enter your information below to add a new comment.

My response is on my own website »
Author Email (optional):
Author URL (optional):
Post:
 
All HTML will be escaped. Hyperlinks will be created for URLs automatically.