of school indicate the number of persons enrolled at each of four levels: Kindergarten, elementary school (generally first to eighth grades), high school (generally ninth to twelfth grades), and college or professional school. The last group includes graduate students in colleges or universities. Persons enrolled in junior high school through the eighth grade are classified as in elementary school, and the others as in high school. Public or private school.--In this report, a public school is defined as any educational institution under the legal control of a public body. SOURCE AND RELIABILITY OF THE ESTIMATES The estimates present ed in this report are based on data obtained in connection with the monthly population sample survey of the Bureau of the Census. The statistics for 1956 are based on a sample design instituted in May 1956. The sample is spread over 330 sample areas comprising 638 counties and independent cities. A total of about 40,000 dwelling units and other living quarters are designated for the sample at any time, and completed interviews are obtained each month from about 35,000 households. Of the remainder, about 1,500 are households for which information should be obtained but is not, and the rest are vacant dwellings or others that are not to be enumerated for the survey. The data for 1953 and 1954 are based on a different sample design covering 230 areas and consisting of around 21,000 interview households. The data for 1947 through 1953 were based on a sample, which consisted of about the same number of units as the 230 area sample design but which covered only 68 sample areas. Estimating procedure.--The estimating procedure used in the surveys involves, as a final step, the inflation of weighted sample results to independent estimates of the civilian noninstitutional population of the United States. For the current survey these independent estimates are made separately for various age, color, and sex classes, and are based on statistics from the 1950 Census of Population; statistics of births, deaths, immigration, and emigration; and statistics on the strength of the Armed Forces and separation records. mates, except the independent estimates mentioned above, are based on sample data, they are subject to sampling variability, of sam the the The standard error is a measure pling variability. The chances are about 68 out of 100 that the difference due to sampling variability between an estimate and the figure that would have been obtained from a complete count of the population is less than standard error. The amount by which standard error must be multiplied to obtain other odds deemed more appropriate can be found in most statistical textbooks. For example, the chances are about 95 out of 100 that the difference is less than twice the standard error and 99 out of 100 that it is less than 2 times the standard error. For the statements in the text of this report, the criterion of twice the standard error (odds of 95 in 100 or better) has generally been used in determining that differences between sample estimates chance. are not likely to have occurred by The standard error of an estimated percentage depends upon both the size of the percentage and the size of the total on which it is based. The following are examples of the sampling variability of estimated percentages published in this report. The percent of noninstitutional population 5 years old enrolled in public kindergarten was estimated at 40.1 percent. The chances are about 68 out of 100 that a complete census figure between 37.9 percent of civilian tion 14 and 15 years areas enrolled in school was estimated at 97.6. The chances are about 68 out of 100 that a complete census would have yielded a figure between 97.2 and 98.0 percent. would have yielded a and 42.3 percent. The noninstitutional populaof age living in urban depends not but also on by the age, The following variability of of persons 5 The standard error of an absolute estimate based on the current survey only on the size of the estimate the distribution of the estimate color, and sex control groups. are examples of the sampling absolute estimates. The number to 34 years of age enrolled in school in 1956 was estimated at 39,353,000. The chances are about 68 out of 100 that a complete census would have yielded a figure between 39,135,000 and 39,575,000. The number of persons 14 and 15 years of age enrolled in school was estimated at 4,885,000. The chances are about 68 out of B.--Percent of the civilian noninstitutional population Pago for the United States: October 1 5 to 29 years old enrolled in school, by age, for the United States: October 1947 to 1956..... C.--Percent of children 5 years old enrolled in kindergarten, by color, residence, and type of control, for the United States: October 1956 and 1954.... D.--Percent of pupils enrolled in private schools, by level of school, for the United States: October 1948 to 1956.... E.--Percent enrolled in school and percent enrolled in high school, for persons 14 to 17 years old, by color and sex, for the United States: October 1956 and 1950 and April 1940...... F.--Civilian noninstitutional population enrolled in special schools, by age and sex, for the United States: October 1949 to 1956... Table DETAILED TABLES Pago 1.--Fall school enrollment of the civilian noninstitutional population ..... 5 to 34 years old, by age and sex, for the United States: October 1956, 1955, 1954, and 1950... 2.--Fall school enrollment of the civilian noninstitutional population 5 to 34 years old, by age and sex, for the United States, urban and rural: October 1956... 3.--Fall school enrollment of the civilian noninstitutional population 5 to 34 years old, by age, color, and sex, for the United States: October 1956..... 4.--Fall enrollment of the noninstitutional population 5 and 6 years old in public and private kindergartens, by age, color, and sex, for the United States, urban and rural: October 1956..... 5.--Fall school enrollment of the civilian noninstitutional population 5 to 34 years old, by type of school, age, color, and sex, for the United States: October 1956....... 6.--Fall enrollment of the civilian noninstitutional population 5 to 34 years old in public and private schools, by type of school, age, color, and sex, for the United States: October 1956..... 7.--Percent by marital status, for the civilian noninstitutional population 14 to 34 years old enrolled in school, by type of school, age, and sex, for the United States: tober 1956... 10 010 Oc 11 of school indicate the number of persons enrolled at each of four levels: Kindergarten, elementary school (generally first to eighth grades), high school (generally ninth to twelfth grades), and college or professional school. The last group includes graduate students in colleges or universities. Persons enrolled in junior high school through the eighth grade are classified as in elementary school, and the others as in high school. Public or private school.--In this report, a public school is defined as any educational institution under the legal control of a public body. SOURCE AND RELIABILITY OF THE ESTIMATES The estimates presented in this report are based on data obtained in connection with the monthly population sample survey of the Bureau of the Census. The statistics for 1956 are based on a sample design instituted in May 1956. The sample is spread over 330 sample areas comprising 638 counties and independent cities. A total of about 40,000 dwelling units and other living quarters are designated for the sample at any time, and completed interviews are obtained each month from about 35,000 households. Of the remainder, about 1,500 are households for which information should be obtained but is not, and the rest are vacant dwellings or others that are not to be enumerated for the survey. The data for 1953 and 1954 are based on a different sample design covering 230 areas and consisting of around 21,000 interview households. The data for 1947 through 1953 were based on a sample, which consisted about the same number of units as the area sample design but which covered only 68 sample areas. of 230 Estimating procedure.--The estimating procedure used in the surveys involves, as a final step, the inflation of weighted sample results to independent estimates of the civilian noninstitutional population of the United States. For the current survey these independent estimates are made separately for various age, color, and sex classes, and are based on statistics from the 1950 Census of Population; statistics of births, deaths, immigration, and emigration; and statistics on the strength of the Armed Forces and separation records. mates, except the independent estimates mentioned above, are based on sample data, they are subject to sampling variability,,. of sam The standard error is a measure pling variability. The chances are about 68 out of 100 that the difference due to sampling variability between an estimate and the figure that would have been obtained from a complete count of the population is less than the standard error. The amount by which the standard error must be multiplied to obtain other odds deemed more appropriate can be found in most statistical text books. For example, the chances are about 95 out of 100 that the difference is less than twice the standard error and 99 out of 100 that it is less than 2 times the standard error. For the statements in the text of this report, the criterion of twice the standard error (odds of 95 in 100 or better) has generally been used in determining that differences between sample estimates are not likely to have occurred by chance. The standard error of an estimated percentage depends upon both the size of the percentage and the size of the total on which it is based. The following are examples of the sampling variability of estimated percentages published in this report. The percent of noninstitutional population 5 years old enrolled in public kindergarten was estimated at 40.1 percent. The chances are about 68 out of 100 that a complete census would have yielded a figure between 37.9 and 42.3 percent. The percent of civilian noninstitutional popula tion 14 and 15 years of age living in urban areas enrolled in school was estimated at 97.6. The chances are about 68 out of 100 that a complete census would have yielded a figure between 97.2 and 98.0 percent. depends not but also on by the age, The following The standard error of an absolute estimate based on the current survey only on the size of the estimate the distribution of the estimate color, and sex control groups. are examples of the sampling variability of absolute estimates. The number of persons 5 to 34 years of age enrolled in school in 1956 was estimated at 39,353,000. The chances are about 68 out of 100 that a complete census would have yielded a figure between 39,135,000 and 39,575,000. The number of persons 14 and 15 years of age enrolled in school was estimated at 4,885,000. The chances are about 68 out of B.--Percent of the civilian noninstitutional Page for the United States: October 1 population 5 to 29 years old enrolled in school, by age, for the United States: October 1947 to 1956.... C.--Percent of children 5 years old enrolled in kindergarten, by color, residence, and type of control, for the United States: October 1956 and 1954.... D.--Percent of pupils enrolled in private schools, by level of school, for the United States: October 1948 to 1956................... E.--Percent enrolled in school and percent enrolled .... in high school, for persons 14 to 17 years old, by color and sex, for the United States: October 1956 and 1950 and April 1940..... F.--Civilian noninstitutional population enrolled in special schools, by age and sex, for the United States: October 1949 to 1956.... DETAILED TABLES Table 1.--Fall school enrollment of the civilian noninstitutional population 5 to 34 years old, by age and sex, for the United States: October 1956, 1955, 1954, and 1950..... 2.--Fall school enrollment of the civilian noninstitutional population 5 to 34 years old, by age and sex, for the United States, urban and rural: October 1956.... 3.--Fall school enrollment of the civilian noninstitutional population 5 to 34 years old, by age, color, and sex, for the United States: October 1956..... 4.--Fall enrollment of the noninstitutional population 5 and 6 years old in public and private kindergartens, by age, color, and sex, for the United States, urban and rural: October 1956.... 5.--Fall school enrollment of the civilian noninstitutional population 5 to 34 years old, by type of school, age, color, and sex, for the United States: October 1956......... 6.--Fall enrollment of the civilian noninstitutional population 5 to 34 years old in public and private schools, by type of school, age, color, and sex, for the United States: October 1956..... 7.--Percent by marital status, for the civilian noninstitutional population 14 to 34 years old enrolled in school, by type of school, age, and sex, for the United States: tober 1956... Oc 11 Table 1.--FALL SCHOOL ENROLLMENT OF THE CIVILIAN NONINSTITUTIONAL POPULATION 5 TO 34 YEARS OLD, BY AGE AND SEX, FOR THE UNITED STATES: (Figures include children enrolled in kindergarten; statistics for 1950 revised accordingly. Age and sex the nearest thousand without being adjusted to group totals, which are independently rounded) The individual figures in this report are rounded to Table 2.--FALL SCHOOL ENROLLMENT OF THE CIVILIAN NONINSTITUTIONAL POPULATION 5 TO 34 YEARS OLD, BY AGE AND SEX, FOR THE UNITED STATES, (Figures for persons enrolled in school include children enrolled in kindergarten) |