Hi!
I'm conducting a survey-experiment, and I would like to calculate the required sample size, but I'm unsure how to do that.
I will just here provide a breif context
First 50% of alle the respondents get treatment A (an intervention) and the other 50% get no intervention (control). Hereafter the respondents are presented three cases that can either be male or female. Hereafter the respondents are asked to rate the three cases on a scale of 1-3 (dependent variabel). I can thus create 6 observations pr. respondent in terms of their ranking of Case A vs. B, A vs. C, B vs. C (those will be clustered in the regression analysis)...
In sum I'm making an analysis with two levels on the independent variable (male vs. female) and two levels on the moderating variable (intervention or no intervention). The dependent variabel will also be binary comparing the ranking of the cases respectively.
I want my significane level to be 0,05 and power to be 0,8. I don't know the effect size or variance yet, but I expect both be small.
Can Stata help me calculate the sample size I need for this experiment, and if so how? (I have seen some videos on how to calculate sample sizes for e.g., one-way analysis, but I haven't been able to find any examples that fits my concrete case)
Thanks in advance!
/Amalie
I'm conducting a survey-experiment, and I would like to calculate the required sample size, but I'm unsure how to do that.
I will just here provide a breif context
First 50% of alle the respondents get treatment A (an intervention) and the other 50% get no intervention (control). Hereafter the respondents are presented three cases that can either be male or female. Hereafter the respondents are asked to rate the three cases on a scale of 1-3 (dependent variabel). I can thus create 6 observations pr. respondent in terms of their ranking of Case A vs. B, A vs. C, B vs. C (those will be clustered in the regression analysis)...
In sum I'm making an analysis with two levels on the independent variable (male vs. female) and two levels on the moderating variable (intervention or no intervention). The dependent variabel will also be binary comparing the ranking of the cases respectively.
I want my significane level to be 0,05 and power to be 0,8. I don't know the effect size or variance yet, but I expect both be small.
Can Stata help me calculate the sample size I need for this experiment, and if so how? (I have seen some videos on how to calculate sample sizes for e.g., one-way analysis, but I haven't been able to find any examples that fits my concrete case)
Thanks in advance!
/Amalie
