CFA论坛 - Powered by Discuz! Board

标题: Reading 11: Hypothesis Testing - LOS g ～ Q1-2 [打印本页]

作者: mayanfang1 时间: 2009-1-13 16:19 标题: [2009] Session 3 - Reading 11: Hypothesis Testing - LOS g ～ Q1-2

Q1. Which of the following statements about parametric and nonparametric tests is least accurate?

A) The test of the difference in means is used when you are comparing means from two independent samples.

B) The test of the mean of the differences is used when performing a paired comparison.

C) Nonparametric tests rely on population parameters.

Q2. Which of the following statements about parametric and nonparametric tests is least accurate?

A) Nonparametric tests have fewer assumptions than parametric tests.

B) Nonparametric tests are often used in conjunction with parametric tests.

C) Parametric tests are most appropriate when a population is heavily skewed.

作者: mayanfang1 时间: 2009-1-13 16:21

答案和详解如下：

Q1. Which of the following statements about parametric and nonparametric tests is least accurate?

A) The test of the difference in means is used when you are comparing means from two independent samples.

B) The test of the mean of the differences is used when performing a paired comparison.

C) Nonparametric tests rely on population parameters.

Correct answer is C)

Nonparametric tests are not concerned with parameters; they make minimal assumptions about the population from which a sample comes. It is important to distinguish between the test of the difference in the means and the test of the mean of the differences. Also, it is important to understand that parametric tests rely on distributional assumptions, whereas nonparametric tests are not as strict regarding distributional properties.

Q2. Which of the following statements about parametric and nonparametric tests is least accurate?

A) Nonparametric tests have fewer assumptions than parametric tests.

B) Nonparametric tests are often used in conjunction with parametric tests.

C) Parametric tests are most appropriate when a population is heavily skewed.

Correct answer is C)

For a distribution that is non-normally distributed, a nonparametric test may be most appropriate. A nonparametric test tends to make minimal assumptions about the population, while parametric tests rely on assumptions regarding the distribution of the population. Both kinds of tests are often used in conjunction with one another.

作者: zeraeh 时间: 2009-2-17 21:57

看答案，谢谢LZ

作者: jacky_z 时间: 2009-2-25 21:19

Thanks

作者: 风烈 时间: 2009-2-26 03:43

谢谢楼主～

作者: hhzeng 时间: 2009-3-24 16:43

kkk

作者: hjl2000 时间: 2009-3-28 21:02

d

作者: connie198226 时间: 2009-4-3 01:43

ss

作者: hollyhe 时间: 2009-4-10 17:27

d

作者: gracesun 时间: 2009-4-11 06:14

 thanks

作者: 大狗狗 时间: 2009-4-18 14:43

k

作者: birdybirdy 时间: 2009-4-22 01:01

hi

作者: big36999 时间: 2009-4-24 07:29

xx

作者: dullmul 时间: 2009-5-3 14:43

thx

作者: xuxiaoning 时间: 2009-5-6 17:40

ok

作者: giolu 时间: 2009-5-6 20:28

 thanks

作者: vickyma 时间: 2009-5-7 22:23

3

作者: deqiang 时间: 2009-5-8 00:47

 ok

作者: Michjay 时间: 2009-5-11 01:32

a

作者: saint_zhu 时间: 2009-5-11 15:06

parametric

作者: gerda2000 时间: 2009-5-19 10:05

thanks

作者: zzjz 时间: 2009-5-19 21:09

thx

作者: helloalan 时间: 2009-5-21 12:16

 bc

作者: danqing66 时间: 2009-5-22 15:53

thanks

作者: ellenstone 时间: 2009-5-31 14:31

 re

作者: valvet 时间: 2009-6-3 13:17

bb

作者: kin009 时间: 2009-6-6 19:21

p

作者: albeecho 时间: 2009-6-7 13:05

Q6. Which of the following is the correct sequence of events for testing a hypothesis?

A) State the hypothesis, select the level of significance, compute the test statistic, formulate the decision rule, and make a decision.

B) State the hypothesis, formulate the decision rule, select the level of significance, compute the test statistic, and make a decision.

C) State the hypothesis, select the level of significance, formulate the decision rule, compute the test statistic, and make a decision.

Correct answer is C)

Depending upon the author there can be as many as seven steps in hypothesis testing which are:

1.    Stating the hypotheses.

2.    Identifying the test statistic and its probability distribution.

3.    Specifying the significance level.

4.    Stating the decision rule.

5.    Collecting the data and performing the calculations.

6.    Making the statistical decision.

7.    Making the economic or investment decision.

Q7. Which of the following statements about hypothesis testing is most accurate?

A) The probability of a Type I error is equal to the significance level of the test.

B) If you can disprove the null hypothesis, then you have proven the alternative hypothesis.

C) The power of a test is one minus the probability of a Type I error.

Correct answer is A)

The probability of getting a test statistic outside the critical value(s) when the null is ture is the level of significance and is the probability of a Type I error. The power of a test is 1 minus the probability of a Type II error. Hypothesis testing does not prove a hypothesis, we either reject the null or fail to reject it.

Q8. An analyst conducts a two-tailed z-test to determine if small cap returns are significantly different from 10%. The sample size was 200. The computed z-statistic is 2.3. Using a 5% level of significance, which statement is most accurate?

A) You cannot determine what to do with the information given.

B) Fail to reject the null hypothesis and conclude that small cap returns are close enough to 10% that we cannot say they are significantly different from 10%.

C) Reject the null hypothesis and conclude that small cap returns are significantly different from 10%.

Correct answer is C)

At the 5% level of significance the critical z-statistic for a two-tailed test is 1.96 (assuming a large sample size). The null hypothesis is H0: x = 10%. The alternative hypothesis is HA: x ≠ 10%. Because the computed z-statistic is greater than the critical z-statistic (2.33 > 1.96), we reject the null hypothesis and we conclude that small cap returns are significantly different than 10%.

Q9. An analyst conducts a two-tailed test to determine if mean earnings estimates are significantly different from reported earnings. The sample size is greater than 25 and the computed test statistic is 1.25. Using a 5% significance level, which of the following statements is most accurate?

A) The analyst should reject the null hypothesis and conclude that the earnings estimates are significantly different from reported earnings.

B) The analyst should fail to reject the null hypothesis and conclude that the earnings estimates are not significantly different from reported earnings.

C) To test the null hypothesis, the analyst must determine the exact sample size and calculate the degrees of freedom for the test.

Correct answer is B)

The null hypothesis is that earnings estimates are equal to reported earnings. To reject the null hypothesis, the calculated test statistic must fall outside the two critical values. IF the analyst tests the null hypothesis with a z-statistic, the crtical values at a 5% confidence level are ±1.96. Because the calculated test statistic, 1.25, lies between the two critical values, the analyst should fail to reject the null hypothesis and conclude that earnings estimates are not significantly different from reported earnings. If the analyst uses a t-statistic, the upper critical value will be even greater than 1.96, never less, so even without the exact degrees of freedom the analyst knows any t-test would fail to reject the null.

作者: 流浪狗 时间: 2009-7-7 23:43

[em56]

作者: ch_914 时间: 2009-7-20 19:19

THANKS

作者: jzwx 时间: 2009-7-27 16:03

thanks

作者: josephine_loh 时间: 2009-8-9 15:51

 tq

作者: cracy2749 时间: 2009-8-23 23:25

BC

作者: luodan0103 时间: 2009-9-2 19:25

thanks

作者: huangyichun 时间: 2009-9-7 22:23

thanks

作者: tobuketsu 时间: 2009-9-7 23:10 标题: re

 th

作者: lamchoonho 时间: 2009-9-9 18:23

  thamks

作者: doralin 时间: 2009-10-26 09:20

[em50]

作者: casey11 时间: 2009-10-27 17:43

11

作者: solitute 时间: 2009-10-31 17:31

thanks

作者: lqx1211 时间: 2009-11-4 14:10

a

作者: haisian 时间: 2009-11-8 22:07

O(∩_∩)O谢谢

作者: shjens 时间: 2009-11-17 09:03 标题: asd

assd

作者: shjens 时间: 2009-11-17 09:03 标题: sad

asd

作者: mellsa 时间: 2009-11-18 11:42

ff

作者: yangrucheng 时间: 2009-11-19 22:04

 thanks

作者: yangxi_sisi 时间: 2009-11-28 19:23

d

作者: jrxx99 时间: 2009-12-10 11:15

反复反复反复反复反复反复反复

作者: Vicky724 时间: 2009-12-15 06:53

w xi ang kan

作者: angelene1987815 时间: 2009-12-20 00:31

ok

作者: hehansheng 时间: 2009-12-28 14:47

thx

作者: ken_wangyang 时间: 2009-12-31 16:55

thanks

作者: rrwojia 时间: 2010-1-18 22:47

thx

作者: rivaldo11 时间: 2010-2-9 07:13

kk

作者: lwtzwy 时间: 2010-2-20 21:21

3

作者: flyingdance_nan 时间: 2010-3-11 02:35

great

作者: jerrywang0 时间: 2010-4-23 17:24

qqq

作者: 0939 时间: 2010-5-4 01:00

[em50] 

作者: shuru1207 时间: 2010-5-7 03:25

thnx

作者: chenxu200312 时间: 2010-5-22 08:18

d

作者: annyyu 时间: 2010-5-22 12:24

re

作者: lovemom 时间: 2010-7-13 01:05

thx

作者: corinnadeng 时间: 2010-8-5 04:00

c c

作者: dapeng731 时间: 2010-8-5 16:07

不错

作者: Anyone2010 时间: 2010-8-9 11:57

thks

作者: Anyone2010 时间: 2010-8-9 11:58

thks

作者: scofield1985 时间: 2010-10-13 22:42

d

作者: echopapa 时间: 2010-10-20 12:33

THX

作者: seraphiris0116 时间: 2010-11-9 20:00

thanks

作者: jingh1981 时间: 2010-11-20 05:15

thx

作者: tangfaxi 时间: 2010-11-21 16:22

多谢

作者: btz2009 时间: 2010-11-21 17:09

xiex

作者: leoniegolly 时间: 2010-11-22 19:32

3x

作者: chrisyikhei 时间: 2010-11-22 22:11

 dd

作者: khaipinglai 时间: 2010-11-26 18:12

thanks

作者: jc1188 时间: 2010-11-27 12:04

d

作者: 祈愿修神 时间: 2011-4-6 15:51

3

作者: petitemango 时间: 2011-4-21 13:42

 11

作者: kepei7763 时间: 2011-5-28 05:56

thx

作者: FOREVER396 时间: 2011-6-19 16:27

HAVE A LOOK

作者: shannyzheng 时间: 2011-8-11 16:21

let me have a see

作者: shing1314 时间: 2011-8-19 17:01

thanks for sharing

欢迎光临 CFA论坛 (http://forum.theanalystspace.com/)