Hypothesis testing based on goodness-of-fit in the moving average time series model

Small sample properties of t-tests are compared with those of tests based on relative goodness- of-fit in the context of the first order moving average time series model. Monte Carlo experiments reported in the paper suggest that the actual size of these t-tests greatly exceeds theoretical large sample significance levels, while conformity of goodness-of-fit statistics to the appropriate chi-square or F-distributions is much closer. The evidence presented suggests that practitioners are well advised to employ goodness-of-fit tests as a check on results of t-tests particularly when the latter indicate ‘significance’.     

Breastfeeding versus infant formula: the Kenyan case

An Infant Feeding Practices Study (IFPS) in 1982 in Kenya, which included a cross-sectional survey of a weighted sample of 980 low and middle income Nairobi mothers who had given birth in the previous 18 months, found that most women breastfeed their infants for long periods, but many introduce alternate feeding, especially infant formula, in the 1st 4 months (86 and 50% of the infants were breastfed at 6 and 15 months respectively, but 50% of the 2 month-olds and 63% of the 4 month-olds were receiving substitutes, mostly formula). This is done largely out of the belief that infant formula is an additional health benefit. A workshop to discuss the findings of the IFPS and other available data, and to make policy recommendations urged the adoption of a policy of protection, support and promotion of breastfeeding. Since breastfeeding is already widely prevalent in Kenya, protection of breastfeeding should receive the 1st priority in policy related to infant feeding. Attention should be directed at at least 2 influences which help undermine breastfeeding: widespread availability and promotion of breast milk substitutes. Support for breastfeeding is viewed as the 2nd policy priority. Situations where support can play a helpful role are, women's paid employment outside the home, hospital practices, maternal morbidity, and difficulties in breastfeeding. Since promotion is the least cost effective of the 3 options, and most Kenyan women are already motivated to breastfeed, this should be the last priority. Promotion includes reeduction of mothers to make them better aware of the benefits of breastfeeding. The workshop recommended the dissemination of appropriate information, consisting of standarized messages based on clearcut guidelines, using mass media techniques.