Chapter 6, Problem 57P

The etiology of high blood pressure remains a subject of active investigation. One widely accepted hypothesis is that excessive sodium intake adversely affects blood-pressure Data set available outcomes. To explore this hypothesis, an experiment was set up to measure responsiveness to the taste of salt and to relate the responsiveness to blood-pressure level. The protocol used involved giving 3-day-old infants in the newborn nursery a drop of various solutions, thus eliciting the sucking response and noting the vigor with which they sucked—denoted by MSB (mean number of sucks per burst of sucking). The content of the solution was changed over 10 consecutive periods: (1) water, (2) water, (3) 0.1 molar salt + water, (4) 0.1 molar salt + water, (5) water, (6) water, (7) 0.3 molar salt + water, (8) 0.3 molar salt + water, (9) water, (10) water. In addition, as a control, the response of the baby to the taste of sugar was also measured after the salt-taste protocol was completed. In this experiment, the sucking response was measured over five different periods with the following stimuli: (1) nonnutritive sucking, that is, a pure sucking response was elicited without using any external substance; (2) water; (3) 5% sucrose + water; (4) 15% sucrose + water; (5) nonnutritive sucking.

The data for the first 100 infants in the study are given in Data Set INFANTBP.DAT. The format of the data is given in Data Set INFANTBP.DOC at www.cengagebrain.com.

Construct a variable measuring the response to salt. For example, one possibility is to compute the average MSB for trials 3 and 4 − average MSB for trials 1 and 2 = average MSB when the solution was 0.1 molar salt + water – average MSB when the solution was water. A similar index could be computed comparing trials 7 and 8 with trials 5 and 6.

Construct indices measuring responsiveness to sugar taste, and provide descriptive statistics and graphical displays for these indices. Do the indices appear normally distributed? Why or why not? Compute the sample mean and associated 95% CIs for these indices.