# [R] Trouble with line of best fit

Joshua Wiley jwiley.psych at gmail.com
Mon Jul 25 21:45:18 CEST 2011

```On Jul 25, 2011, at 12:31, Daniel Malter <daniel at umd.edu> wrote:

> Hi,
>
> I hope this is for private purposes. Otherwise, I may cite David Winsemius:
> "The advancement of science would be safer if you knew what you were doing."

Hmm, even if it were not private, the science of FPS video games is a dangerous place---I would hazard the guess it would survive the misspecification.

>
> First, your regression command is inverted. You ought to regress SoloKills
> on range, not vice versa.
>
> abline(lm(graph~range)) #does the trick
>
> Second, given the figure, a linear specification is obviously a
> misspecification of your model, unless you account for autocorrelation.
>
> pacf(reg\$res,plot=T)
>
> HTH,
> Daniel
>
>
>
>
> DimmestLemming wrote:
>>
>> I don't usually do much with graphs in R, and this is my first time adding
>> a line of best fit. Hopefully this is an easy problem to solve.
>>
>> I'm looking at a variable called soloKills along the range 5:28. Here are
>> all my commands, in script form:
>>
>> range=5:28
>> graph=soloKills
>> title="Solo kill/death data"
>> xlabel="Number of deaths/1 game"
>> ylabel="Mean number of kills/1 game"     #No problems with the scatterplot
>>
>> plot(x=range, y=graph, main=title, xlab=xlabel, ylab=ylabel, ylim=c(0,20))
>>
>> abline(lm(range~graph))
>>
>> I checked several websites, the abline(lm(/x-variable/~/y-variable/))
>> format *should* work. But here is what happens:
>>
>> http://r.789695.n4.nabble.com/file/n3693567/Regression_problem.png
>>
>> The line is obviously far too steep. I can guarantee there are no outliers
>> in soloKills to throw it off:
>>
>>> soloKills
>> [1]  9.040472 10.184595 11.201935 12.130823 13.583477 14.098845 14.489703
>> [8] 15.329752 15.562500 15.884757 16.239704 16.513289 16.383912 16.547543
>> [15] 16.823374 17.051370 17.027644 17.300562 17.641723 17.702673 18.436170
>> [22] 18.783562 19.274419 21.373832
>>
>> Can anyone help me fix the regression line? Thanks!
>>
>
> --
> View this message in context: http://r.789695.n4.nabble.com/Trouble-with-line-of-best-fit-tp3693567p3693745.html
> Sent from the R help mailing list archive at Nabble.com.
>
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.

```

More information about the R-help mailing list