jpcarrascal · November 18, 2019 16:26 · Nov 18, 2019
diff --git a/survey_sample_size.R b/survey_sample_size.R
@@ -0,0 +1,26 @@
+# Simple function to determine optimum sample size for a survey.
+# A lot of websites provide online calculators, but here is the code so you can do it yourself in R.
+# Source:
+#     Krejcie, Robert V., and Daryle W. Morgan. "Determining sample size for research activities."
+#     Educational and psychological measurement 30.3 (1970): 607-610.
+#     https://journals.sagepub.com/doi/abs/10.1177/001316447003000308?journalCode=epma
+#     Downloadable PDF: https://home.kku.ac.th/sompong/guest_speaker/KrejcieandMorgan_article.pdf
+#
+# The paper provides a table with chi-squared distribution values for 1 degree of freedom.
+# R function qchisq() generates the right value from a given confidence level, so the table is not needed.
+# Function input parameters:
+#
+# N: population size
+# err: desired margin of error. E.g. for 5%,  err = 0.05
+# cl: confidence level. E.g. for 95%, cl = 0.95
+# P = response distribution (population proportion in the source). Often 50% is used as it gives larger sample size.
+#
+# Written by JP Carrascal: www.jpcarrascal.com, www.github.com/jpcarrascal
+#
+
+sample_size <- function(N, err, cl, P=0.5)
+{
+  chisqV <- qchisq(cl, df=1)
+  ssize <- ( chisqV*N*P*(1-P) ) / ( err^2*(N-1) + chisqV*P*(1-P) )
+  return ( ssize )
+}