Abstract
Data from a Brazilian Inga/maize/bean alleycrop experiment are used to illustrate patterns of variation between and within crop rows and their possible effects in the determination of a sampling strategy. Three methods for the determination of sample sizes in agroforestry experiments are compared: the combined plant technique, the formula of Snedecor and Cochran and variance component estimation. Results show that variability in the edge rows was generally greater than variability in the inner rows and suggest three sampling strata – one for each of the two edge rows and the third for the inner rows. For all three sampling methods a sample size greater than ten plants per stratum per block gave little extra precision. Increasing the number of blocks improves precision and may permit a smaller sample size per row to achieve the same precision. The comparison of different methods of sample size determination shows that variance component estimation is the most flexible and efficient approach.
Similar content being viewed by others
References
Cochran WG (1977) Sampling Techniques, 3rd Edition, London, Wiley, 428 pp
Langton SD and Riley J (1987) Implications of statistical analysis of initial agroforestry experiments. Agroforestry Systems 9: 211-232
Palada MC and Ezeribe AC (1988) An agronomic evaluation of farmer-managed alley cropping trials in Southwestern Nigeria. Paper presented at the National Farming Systems Research Workshop, National FSR Network, Federal Republic of Nigeria. University of Jos. May 10-13, 1988, 24 pp
The Genstat Committee (1993) Genstat 5 Release 3 Reference Manual. Oxford University Press
Poschen P (1985) An evaluation of the Caacia albida-based agroforestry practices in the Hararghe highlands of eastern Ethiopia. Agroforestry Systems 4: 129-143
Rao MR and Coe (1991) Measuring crop yields in on-farm agroforestry studies. Agroforestry Systems 15: 275-289
Rao CS and Prasad ASR (1991) Optimum plot size for estimating yield of blackgram. Indian Journal of Agricultural Science 61: 574-578
Reddy MN and Chetty CKR (1985) Experimental plot size and shape based on data from a uniformity trial with dryland pigeonpea. Indian Journal of Agricultural Science 55: 538-543
Riley J and Smyth S (1993) A study of alley-cropping data from Northern Brazil I. Distributional properties. Agroforestry Systems 22: 241-258
Snedecor GW and Cochran WG (1989) Statistical Methods (eighth edition). Iowa State University Press, Ames
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Oyejola*, B.A., Riley**, J. & Bolton, S. A study of alley-cropping data from Northern Brazil. II. A comparison of methods to estimate sample size. Agroforestry Systems 41, 167–179 (1998). https://doi.org/10.1023/A:1006036914971
Issue Date:
DOI: https://doi.org/10.1023/A:1006036914971