Homework Assignment 5

Define an ordinal or multinomial outcome variable of your choosing and define how you will recode the original variable.

I am using the general health and using all 5 responses, 1=excellent, 2=very good, 3=good, 4f=air, 5=poor, to run a multinomial regression.

State a research question about what factors you believe will affect your outcome variable.

Will having a health care result in people being more likely to report good health or will having a check up more recently result in people more likely to report good health instead?

Fit the ordinal or the multinomial logistic regression models to your outcome.

multifit <- svy_vglm(genhlth ~ raceeth + checkup1 + hlthpln1, family = multinomial(refLevel = 1), design = des)

multifit %>%
tbl_regression()

## ! `broom::tidy()` failed to tidy the model.

## x No tidy method for objects of class svy_vglm

## v `tidy_parameters()` used instead.

## i Add `tidy_fun = broom.helpers::tidy_parameters` to quiet these messages.

## x Unable to identify the list of variables.
## 
## This is usually due to an error calling `stats::model.frame(x)`or `stats::model.matrix(x)`.
## It could be the case if that type of model does not implement these methods.
## Rarely, this error may occur if the model object was created within
## a functional programming framework (e.g. using `lappy()`, `purrr::map()`, etc.).

Characteristic	Beta	95% CI1	p-value
(Intercept):1	0.19	0.10, 0.28	<0.001
(Intercept):2	0.45	0.36, 0.54	<0.001
(Intercept):3	-0.26	-0.37, -0.15	<0.001
(Intercept):4	-1.8	-2.0, -1.6	<0.001
(Intercept):5	-5.1	-5.8, -4.4	<0.001
(Intercept):6	-6.0	-6.8, -5.2	<0.001
raceethnhblack:1	0.25	0.13, 0.37	<0.001
raceethnhblack:2	0.09	-0.03, 0.22	0.13
raceethnhblack:3	-0.10	-0.25, 0.04	0.2
raceethnhblack:4	0.10	-0.15, 0.36	0.4
raceethnhblack:5	0.26	-0.62, 1.1	0.6
raceethnhblack:6	1.0	-0.27, 2.3	0.12
raceethnhmulti:1	0.19	-0.02, 0.41	0.077
raceethnhmulti:2	-0.17	-0.39, 0.06	0.14
raceethnhmulti:3	-0.37	-0.64, -0.10	0.007
raceethnhmulti:4	0.19	-0.19, 0.56	0.3
raceethnhmulti:5	0.26	-0.86, 1.4	0.6
raceethnhmulti:6	0.41	-1.4, 2.2	0.7
raceethnhother:1	0.02	-0.12, 0.16	0.8
raceethnhother:2	-0.15	-0.32, 0.01	0.070
raceethnhother:3	-1.0	-1.2, -0.84	<0.001
raceethnhother:4	-0.65	-1.0, -0.32	<0.001
raceethnhother:5	-0.08	-1.0, 0.86	0.9
raceethnhother:6	-1.1	-2.7, 0.47	0.2
raceethnhwhite:1	0.35	0.25, 0.44	<0.001
raceethnhwhite:2	-0.27	-0.36, -0.18	<0.001
raceethnhwhite:3	-0.65	-0.77, -0.53	<0.001
raceethnhwhite:4	-0.17	-0.37, 0.03	0.10
raceethnhwhite:5	-0.42	-1.2, 0.40	0.3
raceethnhwhite:6	-0.51	-1.3, 0.33	0.2
checkup11last2yrs:1	-0.16	-0.24, -0.08	<0.001
checkup11last2yrs:2	-0.29	-0.39, -0.20	<0.001
checkup11last2yrs:3	-0.70	-0.84, -0.57	<0.001
checkup11last2yrs:4	-1.0	-1.3, -0.76	<0.001
checkup11last2yrs:5	-0.08	-0.70, 0.54	0.8
checkup11last2yrs:6	-1.5	-2.9, -0.18	0.026
checkup12last5yrs:1	-0.09	-0.20, 0.03	0.14
checkup12last5yrs:2	-0.29	-0.42, -0.17	<0.001
checkup12last5yrs:3	-0.47	-0.67, -0.27	<0.001
checkup12last5yrs:4	-1.1	-1.4, -0.84	<0.001
checkup12last5yrs:5	-0.04	-1.3, 1.2	>0.9
checkup12last5yrs:6	-0.44	-1.3, 0.43	0.3
checkup135ormore:1	-0.14	-0.27, -0.02	0.021
checkup135ormore:2	-0.25	-0.41, -0.09	0.003
checkup135ormore:3	-0.42	-0.64, -0.21	<0.001
checkup135ormore:4	-0.30	-0.69, 0.10	0.15
checkup135ormore:5	1.0	-0.04, 2.1	0.059
checkup135ormore:6	-0.81	-2.9, 1.2	0.4
checkup14never:1	-0.25	-0.62, 0.12	0.2
checkup14never:2	-0.30	-0.66, 0.05	0.10
checkup14never:3	-0.24	-0.70, 0.21	0.3
checkup14never:4	-0.22	-1.1, 0.61	0.6
checkup14never:5	-0.58	-2.0, 0.89	0.4
checkup14never:6	0.53	-1.1, 2.2	0.5
hlthpln1nohp:1	-0.14	-0.25, -0.04	0.007
hlthpln1nohp:2	0.26	0.15, 0.37	<0.001
hlthpln1nohp:3	0.25	0.11, 0.39	<0.001
hlthpln1nohp:4	0.17	-0.05, 0.40	0.12
hlthpln1nohp:5	0.39	-0.46, 1.2	0.4
hlthpln1nohp:6	-0.59	-1.6, 0.46	0.3
1 CI = Confidence Interval

Describe the results of your model and present output from the model in terms of odds ratios and confidence intervals for all model parameters in a table.

Overall, those who report good, fair or poor health are less likely to report being in god health than those who initially reported being in very good or excellent health. All groups, 2 to 5, are less likely to report being in good health and there is a general trend of the least recently a person has had a check up, the less likely they are to report good health in comparison to those who self reported being in excellent health. This is the result I expected to see, however, interestingly enough, the results for those who have health insurance did not follow this trend. Those who do not have health insurance that reported good, fair , and poor health are more likely than those who reported very good health to report them being in good health. To answer my research question for this exercise, it seems that whether a person had had a check up recently has more of an influence of how a person self reports on their health versus having health coverage.