National Academies Press: OpenBook

Coverage Matters: Insurance and Health Care (2001)

Chapter: Appendix D: Multivariate Analysis

« Previous: Appendix C: Data Tables
Suggested Citation:"Appendix D: Multivariate Analysis." Institute of Medicine. 2001. Coverage Matters: Insurance and Health Care. Washington, DC: The National Academies Press. doi: 10.17226/10188.
×
Page 135
Suggested Citation:"Appendix D: Multivariate Analysis." Institute of Medicine. 2001. Coverage Matters: Insurance and Health Care. Washington, DC: The National Academies Press. doi: 10.17226/10188.
×
Page 136
Suggested Citation:"Appendix D: Multivariate Analysis." Institute of Medicine. 2001. Coverage Matters: Insurance and Health Care. Washington, DC: The National Academies Press. doi: 10.17226/10188.
×
Page 137
Suggested Citation:"Appendix D: Multivariate Analysis." Institute of Medicine. 2001. Coverage Matters: Insurance and Health Care. Washington, DC: The National Academies Press. doi: 10.17226/10188.
×
Page 138
Suggested Citation:"Appendix D: Multivariate Analysis." Institute of Medicine. 2001. Coverage Matters: Insurance and Health Care. Washington, DC: The National Academies Press. doi: 10.17226/10188.
×
Page 139
Suggested Citation:"Appendix D: Multivariate Analysis." Institute of Medicine. 2001. Coverage Matters: Insurance and Health Care. Washington, DC: The National Academies Press. doi: 10.17226/10188.
×
Page 140
Suggested Citation:"Appendix D: Multivariate Analysis." Institute of Medicine. 2001. Coverage Matters: Insurance and Health Care. Washington, DC: The National Academies Press. doi: 10.17226/10188.
×
Page 141
Suggested Citation:"Appendix D: Multivariate Analysis." Institute of Medicine. 2001. Coverage Matters: Insurance and Health Care. Washington, DC: The National Academies Press. doi: 10.17226/10188.
×
Page 142

Below is the uncorrected machine-read text of this chapter, intended to provide our own search engines and external engines with highly rich, chapter-representative searchable text of each book. Because it is UNCORRECTED material, please consider the following text as a useful but insufficient proxy for the authoritative book pages.

D Multivariate Analyses In the two tables that follow, the Committee reports estimates of how much uninsured rates may be influenced by specific socioeconomic, demographic, and geographic characteristics alone. These estimates were prepared for comparison with the uninsured rates presented in the body of this report. They were derived by means of multivariate statistical analysis, using data from the 2000 Current Population Survey (CPS) in the form of a derived variable file made available to the Committee by Paul Fronstin and the Employee Benefit Research Instituted Four sets of analyses were performed to estimate and predict differences in unin- sured rates by: ~ . . 1. socioeconomic c. ~aracterlstlcs; 2. race and ethnicity; 3. immigrant and nativity status, both alone and specifically by race and ethnicity; and 4. geographic areas. Tables D. 1 and D.2 each present two sets of results for these analyses. The first column of each table reports comparisons of the likelihood of being uninsured between a group of interest and a reference group. For example, Hispanics are compared with non-Hispanic whites, with the difference in uninsured rate be- 1The Committee's analysis considers family units defined in terms of kin relationships, which may give different estimates than other analyses cited in this report, and based on CPS data, in which family units are defined in terms of insurance eligibility. 135

36 CO VERA GE MA TTERS: INSURANCE AND HEALTH CARE TABLE D.1 Estimated Independent Effects of Poverty Level, Education Level, Race and Ethnicity, and Immigrant and Nativity Status on Uninsured Rate Unadjusted Difference Between Uninsured Rate and Uninsured Rate for Reference Group (percentage points) Predicted Difference if Coefficients (based on reference group's covariates) Were the Same as Those for the Reference Group (percentage points) Effect of Poverty Level on Uninsured Rate (Reference Group: Families Earning >200% FPL) Families earning <100% FPL 24.2a 1s.3a Families earning 100 - 149% FPL 19.6a 12.4a Families earning 150 - 199% FPL 1 5.8a 10.1 a Effect of Education Level on Uninsured rate (Reference Group: Primary Wage Earner with Postcollege Education) Primary wage earner has less than high school diploma 28.4a 16.2a Primary wage earner has high school diploma 12.oa 7.9a Primary wage earner has some college 8.2a 5.4a Primary wage earner has college degree 2.2a 1.4c Effect of Race and Ethnicity on Uninsured Rate (Reference Group: Non-Hispanic Whites) Non-Hispanic African American 1o.oa 5.oa Hispanic 22.2a 7.2a All other groups 1 l.3a 5.4a Effect of Immigrant and Nativity Status on Uninsured Rate (Reference Group: U.S. Born) All foreign-born persons Naturalized citizens Long-term residents (at least 6 years) 16.9a Short-term residents (<6 years) 29.8a Foreign-born non-Hispanic whites (Reference Group: U.S. Born Non-Hispanic Whites) Naturalized citizens Long-term residents (at least 6 years) Short-term residents (<6 years) 6.3a 0.7 8.7a 13.8a 2.5a 1o.8a 14.8a 0.7 6.9b 9.3a

APPENDIX D TABLE D.1 Continued 137 Unadjusted Difference Between Uninsured Rate and Uninsured Rate for Reference Group (percentage points) Predicted Difference if Coefficients (based on reference group's covariates) Were the Same as Those for the Reference Group (percentage points) Foreign-born non-Hispanic African Americans (Reference Group: U.S. Born Non-Hispanic African Americans) Naturalized citizens Long-term residents (at least 6 years) 7.6a 6.4 Short-term residents (<6 years) 18.7a Foreign-born Hispanics (Reference Group: U.S. Born Hispanics) lo.3a 5.4 13.6a Naturalized citizens 5.2a 5.5a Long-term residents (at least 6 years) 15.8a ls.3a Short-term residents (<6 years) 31.8a 2l.oa Notes: Effects are reported as follows: (1) the unadjusted uninsured rate, expressed in terms of the difference compared with the uninsured rate for the reference group; (2) the predicted uninsured rate, expressed in terms of the difference with the uninsured rate for the reference group, as adjusted for the covariates. Models for poverty level and for education level include the following covariates: age, gender, nativ- ity, race and ethnicity, whether urban or rural, family type, health status. Model for race and ethnicity includes the following covariates: primary wage earner's education level, primary wage earner's work status, primary wage earner's occupation, whether primary wage earner has full-time or part-time job, size of firm employing primary wage earner (indicator), family income, age, gender, nativity, family type, state (indicator), whether urban or rural, health status. Model for immigrant and nativity status includes the following covariates: primary wage earner's education level, primary wage earner's work status, primary wage earner's occupation, whether pri- mary wage earner has full-time or part-time job, size of firm employing primary wage earner (indica- tor), family income, age, gender, family type, state (indicator), whether urban or rural, health status. ap <0.01 bp <0.05 cp <0.10 SOURCE: EBRI derived variable file, based on March 2000 Current Population Survey.

138 CO VERA GE MA TTERS: INSURANCE AND HEALTH CARE TABLE D.2 Estimated Independent Effect of State of Residence on Uninsured Rate Unadjusted Difference Between Uninsured Rate and National Average Uninsured Rate (17.5%) (percentage points) Predicted Difference, if State's Covariates and Coefficients Were the Same as for National Averages (percentage points) Alabama -1.3 -1.2 Alaska 2. Pa 4. 3a Arizona 6. Sa 4. 1 a Arkansas —0.4 O. ~ California 4. pa - 1 . oa Colorado 0.9 2.2a Connecticut - 6.2a - 2.4a D elaware -4. 6a -2. 7a District of Columbia 0.1 - 3.0b Florida 5. 4a 3. 4a Georgia 0. 4 O. 4 Hawaii - 5 . oa - ~ . 3a Idaho 4.la 4.la Illinois —1 Sa -0.5 Indiana - 5 .2a - 2.2a Iowa - Ma - 4.2a Kansas - 3.5a - 1 .4c Kentucky -1 .0 1.0 Louisiana 7. 6a 6. 2a Maine —4.2a —0.5 Maryland - 3 . Pa - 2. ob Massachusetts - 5 . 7a - 4. 6a Michigan - 5 . 1 a - 2. 3a Minnesota - ~ . 6a - 4. 3a Mississippi 1.5 1.2 Missouri - 7.9a - 4.1 a Montana 3. 6a 2. Sa Nebraska -5 .2a -2.2a Nevada 5. 3a 4. 5a New Hampshire - 6.2a - 2.ob New Jersey -2.5a _1.oc New Mexico 1l.ga 7.4a New York 1. ob - l .1 a North Carolina 0.1 0.9 North Dakota _3.5a —1.4 Ohio - 5.oa - 1 .6a Oklahoma 3. oa 4. 3a Oregon 1.0 - 0.6 Pennsylvania - 6. 5a - 3.2a Rhode Island -9.4a -6.2a South Carolina 2.6b 4.6a South Dakota _3.9a -0.9

APPENDIX D TABLE D.2 Continued 139 Unadjusted Difference Between Uninsured Rate and National Average Uninsured Rate (17.5%) (percentage points) Predicted Difference, if State's Covariates and Coefficients Were the Same as for National Averages (percentage points) Tennessee - 4. Sa - 2. 5a Texas S.3a 4.Sa Utah —2.2b 1.3c Vermont _3 . 9a —1 .5 Virginia —1 .5 2. 5a Washington 0. 1 2. 4a West Virginia 3.oa 4.la Wisconsin - 5.3a - 1 .Sb Wyoming 0.6 2. 7a NOTES: Effects are reported as follows: (1) the unadjusted uninsured rate, expressed in terms of the difference compared with the uninsured rate for the reference group; (2) the predicted uninsured rate, expressed in terms of the difference with the uninsured rate for the reference group, as adjusted for the covariates Model for state includes the following covariates: primary wage earner's education level, primary wage earner's work status, primary wage earner's occupation, whether primary wage earner has full- time or part-time job, size of firm employing primary wage earner (indicator), family income, age, gender, nativity, race and ethnicity, family type, state (indicator), whether urban or rural, health status. ap <0.01 bp <0.05 cp <0.10 SOURCE: EBRI derived variable file, based on March 2000 Current Population Survey. tween the two groups reported in terms of percentage points. The second column reports a comparison between the same two groups as in the first column but taking into consideration, or adjusting for, population characteristics that are known to affect the likelihood of being uninsured and which often are closely related to, or highly correlated with, the group's identifying characteristic, for example, race and ethnicity. For all four sets of comparisons, a series of logistic regression equations were prepared to estimate and predict uninsured rates, with the method of adjusting for population characteristics differing for each of the four sets of comparisons.2 2The Committee's analysis follows the method used by Ku and Matani, 2001, for using logistic regression models to estimate the probability of being uninsured, with comparisons between reference groups and comparison groups reported in terms of percentage point differences (in the case of Ku and Matani, in estimated mean change in the probability of having a specified source of coverage or being uninsured).

40 CO VERA GE MA TTERS: INSURANCE AND HEALTH CARE Except for the analysis of immigrant and nativity status, no interaction terms were used, on the assumption that change in the value of a measured characteristic (or covariate) is unlikely to lead to change in the values of other covariates in unique ways. For the analyses by race and ethnicity, to arrive at the estimated difference reported in the second column of Table D.1, a logistic regression model was created to estimate the likelihood of being uninsured for the reference group and all comparison groups, taking into consideration or adjusting for all measured characteristics other than race and ethnicity.3 This regression model also yielded a set of values, or coefficients, each of which describes the relative influence on the uninsured rate of a characteristic included in the model, for the reference group (e.g., non-Hispanic whites). To estimate the predicted differences reported in the second column of Table D.1, the same logistic regression model was used, com- bining the coefficients generated by the regression model for the reference group and the values (or covariate data) of the population characteristics (e.g., age, gender, health status) that describe the comparison group (e.g., non-Hispanic whites). The difference between this predicted likelihood of being uninsured (reported in column 2) and the reference group's estimated likelihood of being uninsured reflects differences between the comparison and reference group other than those reflected in the values for each population's measured characteristics.4 Linear regression was used to evaluate the size and statistical significance of the difference (reported in column 2) between the predicted likelihood and the com- parison group's estimated likelihood.5 Because the results are presented in terms of differences between comparison and reference groups, an estimated uninsured rate of minus 1.1 percent, for example, is a rate that is 1.1 percentage points below the uninsured rate for the reference group. For example, the logistic regression model based on population characteristics in our CPS data set gives an estimated uninsured rate for Hispanics that is 22.2 percentage points higher than the estimated uninsured rate for non-Hispanic 3The first step of the adjustment process included state fixed effects to control for state policy and other differences that would generate intra-state cluster effects. 4An alternative approach would be to prepare a single logistic regression with covariates for the characteristic of race and ethnicity and all other characteristics, plus interaction terms to describe the relationships between the characteristic of race and ethnicity and all of the other characteristics. Our adjusted comparison would consist of the difference in the probability predictions between what happens for the reference group and each of the comparison groups. This approach would require that the full model (including all covariates) be estimated for each subgroup, which is difficult given the size of some subgroups. The decision was made to limit the number of terms in the full model, because the main concern of the analysis is to evaluate the overall effect, or differences between estimated uninsured rates, rather than values of specific coefficients. 5The linear regression includes weights to account for differential sampling at each stage of the analysis.

APPENDIX D 14 whites, a difference that is statistically significant. If the differences in each population's measured characteristics influenced the likelihood of being uninsured in identical ways for both groups, and if there were no other influences on uninsured rates, the predicted difference between the uninsured rates for Hispanics and non-Hispanic whites should be zero. Instead, the predicted difference is 7.2 percentage points, a difference that is both statistically significantly different from zero and about 15 percentage points smaller than the unadjusted difference be- tween the two groups. Therefore, two-thirds of the difference in estimated unin- sured rates between Hispanics and non-Hispanic whites reflects differences in the values of measured population characteristics between these two groups, while approximately one-third of the difference reflects other factors that were not measured by the CPS data set or modeled in the multivariate analysis. The analyses by immigrant and nativity status were similar to the analysis by race and ethnicity. For each group identified by race and ethnicity (e.g., Hispanic, non-Hispanic African American, and other), a logistic regression model was pre- pared to estimate an uninsured rate and a set of coefficients for a reference group of U.S. born citizens. The difference in estimated uninsured rates between each comparison group (e.g., foreign born, short-term resident, long-term resident) and the reference group is reported in column 1, stratified by race and ethnicity. To estimate the predicted differences in estimated uninsured rates reported in column 2, logistic regression models were prepared for each racial and ethnic group in which the coefficients for the reference group were combined with covariate data for each comparison group.6 A preliminary analysis of the data suggested that stratifying the multivariate analysis by race and ethnicity would allow for the observation of important differences among populations of immi- grants and naturalized citizens, especially useful for understanding uninsured rates within the Hispanic population. The analyses by poverty level and education level of primary wage earner and the analysis by state were conducted using an approach that differed only slightly from the analysis by race and ethnicity. To obtain the estimated differences re- ported in the second column, a logistic regression model was created to estimate the likelihood of being uninsured for both the reference groups (e.g., families earning greater than 200 percent of the federal poverty level, and primary wage earner with postcollege education) and all comparison groups. This model took into account or adjusted for all the measured characteristics save for the character- istics of poverty level and education or state (in Table D.2~. Linear regression analysis was used to evaluate the size and statistical significance of the difference (reported in column 2) between the adjusted likelihood of being uninsured for each comparison group and that of each reference group.7 6Linear regression was used to evaluate the adjusted comparison, with correction for oversampling and robust standard errors. 7For the linear regression analysis of the multivariate analyses by poverty and education and by state, weights were included to account for differential sampling.

42 COVERAGE MATTERS: INSURANCE AND HEALTH CARE The estimates reported in Tables D.1 and D.2 indicate that there is consider- able variation, both in how much specific characteristics may influence a group's uninsured rate, independently of other measured characteristics, and in how much variation between uninsured rates is not accounted for by the measured character- istics used in the models. For example, the average uninsured rate for members of families earning less than 100 percent of FPL is estimated to be 24.2 percentage points higher than the average uninsured rate for members of families earning at least 200 percent of FPL. If members of families earning less than 100 percent of FPL as a group resembled members of families earning at least 200 percent of FPL, the uninsured rate for family members earning less than 100 percent of FPL would be predicted to be 15.3 percentage points, a 9 percentage-point or 37 percent diminution in the difference between uninsured rates. The 63 percent difference that remains cannot be attributed to differences in the measured characteristics (other than poverty level and education) and is not addressed by the models in this specific analysis. One would expect fairly large proportions of the differences in uninsured rates to remain unaccounted for by or associated with the specific characteristics evaluated, because there are many aspects of socioeconomic status, demographic characteristics, health status, and geography that are not measured in this analysis. In every case, controlling for other correlated factors that influence insurance status reduces the estimated effect of a factor examined in the simple bivariate comparisons. In no case were the effects of those factors completely related to additional covariates.

Next: Appendix E: Glossary »
Coverage Matters: Insurance and Health Care Get This Book
×
Buy Paperback | $45.00 Buy Ebook | $36.99
MyNAP members save 10% online.
Login or Register to save!
Download Free PDF

Roughly 40 million Americans have no health insurance, private or public, and the number has grown steadily over the past 25 years. Who are these children, women, and men, and why do they lack coverage for essential health care services? How does the system of insurance coverage in the U.S. operate, and where does it fail? The first of six Institute of Medicine reports that will examine in detail the consequences of having a large uninsured population, Coverage Matters: Insurance and Health Care, explores the myths and realities of who is uninsured, identifies social, economic, and policy factors that contribute to the situation, and describes the likelihood faced by members of various population groups of being uninsured. It serves as a guide to a broad range of issues related to the lack of insurance coverage in America and provides background data of use to policy makers and health services researchers.

  1. ×

    Welcome to OpenBook!

    You're looking at OpenBook, NAP.edu's online reading room since 1999. Based on feedback from you, our users, we've made some improvements that make it easier than ever to read thousands of publications on our website.

    Do you want to take a quick tour of the OpenBook's features?

    No Thanks Take a Tour »
  2. ×

    Show this book's table of contents, where you can jump to any chapter by name.

    « Back Next »
  3. ×

    ...or use these buttons to go back to the previous chapter or skip to the next one.

    « Back Next »
  4. ×

    Jump up to the previous page or down to the next one. Also, you can type in a page number and press Enter to go directly to that page in the book.

    « Back Next »
  5. ×

    To search the entire text of this book, type in your search term here and press Enter.

    « Back Next »
  6. ×

    Share a link to this book page on your preferred social network or via email.

    « Back Next »
  7. ×

    View our suggested citation for this chapter.

    « Back Next »
  8. ×

    Ready to take your reading offline? Click here to buy this book in print or download it as a free PDF, if available.

    « Back Next »
Stay Connected!