RandomizedBlockDesignEffectSizes function

RandomizedBlockDesignEffectSizes

This function finds the theoretical effect sizes for a four-group randomized block experiments assuming one of four different underlying distributions specified by the type parameter. The design assumes two blocks each comprising a control and treatment group. If required a fixed Blocking effect is added to the mean for Block 2.

RandomizedBlockDesignEffectSizes(
  m1,
  std1,
  m2,
  std2,
  m3,
  std3,
  m4,
  std4,
  BE = 0,
  type = "n"
)

Arguments

• m1: The theoretical mean for the control group in Block 1
• std1: The theoretical variance for the control group in Block 1
• m2: The theoretical mean for the treatment group in Block 1
• std2: The theoretical variance for the treatment group in Block 1
• m3: The theoretical mean for the control group in Block 2
• std3: The theoretical variance for the control group in Block 2
• m4: The theoretical mean for the treatment group in Block 2
• std4: The theoretical variance for the treatment group in Block 2
• BE: A fixed block effect to be added to the Block 2 mean values.
• type: String identifying the distribution, 'n' for normal, 'ln' for lognormal, 'lap' for Laplace, 'g' for Gamma

Returns

dataframe holing the expected unstandardized mean difference effect size, the pooled within group variance, the standardized effect size and the point bi-serial correlation.

Examples

RandomizedBlockDesignEffectSizes(m1=0,std1=1,m2=1,std2=1,m3=0,std3=1,m4=1,
  std4=1,BE = 1,type = 'n')
# ES Var StdES      rPBS
#1  1   1     1 0.4472136
RandomizedBlockDesignEffectSizes(m1=0,std1=1,m2=1,std2=1,m3=0,std3=1,m4=1,
  std4=1,BE = 1,type = 'l')
#        ES      Var     StdES      rPBS
#1 5.266886 82.17791 0.5810004 0.2789675
RandomizedBlockDesignEffectSizes(
  m1=0,std1=1,m2=0.266,std2=1,m3=0,std3=1,m4=0.266,std4=1,BE = 0,type = 'l')
#        ES      Var     StdES       rPBS
#1 0.5024232 6.310995 0.1999957 0.09950162

Author(s)

Barbara Kitchenham and Lech Madeyski