nurrizkitazkiaaz-blog

[nurrizkitazkiaaz-blog]

Depressed People: Family History and Drugs/Alcohol Dependence Assignment #Week04: Graphing Data

The hypothesis I made on previous assignments from NESARC Study were that women tend to suffer from depression as nearly twice to men. Also, people who had suffered from depression are not associated to their family history who had had suffered from depression as well. And the last is that depressed people are not dependent to alcohol/drugs. So now I’m going to make it clear to be seen in graphical data which is bar chart since the explanatory variable and the respond variable for my study are categorical variables. Here is to you the bar charts that lead us to the hypothesis I have made.

We can’t say that most depressed people are alcohol dependence because among 1445 youth who suffered from depression, there are about 800 people who took alcohol to improve their mood which is only about 54% of them. The same thing we say about drugs/medicine dependence, there are only about a hundred youth who took drugs/medicine to improve their mood which is only about 7% of them. Finally, the last one is that count for youth suffered from depression and had mother suffered from depression too is only about 600 people which is about 41% of them, so we can’t say that there is any association between depressed people and their family history.

The last bar chart is sex bivariate graph that shows us the sex distribution who had mother suffered from depression too. Surprisingly, it turns out that men counts is slightly more than women counts.

[nurrizkitazkiaaz-blog]

Depressed People: Family History and Drugs/Alcohol Dependence Assignment #Week03: Replace Blank and Unknown Item to NaN and Youth Ages Grouping

On this assignment, I have just done replacing ‘blank’ and ‘unknown’ item to NaN and evaluating youth ages who suffered from depression. Even though the interval age of youth is 15 to 24 years old, on this assignment there will only be range of ages from 18 to 24 years old due to the NESARC data survey. So below are my script on python.

The results from the script shown above are as the same as last week assignment, but the only difference is that youth age grouping.

The results above show us that number of youth who suffered with depression is 1445 people with 61.18% of female and 38.82% of male. We can see another information about their family history, 41.18% of them had had their mothers suffered from depression as well. Besides, 14.81% of them did consume alcohol and 6.78% of them did consume drugs/medicine to improve their mood. I grouped youth ages into 5 groups, 15-16, 17-18, 19-20, 21-22, 23-24 years old. According to the result shown above, we can see that youth who mostly had had along with depression are youth at 23 to 24 years old.

[nurrizkitazkiaaz-blog]

Depressed People: Family History and Drugs/Alcohol DependenceAssignment #Week02: Call in Dataset (NESARC)

I choose python to write my 1st  program. The variables that I have chosen to work with were written on the 1st assignment last week. In this assignment, I made my own dataset called subset1 that categorized the respondents by age 15 to 24 called as youth (WHO reference) and have suffered depression. My script on call in NESARC dataset are written below.

 #depression and family history study

#depression and alcohol/drugs dependence study

import pandas

import numpy

 mynesarc = pandas.read_csv('nesarc_pds.csv', low_memory=False)

 #A bug fix for display formats to avoid run time errors

pandas.set_option("display.float_format", lambda x:"%f" %x)

 print(len(mynesarc)) #number of observations (rows)

print(len(mynesarc.columns)) #number of variables (columns)

 #Frequency of the variables I work with

print("counts for SEX")

sex = mynesarc.groupby("SEX").size()

print(sex)

 print("percentages for SEX")

sex = mynesarc.groupby("SEX").size()*100/len(mynesarc)

print(sex)

 print("counts for S4AQ1 - Felt depressed, sad, blue, or down for 2 weeks")

c1 = mynesarc["S4AQ1"].value_counts().sort_index(ascending=True)

print(c1)

 print("percentages for S4AQ1 - Felt depressed, sad, blue, or down for 2 weeks")

p1 = mynesarc.groupby("S4AQ1").size()*100/len(mynesarc)

print(p1)

 print("counts for S4AQ420A - Alcohol consume to improve mood")

c2 = mynesarc["S4AQ20A"].value_counts().sort_index(ascending=True)

print(c2)

 print("percentages for S4AQ20A - Alcohol consume to improve mood")

p2 = mynesarc.groupby("S4AQ20A").size()*100/len(mynesarc)

print(p2)

 print("counts for S4AQ21A - medicine/drug consume to improve mood")

c3 = mynesarc["S4AQ21A"].value_counts().sort_index(ascending=True)

print(c3)

 print("percentages for S4AQ21A - medicine/drug consume to improve mood")

p3 = mynesarc.groupby("S4AQ21A").size()*100/len(mynesarc)

print(p3)

 print("counts for S4BQ2 - Biological mother suffered from depression")

c4 = mynesarc["S4BQ2"].value_counts().sort_index(ascending=True)

print(c4)

 print("percentages for S4BQ2 - Biological mother suffered from depression")

p4 = mynesarc.groupby("S4BQ2").size()*100/len(mynesarc)

print(p4)

 #subset data to youth by range 15 to 24 (WHO reference) who have suffered from depression

subsetnew1 = mynesarc [(mynesarc["AGE"]>=15)&(mynesarc["AGE"]<=24)&(mynesarc["S4AQ1"]==1)]

 #copy of new subset1 data frame

subset1 = subsetnew1.copy()

 print("Counts for youth who have suffered from depression")

Count1 = subset1.groupby("S4AQ1").size()

print(Count1)

 print("percentages for youth who have suffered from depression")

Per1 = subset1.groupby("S4AQ1").size()*100/len(subset1)

print(Per1)

 print("Counts for SEX youth who have suffered from depression, 1=male")

Count2 = subset1.groupby("SEX").size()

print(Count2)

 print("percentages for SEX youth who have suffered from depression, 1=male")

Per2 = subset1.groupby("SEX").size()*100/len(subset1)

print(Per2)

 print("counts for youth AGE who have suffered from depression")

Count3 = subset1.groupby("AGE").size()

print(Count3)

 print("Percentages for youth AGE who have suffered from depression")

Per3 = subset1.groupby("AGE").size()*100/len(subset1)

print(Per3)

 print("counts for youth who have suffered from depression and had mother suffered from depression too, 1=yes")

Count4 = subset1.groupby("S4BQ2").size()

print(Count4)

 print("percentages for youth who have suffered from depression and had mother suffered from depression too, 1=yes")

Per4 = subset1.groupby("S4BQ2").size()*100/len(subset1)

print(Per4)

 print("Counts for youth who have suffered from depression and took alcohol to improve mood")

Count5 = subset1.groupby("S4AQ20A").size()

print(Count5)

 print("percentages for youth who have suffered from depression and took alcohol to improve mood")

Per5 = subset1.groupby("S4AQ20A").size()*100/len(subset1)

print(Per5)

 print("Counts for youth who have suffered from depression and took medicine/drugs to improve mood")

Count6 = subset1.groupby("S4AQ21A").size()

print(Count6)

 print("Percentages for youth who have suffered from depression and took medicine/drugs to improve mood")

 And the results of my own dataset are written below.

 Counts for youth who have suffered from depression

S4AQ1

1    1445

dtype: int64

Counts for SEX youth who have suffered from depression, 1=male

SEX

1    561

2    884

dtype: int64

percentages for SEX youth who have suffered from depression, 1=male

SEX

1    38.823529

2    61.176471

dtype: float64

counts for youth AGE who have suffered from depression

AGE

18    205

19    194

20    195

21    199

22    218

23    199

24    235

dtype: int64

Percentages for youth AGE who have suffered from depression

AGE

18    14.186851

19    13.425606

20    13.494810

21    13.771626

22    15.086505

23    13.771626

24    16.262976

dtype: float64

counts for youth who have suffered from depression and had mother suffered from depression too, 1=yes

S4BQ2

1    595

2    708

9    142

dtype: int64

percentages for youth who have suffered from depression and had mother suffered from depression too, 1=yes

S4BQ2

1    41.176471

2    48.996540

9     9.826990

dtype: float64

Counts for youth who have suffered from depression and took alcohol to improve mood

S4AQ20A

    453

1    214

2    776

9      2

dtype: int64

percentages for youth who have suffered from depression and took alcohol to improve mood

S4AQ20A

    31.349481

1    14.809689

2    53.702422

9     0.138408

dtype: float64

Counts for youth who have suffered from depression and took medicine/drugs to improve mood

S4AQ21A

    453

1     98

2    893

9      1

dtype: int64

Percentages for youth who have suffered from depression and took medicine/drugs to improve mood

S4AQ21A

    31.349481

1     6.782007

2    61.799308

9     0.069204

dtype: float64

 The results above show us that number of youth who suffered with depression is 1445 people with 61.18% of female and 38.82% of male. We can see another information about their family history, 41.18% of them had had their mothers suffered from depression as well. Besides, 14.81% of them did consume alcohol and 6.78% of them did consume drugs/medicine to improve their mood. Can we infer that women incline to suffer from depression as nearly twice to men? Also, can we say that there is no association between depressed people to their family history? And depressed people are not more likely to be alcohol/drugs dependence?

[nurrizkitazkiaaz-blog]

Depressed People: Family History and Drug/Alcohol Dependence Assignment #Week01: Getting your research project started

To complete on my research project, I decided to choose National Institute on Alcohol Abuse and Alcoholism (NESARC) datasets. My topic of interest is people who suffer major depression and seek if there any association between them and the family history of major depression.

I will also look if mostly the depressed people are addicted to alcohol/drugs.

 So, my research questions:

Is major depression associated to a family history?

Are depressed people more likely to be dependent to drugs/alcohol?

 Instead of using google scholar, I used Science Direct to help me find the references towards my research questions. I found a study done by van Oostrom et al in 2013[1], they found children of mothers with major depressive disorder (MDD) show stronger negative affective bias, a central cognitive dysfunction in MDD, than children with no ancestor suffered from depression. Other than that, Nierenberg et al in 2007 on their study found that people with positive family history of depression suffered the same thing in younger age of onset probands. Besides, they found that women tend to suffer with MDD twice as often if compared to men[2]. This conclusions of the research leads to a hypothesis of my 1st question research that major depression is associated to a family history especially female ancestor (i.e. mother) and women tend to suffer from MDD as twice to men.

Alcohol use disorders (AUD) study done by some researchers back in early 2000s have showed us that people with anxiety, depression, and stress suffer more addicted to alcohol and drugs than normal people. Because, they believe that drugs or alcohol would reduce their pain or negative emotions[3]. In addition, an AUD survey in 2015 in Hallgren study in 2018 found an inference that people with any mood disorder was 1.5 times higher addicted to drugs/alcohol compared to normal people[4]. My hypothesis is that people with MDD is much more to be alcohol or drugs dependence than normal people.

 These are variables I choose to help me answer my research questions from NESARC codebook:

Section 1: Background Information (Page 1)

Variable name (code, page)

Sex (SEX, 5)

Section 4A: Major Depression (Page 302)

Felt depressed, sad, blue, or down for 2 weeks? (S4AQ1, 302)

Suicide attempt? (S4AQ4A16, 305)

Did alcohol consume to improve mood? (S4AQ20A, 314)

Did medicine/drug consume to improve mood? (S4AQ21A, 314)

 Section 4B: Family History of Major Depression (Page 316)

Biological mother suffered from depression? (S4BQ2, 316)

References

[1]      I. van Oostrom et al., “Never-depressed females with a family history of depression demonstrate affective bias,” Psychiatry Res., vol. 205, no. 1–2, pp. 54–58, Jan. 2013, doi: 10.1016/j.psychres.2012.08.004.

[2]      A. A. Nierenberg et al., “Family history of mood disorder and characteristics of major depressive disorder: A STAR*D (sequenced treatment alternatives to relieve depression) study,” J. Psychiatr. Res., vol. 41, no. 3–4, pp. 214–221, Apr. 2007, doi: 10.1016/j.jpsychires.2006.02.005.

[3]      N. Fooladi, R. Jirdehi, and Z. Mohtasham-Amiri, “Comparison of Depression, Anxiety, Stress and Quality of life in Drug Abusers with Normal Subjects,” Procedia-Social Behav. Sci., vol. 159, pp. 712–717, 2014, doi: 10.1016/j.sbspro.2014.12.459.

[4]      M. Hallgren, “Exercise for Alcohol Use Disorders,” in Exercise-Based Interventions for Mental Illness, Elsevier, 2018, pp. 83–106.