Analysis

Sample size

n = 56

Descriptive statistics split by condition

Control condition (prime code = 0)

##    vars  n mean   sd min max range   se
## X1    1 28 5.48 1.45   3   8     5 0.27

Aggression condition (prime code = 1)

##    vars  n mean   sd min max range   se
## X1    1 28 5.43 1.86   2   9     7 0.35

Independent samples t-test with mean aggression rating as DV and prime condition as IV

Gives ordinary asymptotic p-value.

## 
##  Welch Two Sample t-test
## 
## data:  dv by prime
## t = 0.12023, df = 50.967, p-value = 0.9048
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -0.8409843  0.9481271
## sample estimates:
## mean in group 0 mean in group 1 
##        5.482143        5.428571

Cohen’s d effect size

## 
## Cohen's d
## 
## d estimate: 0.03213234 (negligible)
## 95 percent confidence interval:
##        inf        sup 
## -0.5135632  0.5778279

Exact two-tailed p-value and associated 99%CI for the p-value from a Monte-Carlo permutation (randomization) test

Apart from precision, permutation test sidesteps conditioning on any distributional assumptions.

## 
##  Exact Permutation Test Estimated by Monte Carlo
## 
## data:  GROUP 1 and GROUP 2
## p-value = 0.9067
## alternative hypothesis: true mean GROUP 1 - mean GROUP 2 is  0
## sample estimates:
## mean GROUP 1 - mean GROUP 2 
##                  0.05357143 
## 
## p-value estimated from 1e+05 Monte Carlo replications
## 99 percent confidence interval on p-value:
##  0.9042862 0.9090350

Bayesian analysis

Compute Bayes Factor for independent t-test of a one-tailed hypothesis

For the purpose of quantifying the available evidence. The Bayes factor is the relative evidence in the data. The evidence in the data favors one hypothesis, relative to another, exactly to the degree that the hypothesis predicts the observed data better than the other (answering the question how many times are the data more likely under one hypothesis as oposed to the other. BF10 = evidence in favor of Ha, BF01 = evidence in favor of H0. More info here. Using a prior width of 1/2. Testing a directional, one-tailed hypothesis that aggressive priming leads to a higher rating of aggression.

## [1] "BF01 = 3.07"

Bayesian sequential analysis

Plotted evolving empirical support (relative likelihood) in favor of Ha or H0 as more and more data come in. More info here.

## NULL