The information available for estimating the parameters of a mixture of two normal distributions is examined for five diffeient types of sample. The information in these samples is compared through the asymptotic relative efficiencies of the maximum likelihood estimates wing both generalized and total variances. The efficiency of the maximum likelihood estimates is increased substantially if the component of origin of a small proportion of the sample is known. Guidelines are suggested for choosing the best type of sample.
To facilitate periodic developmental screening of all children, a Prescreening Developmental Questionnaire (PDQ) was created to identify those children who require a more thorough screening with the Denver Developmental Screening Test (DDST). Children positive on the DDST screen are then referred for a diagnostic assessment. To devise the PDQ, 97 of 105 standard DDST items were formulated into questions. Ten age-appropriate questions were answered by 1,155 parents with subsequent evaluation of their children with the DDST. Agreement between parental responses for individual items and the score for their children's corresponding DDST item varied from 68% to 100% (mean, 93.3%). When the PDQ was positive, 31.2% of the children were referred for a DDST screen. These referrals included 86.7% of abnormal and 53.8% of questionable DDSTs among the 1,155 children screened. The predictive value of a referral was 23.3%. The predictive value of a referral did not differ significantly whether the PDQ was answered by a parent or by day care center staff personnel. A subsequent field trial of 1,027 PDQs in private physicians' offices and public health clinics yielded a similar predictive value (24.7%) for a referral. The parents liked the PDQ which took them only about five minutes to answer and the physicians liked the PDQ since it decreased by almost 69% the number of DDSTs they felt obliged to administer.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.