Academic Integrity: tutoring, explanations, and feedback — we don’t complete graded work or submit on a student’s behalf.

Equity of access is a primary goal of many health systems. Determining whether A

ID: 3243078 • Letter: E

Question

Equity of access is a primary goal of many health systems. Determining whether Australia's system (Medicare) meets this goal is an important research question. Consider the case of access to general practitioners (GPs). The multiple regression results presented below in Table 3 are part of an analysis aimed at answering whether there is equitable access to GP services where access is defined on the basis of health needs rather than socio-economic status (SES). The data come from the 1995 National Health Survey conducted by the Australian Bureau of Statistics. A sub-sample of 2446 working age (18-60) single females were selected for analysis. The dependent variable for the study was Visit, a dummy variable that was equal to one if the individual had visited a GP in the last two weeks and zero otherwise. Table 2 provides definitions of all variables used in the analysis together with their means. Age and Poorhealth are the two variables chosen to represent the need for health care while Income and Education represent socio-economic status. Results in columns (1) and (2) of Table 3 represent alternative choice of explanatory variables. (i) Provide one good reason for restricting the sample to single females? (ii) How should we interpret the intercept in column (1)? (iii) Why do you think the heteroskedastic-robust standard errors have been reported? (iv) Interpret the estimates for Age and Poorhealth in column (1). Do they seem to be sensible estimates? Are they statistically significant? (v) If there is equity of access then variables related to Income and Education should not affect visits to GPs. Using the results in columns (1) and (2) evaluate the null hypothesis of equity of access? Be sure to explicitly state the null and alternative hypotheses. You will need to use the reported R-squared's to construct the test statistic. Do you have any concerns about using this form of the test?

Explanation / Answer

Answer to part (i)

The sample is restricted to working single women, may be because they are the last one to access such medical services. In a family the head of the family is supposed to provide all the family members the medical services aand makes sure that this need is catered to properly without delay. Even single males get easy access to such services. But when it comes to single females the question arises, whether they too get such services with the same ease as the rest of the categories. In and all it aims at finding equity of access of medical systems based on gender.

.

Answer to part (ii)

The intercept for those who visited in last two weeks is 0.156 with a standard error of 0.028 and similary for those who didnot visit the GP in last two weeks the value of intercept is 0.154 ( a bit lessed) with a standard error of 0.027.

This simply means that there is some basic minimum visit to the doctor irrespective of the age , income and gender

.

Answer to part (iii)

Robust errors are generally larger than the non robust ones , and that is why it is always better to report them in order to know the maximum error limit. The test of heteroskedasticity is positive in larger samples and thus in this case since the sample is very large ( sample size = 2446) we include this error.

.

Answer to part (iv)

For age the intercept is 0.00151, which seems to show that the visit is influenced by the age. Yes this value is significant

For poorhealth the estimate is 0.126 which seems to show that the poorhealth is not a significant factor for the visit. This seems to be impractical , as the visit is driven by poorhealth.