MATH 1281 – Statistical Inference

University of the People

Math Assignment Unit 3

Microhabitat factors associated with forage and bed sites of barking deer in Hainan Island, China

were examined. In this region, woods make up 4.8% of the land, cultivated grass plot makes up

14.7%, and deciduous forests make up 39.6%. Of the 530 sites where the deer forage, 6 were

categorized as woods, 18 as cultivated grassplot, and 71 as deciduous forests. The table below

summarizes these data.

Habitat Count

Woods 6

Cultivated grassplot 18

Deciduous forests 71

others 435

Total 530

a. Hypotheses:

Null hypothesis (H₀): Barking deer do not prefer any particular habitat for foraging. The

proportions of sites in different habitats are equal to the proportions of those habitats in the

region.

Alternative hypothesis (H₁): Barking deer prefer certain habitats for foraging over others. The

proportions of sites in different habitats are not equal to the proportions of those habitats in the

region.
b. Type of Test:

We can use the chi-square goodness of fit test to answer this research question. This test will

compare the observed frequencies of the deer foraging sites to the expected frequencies based on

the habitat proportions (Diez, Barr, & Çetinkaya-Rundel, 2019).

c. Assumptions and Conditions:

The assumptions and conditions for the chi-square goodness of fit test are:

The data are frequencies or counts of cases.

The categories are mutually exclusive.

The expected frequency in each category should be at least 5 (Diez, Barr, & Çetinkaya-Rundel,

2019).

Let's check the expected frequencies:

Woods: 530×0.048= 25.44

Cultivated grassplot: 530×0.147=77.91

Deciduous forests: 530×0.396=209.88

Other: 530×0.409=216.77

All expected frequencies are greater than 5, so the conditions are satisfied.

d. Hypothesis Test:

To determine if these data provide convincing evidence that barking deer prefer to forage in

certain habitats over others, we will conduct the chi-square goodness of fit test.
Chi-squared statistic:

here Oi are the observed frequencies and Ei are the expected frequencies (Diez, Barr, &

Çetinkaya-Rundel, 2019).

X2 = 372.52

Degrees of Freedom:

df=k−1

where kkk is the number of categories (Diez, Barr, & Çetinkaya-Rundel, 2019).

df=4−1=3

Critical Value:

At a 5% significance level, the critical value for χ2 with 3 degrees of freedom is 7.815 (Diez,

Barr, & Çetinkaya-Rundel, 2019).

Given that the p-value is less than 0.001, we compare our calculated chi-squared statistic to the

critical value.
Since χ2=372.52 is much greater than the critical value of 7.815, we reject the null hypothesis.

Conclusion:

There is convincing evidence to suggest that barking deer prefer to forage in certain habitats over

others on Hainan Island, China.

Part II

The OpenIntro website occasionally experiments with design and link placement. We conducted

one experiment testing three different placements of a download link for this textbook on the

book’s main page to see which location, if any, led to the most downloads. The number of site

visitors included in the experiment was 501 and is captured in one of the response combinations

in the following table:

a. Calculate the actual number of site visitors in each of the six response categories:

Given the total number of site visitors is 501, we can calculate the actual number of site visitors

in each category by using the given percentages.

Position 1, Download=501×0.16=80.16≈80

Position 1, No Download= 501× 0.209= 104.709 ≈ 105

Position 2, No Download=501×0.212=106.212≈106

Position 3, Download=501×0.119=59.619≈60

Position 3, No Download=501×0.152=76.152≈76

The actual numbers in each category are approximately:

Position 1, Download: 80

Position 1, No Download: 105

Position 2, Download: 74

Position 2, No Download: 106

Position 3, Download: 60

Position 3, No Download: 76

b. Test for Group Imbalance:

We need to check if the groups were imbalanced. We can use the chi-square test for

independence to test this hypothesis. (Diez, Barr, & Çetinkaya-Rundel, 2019).

Hypotheses:
Null hypothesis (H₀): The groups are balanced. The proportions of site visitors in each response

category are equal.

Alternative hypothesis (H₁): The groups are not balanced. The proportions of site visitors in each

response category are not equal.

Expected Counts:

Since each individual had an equal chance of being in any of the three experiment groups, we

expect the total number of visitors to be evenly distributed among the groups.

Total visitors in Position 1=501× (1/3) =167

Total visitors in Position 2=501× (1/3) =167

Total visitors in Position 3=501× (1/3) =167

Thus, the expected counts for each category are:

Position 1, Download = 167 × (80/501) ≈ 26.7

Position 1, No Download = 167 × (105/501) ≈ 35

Position 2, Download = 167 × (74/501) ≈ 24.7

Position 2, No Download = 167 × (106/501) ≈ 35.3

Position 3, No Download = 167 × (76/501) ≈ 25.3

Chi-Squared Statistic:

where Oi are the observed frequencies and Ei are the expected frequencies (Diez, Barr, &

Çetinkaya-Rundel, 2019).

Using the calculated expected counts:

Degrees of Freedom:

df=(r−1)×(c−1)

where rrr is the number of rows and ccc is the number of columns.

df=(3−1)×(2−1)=2

Significance Level:

Using a significance level of 0.05.

Given the p-value of 0.01215, we can compare it to the significance level.

Since the p-value (0.01215) is less than the significance level (0.05), we reject the null

hypothesis.

Conclusion:
There is evidence to suggest that the groups were actually imbalanced, and the proportions of site

visitors in each response category are not equal.

References:

Diez, D. M., Barr, C. D., & Çetinkaya-Rundel, M. (2019). OpenIntro Statistics (4th ed.).

OpenIntro.