"Education Statistics" Homework

First job:? Right, wrong, right, right, right, wrong, wrong, wrong, wrong, right.

Second job:? Right, right, wrong, wrong, wrong, wrong, wrong, wrong, wrong, wrong.

Third job:? Right, right, right, wrong, right, wrong, right, wrong, wrong, wrong.

Fourth job:?

An object of study outlined education statistics.

A: Education Statistics is the mathematical statistical principles and methods used to study education issues an applied science. It is the study of how to collect, collate, analyze data from the survey of education and educational experiments obtained, and to

This is the basis of scientific inference, to reveal the objective laws of educational phenomenon implied a science.

Educational Statistics as a branch of science education, it provides a scientific method for the study of education, scientific research is an important tool for the quantitative analysis of education. It not only helps project management education workers, improve the management level, but also contribute to education theorists literature related to educational research, and help teachers understand the students in depth, analysis of teaching effectiveness, thereby enhancing their own research ability.

2. Why learn educational statistics?

A: (1) Education statistics for scientific research provides a scientific method.

(2) Education Statistics is an important research tool for quantitative analysis of education.

(3) The method of education statistics can be used to learn about the curriculum and educational practice work in.

Education statistics in addition to educational research tool for educators, learning it also has specific meaning in the following areas:

(1) can be successfully read using statistical methods for quantitative analysis of scientific reports and literature, from which you can learn the advanced research results indirectly. Because some scientific reports with statistical methods to express, explain, explain their research results. Statistical significance of the process and if we do not statistically terminology and what it stands can not understand the meaning of them.

(2) can improve the efficiency of scientific and educational work.

(3) lay the foundation for educational measurement and evaluation of educational learning.

3 What are the types of data?

A: Data are observations of random variables. The different types of data, statistical processing methods are also different.

(1) Statistical data source can be divided by the dot count data and measurement data. Dot count data is data obtained by computing the number. Metric data refers to data for a certain tool or a certain standard measurement obtained.

(2) Statistics by the random variable value, and the data can be divided into continuous random variable data indirectly random variables. A limited number of data values, referred to as the indirect data random variables. Unlimited number of data values, referred to as data continuous random variables.

What precautions 4 tabulation there?

A: The structure of the table should be simple and straightforward. A table can have only one hub, description of the problem to be focused, clear, large table to avoid drawing bloated all-inclusive; the level of the table to make it clear, according to a logical order item, indicators and reasonable arrangement.

5, the basic structure and mapping rules outlined chart.

A: The basic structure: a title, drawing number, headings, graphics, other items of note in FIG.

Draw rules:? (1) Title name of the map should be concise, suitable for the content map, you can specify the time and place when necessary. Figure caption font is the largest in the figure, from left to right in the bottom of the figure write. (2) figure number? If several figures in the article, you need to compile the order in which they appear on the serial number, written on the left front of the figure caption. (3) heading? Chart for the vertical and horizontal axes, respectively, shall indicate statistical items and their scale in vertical and horizontal axes. The horizontal axis is the baseline, generally represent the phenomenon being observed, the scale to be equidistant from left to right, small to large, writing under the horizontal axis. Vertical axis scale line, scale starts at 0, bottom-up, from small to large, writing in the left side of the longitudinal axis. Two shafts must specify unit. (4) Graphics? Graphics line in the figure is the thickest, and should be clear. For aesthetic reasons, the pattern height to width ratio of preferably 3 to 5. If several pattern compared in one figure, can be distinguished by a different line pattern, the meaning of the various graphics line may be used in place legend be indicated. (5) Legend? Legend is not part of the figure needed. If local figures must be interpreted, it can be used to illustrate the legend. Legend of the text to be concise, smaller font, write at the bottom of the chart title.

6. What are the main differences in coefficient of use there?

A: First, comparing the same unit while the average difference between the degree of difference of larger data set of data.

Second, the degree of difference between the different units of comparison data set information.

7. What is the correlation? How correlation analysis?

A: Is there a correlation between the two variables studied, if there is a correlation, how it related to the direction and closeness, a process known as correlation analysis statistically.

The main method is to draw the correlation analysis and correlation coefficient associated scattergram.

8, commonly used sampling methods are there?

A commonly used sampling methods are what categories: First, simple random sampling. The lottery process, a random number table method, die method random number, the random number calculator method. Second, the mechanical sampling. Third, stratified sampling. The ratio of respective layers according to the number of distribution, optimal configuration method. Fourth, cluster sampling.

9. What is inferential statistics? It contains what?

A: inferential statistics is based on information provided by the sample, the use of probability theory analysis, feasibility studies, statistical methods to estimate or guess the overall distribution of a certain degree of reliability on its contents include general parameter estimation and hypothesis testing.

10, what application conditions ��2 test is a one-way table? Test examples.

A: The way the table ��2 test is a one-way data table were ��2 test, that single factor ��2 test.

?? way the dot count table is a table of measured data according to a classification standard preparation obtained. (Examples)

11. DESCRIPTION meaning and purpose of the sign test.

A: The sign test is a sign of the statistical tests as the test data, is checked by the relevant sign of the difference of the two samples of each pair of data (plus or minus) to compare the differences of the two samples significant. It applies to two related differences in test samples. In the sign test, i.e., considering only the symbol of the direction difference of each pair of data related to two samples, not considering the size difference.

12. Description of the meaning and purpose of the rank sum test

A: The rank is rank or grade and the sum. Rank sum test based on rank and test methods for the test data. Rank sum test methods are differences in the two independent samples were tested.

Fifth job:

1. The following 20 students divided into groups of 5 to music performance from the preparation of a frequency table.

Table 1? 20 students in music performance

77? 78? 80? 81? 82 ?? 88? 86? 85? 86? 88

84? 83? 83? 88? 89 ?? 77? 78? 79? 83? 82

answer:

?? 20 students in music performance frequency distribution table

Median scores set frequency cumulative percentage cumulative frequency 85

80

75 87.5

82.5

77.5 7

8

520

13

5 100.0

65.0

25.0 the sum of? 20??

?

2. A unit take the form of self-assessment and evaluation of his combination of staff assessment, self-assessment and his staff assessment scores each accounted for 40?nd 60?n the final score, a self-assessment scores of workers is 85 points, his assessment the score is 80 points, the final score is the number of workers?

????? Solution: calculating a weighted average: 82 =

A: The final score is 82 points workers.

3. Large classes and a kindergarten for Intermediate students conducted a test, please test scores of the two classes by comparing an explanation.

Do not shift the class average standard deviation class Intermediate 766 Taipan 8312

A: It can be seen from an average of two classes of tests, Intermediate Taipan grade point average higher than the average score, on the other hand, the standard deviation is greater than the standard Intermediate Taipan achievement scores of poor students in the class visible difference in performance than the middle shift big.

4. A school for teachers conducted two assessment, please Chen, Ma two teachers score into a standard score, their total score were compared using standard scores.

Assessment school school average standard deviation scores Chen fraction of a horse two 7,666,470 8,689,088

Solution: two teachers two results is calculated using the following formula may be a quasi standard score, then calculate the total score of each compared.

Chen standard score score 2 and 0.5, respectively, and both of -1.5;

Ma teacher performance standard score of -1 and 0.25, respectively, both of and -0.75;

Chen's total score is not a good horse teacher.

5, randomly selected 32 male and 50 female teachers teachers a test Testing Results: The average male teachers is 80 minutes, the standard deviation is 8 minutes; female teachers average is 76 points, the standard deviation is 10 Minute. Please check male, female teachers Testing Results of the presence or absence of a significant difference.

?

? Solution: �� hypothesis:

H0: ��1 = ��2 ?? H1:��1 �� ��2

�� Z value is calculated:

This embodiment uses separate large test sample Z, Z value is calculated using the following formula:

Is calculated according to the formula: Z = 2

�� inspection form: two-sided test

�� Statistical Decision: 1.96

?

6. Eight students were two types of tests, test scores is represented by grade, the table below, calculate the rank correlation coefficient of two test scores.

Student Number 1 ?? 2 ?? 3 ??? 4 ??? 5 ??? 6 ??? 7 ???? 8 X 8 ?? 4 ?? 6 ??? 2 ??? 7 ??? 3 ??? 5 ???? 1 Y 7 ?? 4 ?? 5 ??? 2 ??? 6 ??? 3 ??? 8 ???? 1

Solution: D were calculated according to the respective levels of data, and then obtains D2 ��D2

?? A: The eight student test scores rank correlation coefficient of two is 0.857.

? Description: calculation procedures and methods see the table below.

? Rank correlation coefficient of two kinds of test calculation table

? Student Number ?? X ??? Y ??? D ?? D2 ?? 1

?? 2

3 ??

4 ??

5 ??

6 ??

7 ??

8 ?? 8 ??

4 ??

6 ??

?? 2

7 ??

3 ??

5 ??

17 ??

4

5

2

6

3

8

11

0

1

0

1

0

? -3

??? 1 0 ??

0 ??

?? 1

0 ??

?? 1

0 ??

?? 9

?? 0 n = 8??? ��D2 = 12

?

7. High school entrance exams male and female students' English scores in the table below, please correlation coefficient calculation English test scores and gender.

Gender above average below average sum M

Female 15

3631

1846

54 Total 5,149,100

A: The English test scores and gender �� correlation coefficient is -0.34 students.

8. Randomly selected 76 students from a school in which 50 people like sports, 26 people do not like sports, the school asked the students if the number of likes and dislikes sports a significant difference?

Solution: �� put forward the hypothesis H 0: There was no significant difference in the number of likes and dislikes sports. H 1: There are significant differences in the number of likes and dislikes sports. �� calculated ��2 first assume that the null hypothesis holds, the likes and dislikes of each half of the total number of the number of sports that are each 38 people. Theoretical frequency ft = 76 �� 2 = 38 calculating Chi-square according to the formula: �� Statistical decision df = K-1 = 2-1 = 1, check the Chi-square table obtained at 0.05 level of significance, ��2 = 3.84, at 0.01 significance level , ��2 = 6.63,7.58> 6.63, P <0.01. According to statistical decision rule ��2 test, and accept the alternative hypothesis (H 1) at a significance level of 0.01, which is the number of likes and dislikes sports are very significant differences.