Presenting Regression Analyses in R: Part 2

Correlation analyses

Correlation heat map

Grid of heat maps

Summary statistics

• Can create easily formatted summary stats tables in code and add effect sizes
• Can use any effect size formula of interest

Regression summaries

Linear Models

F and t-test

## [1] 0.1455299

## Parameter | Cohen's f2 |       95% CI
## -------------------------------------
## RiskGroup |       0.15 | [0.08, 0.22]

Effect sizes

## [1] 0.1610369

## Parameter         | Cohen's f2 (partial) |       95% CI
## -------------------------------------------------------
## RiskGroup         |                 0.16 | [0.08, 0.26]
## RightAmygdala_V24 |             1.59e-03 | [0.00, 0.02]

## [1] 0.1735988

Semi-partial correlation

## 
## Call:
## lm(formula = V24_MSEL_EL_ae ~ RiskGroup + RightAmygdala_V24 + 
##     TBV_V24, data = brain_data_v24)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -18.4938  -3.3307  -0.4274   3.1913  17.5486 
## 
## Coefficients:
##                     Estimate Std. Error t value Pr(>|t|)    
## (Intercept)        1.337e+01  3.456e+00   3.868 0.000131 ***
## RiskGroupHR-Neg    5.430e+00  8.302e-01   6.540 2.16e-10 ***
## RiskGroupLR-Neg    6.935e+00  9.237e-01   7.508 4.99e-13 ***
## RightAmygdala_V24 -4.399e-03  4.533e-03  -0.970 0.332510    
## TBV_V24            8.746e-06  4.687e-06   1.866 0.062903 .  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 5.415 on 352 degrees of freedom
##   (145 observations deleted due to missingness)
## Multiple R-squared:  0.1485, Adjusted R-squared:  0.1388 
## F-statistic: 15.35 on 4 and 352 DF,  p-value: 1.402e-11

Mixed Models