0

I've run the lm code below, with one DV and three IVs, and I'm not sure how to interpret the output. What does (Intercept) refer to, and what is that row telling me? What are the other rows telling me? I'm mainly interested in understanding the p-values.

Thank you!

Call:
lm(formula = NL_EN_M ~ A_S_S + A_P_S + A_A_S, data = IV)

Residuals:
     Min       1Q   Median       3Q      Max 
-1.12516 -0.22312  0.00767  0.23596  1.06969 

Coefficients:
            Estimate Std. Error t value Pr(>|t|)    
(Intercept)  2.79551    0.36485   7.662  6.6e-09 ***
A_S_S        0.03037    0.10404   0.292    0.772    
A_P_S       -0.01776    0.12650  -0.140    0.889    
A_A_S       -0.11809    0.10122  -1.167    0.251    
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.5771 on 34 degrees of freedom
Elias Shakkour
  • 11
  • 2
  • It would be easier to interpret (and therefore help), if you could edit your question and put dput(IV) somewhere within. – hd1 Jan 13 '21 at 01:51

1 Answers1

0

How many levels are there for each IV? It is hard to interpret this without fully understanding the structure of your data.

I will still try even though I don't know the structure of your data. If your IVs are categorical, (Intercept) will be the first level of the factor. If your IVs are continuous/numerical, (Intercept) will be the expected (mean) value of the DV when the IV is zero (if that is possible). Modelling your data as DV ~ IV1 + IV2 + IV3 treats the three independent variables as independent from one another and solely interprets the main effects without allowing the slopes to vary (and looking for interactions). Here each row is showing how much the value for that IV varies from the intercept. However, they do not vary significantly from one another so you fail to reject the null hypothesis.

(anyone else, feel free to correct me if I made mistakes here)

darrenmk
  • 25
  • 4
  • Thank you! Each IV has 11 levels (a number from 0-10), so the levels are continuous/numerical, I think. The DV is a nativelikeness score calculated based on performance on tasks measuring participants' degree of native(like) proficiency in English. The three IVs come from a questionnaire asking about socioaffective factors. Each part of the questionnaire was quantified on a scale of 0 to 10. I want to know whether any of the IVs correlated with nativelikeness, i.e. whether any of them can explain why subjects got the nativelikeness scores they did. Let me know if you have any other questions! – Elias Shakkour Jan 13 '21 at 21:34
  • Okay, so it looks like the average score on nativelikeness is around 2.79, which is the intercept, and none of the IVs significantly predict a higher/lower score. – darrenmk Jan 14 '21 at 21:08