a2

> m1 = lm(happy_o ~ 1 + drugcond + emocond, 
        data = h_dat) # Model 1 with main effects only

> m2 = lm(happy_o ~ 1 + drugcond + emocond + 
        drugcond:emocond, data = h_dat) # Model with main effects and interaction

> summary(m2) # Summary of model 2 (with same p-value as original ANOVA for the interaction)

Call:
lm(formula = happy_o ~ 1 + drugcond + emocond + drugcond:emocond, 
    data = h_dat)

Residuals:
     Min       1Q   Median       3Q      Max 
-2.66667 -0.80208  0.04545  0.35714  3.04545 

Coefficients:
                 Estimate Std. Error t value Pr(>|t|)    
(Intercept)        1.9545     0.2318   8.434 6.23e-12 ***
drugcond          -0.3117     0.3716  -0.839  0.40480    
emocond            0.9830     0.3572   2.752  0.00772 ** 
drugcond:emocond   1.0409     0.5392   1.930  0.05806 .  
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 1.087 on 63 degrees of freedom
  (49 observations deleted due to missingness)
Multiple R-squared:  0.3513,	Adjusted R-squared:  0.3204 
F-statistic: 11.37 on 3 and 63 DF,  p-value: 4.693e-06

> anova(m1, m2) # A comparison of model 1 and model 2 to calculate the F statistic, which is the same as the original ANOVA

Analysis of Variance Table

Model 1: happy_o ~ 1 + drugcond + emocond
Model 2: happy_o ~ 1 + drugcond + emocond + drugcond:emocond
  Res.Df    RSS Df Sum of Sq      F  Pr(>F)  
1     64 78.843                              
2     63 74.440  1    4.4031 3.7264 0.05806 .
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1